Linguistik
Refine
Year of publication
Document Type
- Article (186)
- Preprint (69)
- Part of a Book (65)
- Working Paper (40)
- Conference Proceeding (33)
- Book (24)
- Review (12)
- Part of Periodical (7)
- Course Material (1)
- Report (1)
Language
- Croatian (150)
- English (141)
- German (120)
- Portuguese (9)
- Turkish (7)
- mis (4)
- French (3)
- Italian (2)
- Multiple languages (1)
- Spanish (1)
Has Fulltext
- yes (438) (remove)
Is part of the Bibliography
- no (438)
Keywords
- Kroatisch (50)
- Linguistik (50)
- Rezension (48)
- Deutsch (35)
- Computerlinguistik (32)
- Syntax (19)
- Japanisch (18)
- Grammatik (17)
- Namenkunde (17)
- Rezensionen (17)
Institute
- Extern (438) (remove)
Unter Syntaktikern besteht generell die Tendenz, im Deutschen die Freiheit bezüglich der Positionierung der Adverbiale sogar für noch größer zu halten als die Freiheit der Positionierung der Argumente. Wie die Stellungsfreiheit der Argumente im Mittelfeld eines deutschen Satzes theoretisch zu erfassen sei, wird seit langer Zeit kontrovers diskutiert. Die Hauptfrage dreht sich darum, ob alle Serialisierungen der Argumente basisgeneriert sind oder ob es eine ausgezeichnete Serialisierung der Argumente, eine sogenannte Grundabfolge, gibt, aus der sämtliche anderen Aktantenserialisierungen durch eine Ableitungsoperation bzw. Bewegung zu gewinnen sind. Diese grundsätzlichen Fragen stellen sich auch bezüglich der Positionierungsmöglichkeiten der Adverbiale, auch wenn sie hierfür bei weitem nicht so häufig gestellt und diskutiert wurden.
Buli is an Oti-Volta tone language spoken in Northern Ghana. This paper outlines the basic features of its tonal system and explores whether and in which way pitch respectively phonemic tone is approached as a means to indicate the pragmatic category of focus. Pursued are cases with focus-related surface tone changes as well as cases where pitch could help to disambiguate between broad and narrow foci. It is argued that focus is not consistently encoded by pitch or tone. Parallel findings for the closely related languages Kopen o (phonetic symbol)nni and Dagbani suggest that the apparent lack of significant prosodic focus signals in Buli might pertain to a larger group of tonal languages of the Gur family.
The present article illustrates that the specific articulatory and aerodynamic requirements for voiced but not voiceless alveolar or dental stops can cause tongue tip retraction and tongue mid lowering and thus retroflexion of front coronals. This retroflexion is shown to have occurred diachronically in the three typologically unrelated languages Dhao (Malayo-Polynesian), Thulung (Sino-Tibetan), and Afar (East-Cushitic). In addition to the diachronic cases, we provide synchronic data for retroflexion from an articulatory study with four speakers of German, a language usually described as having alveolar stops. With these combined data we supply evidence that voiced retroflex stops (as the only retroflex segments in a language) did not necessarily emerge from implosives, as argued by Haudricourt (1950), Greenberg (1970), Bhat (1973), and Ohala (1983). Instead, we propose that the voiced front coronal plosive /d/ is generally articulated in a way that favours retroflexion, that is, with a smaller and more retracted place of articulation and a lower tongue and jaw position than /t/.
Woher kommt das neuerwachte Interesse an Sprachrichtigkeit? Woher kommt die ausgeprägte sprachliche Unsicherheit, die auch bei vielen hochgebildeten Menschen den Wunsch entstehen lässt, von Sprachpflegern über ihr Ureigenstes, nämlich ihre Muttersprache, belehrt zu werden? Obwohl Antworten auf diese Fragen letztlich spekulativ bleiben, wage ich doch die These, dass eine Ursache hierfür die Rechtschreibreform ist, die von einem Großteil der Bevölkerung nach wie vor nicht angenommen wird, die insgesamt weder zur Vereinfachung noch zu einer höheren Einheitlichkeit geführt hat; die aber andererseits ein öffentliches Nachdenken und Diskutieren über Sprachrichtigkeit in Gang setzte. – Jedenfalls ist die Verunsicherung ein Faktum, das von Linguisten nicht ignoriert werden sollte.
Ausgangspunkt: Die Kritik am "Zwei-Welten-Modell": Die grundlegende linguistische Unterscheidung zwischen "Sprache" und "Sprechen" ist im Rahmen der neueren Debatten um Sprachmedialität wieder verstärkt thematisiert und kritisiert worden. Lässt sich dieses schulbildende, in der Linguistik geradezu eherne Begriffspaar überhaupt noch sinnvollerweise aufrechterhalten? Oder muss es mindestens umdefiniert, vielleicht sogar gänzlich verworfen werden? Hat sich insbesondere die auf Chomsky zurückgehende Unterscheidung von Sprachkompetenz und -performanz nicht von selbst ad absurdum geführt, nachdem der linguistische Kognitivismus chomskyscher Provenienz Sprache als lebendiges Phänomen, als Medium menschlicher Kommunikation, vollständig aus dem Blick verloren hat? Führt nicht schon die scheinbar harmlose linguistische Differenzierung zwischen einer Sprachregel und ihrer Anwendung zu einer irreführenden und unangemessenen Verdinglichung von Sprache? ...
The medium of (oral) language is mostly disregarded (or overlooked) in contemporary media theories. This "ignoring of language" in media studies is often accompanied by an inadequate transport model of communication, and it converges with an "ignoring of mediality" in mentalistic theories of language. In the present article it will be argued that this misleading opposition of language and media can only be overcome if one already regards oral language, not just written language, as a medium of the human mind. In my argumentation I fall back on Wittgenstein’s conception of language games to try to show how Wittgenstein’s ideas can help us to clear up the problem of the mediality of language and also to show to what extent the mentalistic conception of Chomskyan provenance cannot be adequate to the phenomenon of language.
In this paper, we argue that difficulties in the definition of coreference itself contribute to lower inter-annotator agreement in certain cases. Data from a large referentially annotated corpus serves to corroborate this point, using a quantitative investigation to assess which effects or problems are likely to be the most prominent. Several examples where such problems occur are discussed in more detail, and we then propose a generalisation of Poesio, Reyle and Stevenson’s Justified Sloppiness Hypothesis to provide a unified model for these cases of disagreement and argue that a deeper understanding of the phenomena involved allows to tackle problematic cases in a more principled fashion than would be possible using only pre-theoretic intuitions.
Traditionally, parsers are evaluated against gold standard test data. This can cause problems if there is a mismatch between the data structures and representations used by the parser and the gold standard. A particular case in point is German, for which two treebanks (TiGer and TüBa-D/Z) are available with highly different annotation schemes for the acquisition of (e.g.) PCFG parsers. The differences between the TiGer and TüBa-D/Z annotation schemes make fair and unbiased parser evaluation difficult [7, 9, 12]. The resource (TEPACOC) presented in this paper takes a different approach to parser evaluation: instead of providing evaluation data in a single annotation scheme, TEPACOC uses comparable sentences and their annotations for 5 selected key grammatical phenomena (with 20 sentences each per phenomena) from both TiGer and TüBa-D/Z resources. This provides a 2 times 100 sentence comparable testsuite which allows us to evaluate TiGer-trained parsers against the TiGer part of TEPACOC, and TüBa-D/Z-trained parsers against the TüBa-D/Z part of TEPACOC for key phenomena, instead of comparing them against a single (and potentially biased) gold standard. To overcome the problem of inconsistency in human evaluation and to bridge the gap between the two different annotation schemes, we provide an extensive error classification, which enables us to compare parser output across the two different treebanks. In the remaining part of the paper we present the testsuite and describe the grammatical phenomena covered in the data. We discuss the different annotation strategies used in the two treebanks to encode these phenomena and present our error classification of potential parser errors.
Nous présentons ici différents algorithmes d’analyse pour grammaires à concaténation d’intervalles (Range Concatenation Grammar, RCG), dont un nouvel algorithme de type Earley, dans le paradigme de l’analyse déductive. Notre travail est motivé par l’intérêt porté récemment à ce type de grammaire, et comble un manque dans la littérature existante.
Die Ressource "Wissen" rückte in den letzten Jahrzehnten als Quelle wissenschaftlicher Innovation immer stärker ins Zentrum des Interesses. Diese Fokussierung mündete in eine Selbstreflexion der Wissenschaft und der wissenschaftlichen Disziplinen: Thematisiert werden vor allem die Art und Weise, wie Wissen gewonnen wird, sowie die damit zusammenhängende Frage nach der Konstruktion von Wissenschaftlichkeit, womit das Bewusstsein gleichzeitig auf die mehr und mehr sich auflösende Abgrenzung zwischen den Disziplinen beziehungsweise zwischen den drei hauptsächlichen Wissenschaftskulturen, von Natur-, Geistes- und Kultur- sowie Sozialwissenschaften gelenkt wird. Innerhalb und außerhalb der Universitäten bildeten und bilden sich nicht immer klar verortbare "trading zones" (Gallison 1997), in denen neue Formen und Techniken der Wissensproduktion und Wissensvermittlung geprüft, geübt und teilweise auch institutionalisiert werden. ...
Distributional approximations to lexical semantics are very useful not only in helping the creation of lexical semantic resources (Kilgariff et al., 2004; Snow et al., 2006), but also when directly applied in tasks that can benefit from large-coverage semantic knowledge such as coreference resolution (Poesio et al., 1998; Gasperin and Vieira, 2004; Versley, 2007), word sense disambiguation (Mc- Carthy et al., 2004) or semantical role labeling (Gordon and Swanson, 2007). We present a model that is built from Webbased corpora using both shallow patterns for grammatical and semantic relations and a window-based approach, using singular value decomposition to decorrelate the feature space which is otherwise too heavily influenced by the skewed topic distribution of Web corpora.
Parsing coordinations
(2009)
The present paper is concerned with statistical parsing of constituent structures in German. The paper presents four experiments that aim at improving parsing performance of coordinate structure: 1) reranking the n-best parses of a PCFG parser, 2) enriching the input to a PCFG parser by gold scopes for any conjunct, 3) reranking the parser output for all possible scopes for conjuncts that are permissible with regard to clause structure. Experiment 4 reranks a combination of parses from experiments 1 and 3. The experiments presented show that n- best parsing combined with reranking improves results by a large margin. Providing the parser with different scope possibilities and reranking the resulting parses results in an increase in F-score from 69.76 for the baseline to 74.69. While the F-score is similar to the one of the first experiment (n-best parsing and reranking), the first experiment results in higher recall (75.48% vs. 73.69%) and the third one in higher precision (75.43% vs. 73.26%). Combining the two methods results in the best result with an F-score of 76.69.
Trubetzkoy's recognition of a delimitative function of phonology, serving to signal boundaries between morphological units, is expressed in terms of alignment constraints in Optimality Theory, where the relevant constraints require specific morphological boundaries to coincide with phonological structure (Trubetzkoy 1936, 1939, McCarthy & Prince 1993). The approach pursued in the present article is to investigate the distribution of phonological boundary signals to gain insight into the criteria underlying morphological analysis. The evidence from English and Swedish suggests that necessary and sufficient conditions for word-internal morphological analysis concern the recognizability of head constituents, which include the rightmost members of compounds and head affixes. The claim is that the stability of word-internal boundary effects in historical perspective cannot in general be sufficiently explained in terms of memorization and imitation of phonological word form. Rather, these effects indicate a morphological parsing mechanism based on the recognition of word-internal head constituents. Head affixes can be shown to contrast systematically with modifying affixes with respect to syntactic function, semantic content, and prosodic properties. That is, head affixes, which cannot be omitted, often lack inherent meaning and have relatively unmarked boundaries, which can be obscured entirely under specific phonological conditions. By contrast, modifying affixes, which can be omitted, consistently have inherent meaning and have stronger boundaries, which resist prosodic fusion in all phonological contexts. While these correlations are hardly specific to English and Swedish it remains to be investigated to which extent they hold cross-linguistically. The observation that some of the constituents identified on the basis of prosodic evidence lack inherent meaning raises the issue of compositionality. I will argue that certain systematic aspects of word meaning cannot be captured with reference to the syntagmatic level, but require reference to the paradigmatic level instead. The assumption is then that there are two dimensions of morphological analysis: syntagmatic analysis, which centers on the criteria for decomposing words in terms of labelled constituents, and paradigmatic analysis, which centers on the criteria for establishing relations among (whole) words in the mental lexicon. While meaning is intrinsically connected with paradigmatic analysis (e.g. base relations, oppositeness) it is not essential to syntagmatic analysis.
Mit Erstaunen stellen LinguistInnen aus Deutschland, Österreich und der Schweiz immer wieder fest, dass sich in der "kleinen" Schweiz der geschlechtergerechte Sprachgebrauch in Öffentlichkeit und Alltag weit stärker durchgesetzt hat als in den anderen deutschsprachigen Ländern. Diese Einschätzung gilt es hier zu überprüfen und, falls sie zutrifft, zu belegen. Ausserdem werden - als erster Schritt fur weitere Untersuchungen - Thesen formuliert, die Erklärungen liefern, worauf diese Entwicklung zurückgeführt werden kann. Mit diesem Artikel geben wir anband von ausgewählten, konkreten Beispielen einen Einblick in die Situation, wie sie sich zur Zeit in der Schweiz präsentiert. Wir konzentrieren uns - unter sprachsoziologischer Perspektive - auf eine erste Bestandesaufnahme mit dem Blick auf die Diskussion in den Medien, die Institutionalisierung und die Einstellungen, die die spezifische sprachliche Situation in der Deutschschweiz prägen. Einen Rahmen fur unsere Untersuchung bilden die Überlegungen von Schräpel (SCHRÄPEL 1986), die die Auseinandersetzung um nichtsexistische Sprache als ein besonderes Sprachwandelphänomen untersucht. Sprachwandel im Vollzug ist einerseits einfacher zu erfassen als einer, der weiter zurückliegt, andererseits erschwert die Fülle des greifbaren Materials auch den Durchblick und das klare Erkennen von Tendenzen. Aus diesem Grund werten wir unser Datenmaterial nicht quantitativ aus, sondern konzentrieren uns darauf, für verschiedene Aspekte typische Beispiele zu geben und so den Stand der öffentlichen Diskussion und die Breite der vertretenen Meinungen darzustellen. Es wäre verlockend, das hier vorliegende Material auch allgemeinerer Form unter der Thematik "Sprachkritik" oder "Einstellungen" zu analysieren. Dies ist jedoch nicht im Zentrum unserer Fragestellung, weshalb wir bei einigen Beispielen auf entsprechende Untersuchungen (z.B. BLAUBERGS 1980, SCHOENTHAL 1989) verweisen.
Intimität und Geschlecht : zur Syntax und Pragmatik der Anrede im Liebesbrief des 20. Jahrhunderts
(2000)
Die Trennung der Lebenswelt in Privatsphäre und Öffentlichkeit käme der Verortung von Intimität entgegen. Es scheint aber, als ob Intimität nicht einem klar abgegrenzten Bereich zugeordnet werden kann, sondern nunmehr als relationale Kategorie zu fassen ist. Gerade der historische Vergleich (Vgl. CORBIN 1992) erlaubt weder einheitlich räumliche oder körperliche noch ästhetische Kriterien zur Abgrenzung von Intimität. ...
Das ausgehende 19. und beginnende 20. Jahrhundert setzt sich von den erkenntnistheoretischen Konzepten der vorangegangenen Zeit deutlich ab:Während – stark vereinfacht – die Philosophie bis dahin die Möglichkeit der Erkenntnis entweder in der subjektiven oder objektiven Dimension zu finden glaubte,wobei die Funktion der Sprache im Erkenntnisprozess kaum hinterfragt wurde, wird zur Jahrhundertwende eine Tendenz deutlich, die einerseits die Adäquatheit der sprachlichen Vermittlung entweder in Frage stellt oder zumindest thematisiert, andererseits die tradierten Erkenntnismodi neu reflektiert oder ihnen sogar den Rücken kehrt.
This paper describes the creation and preparation of TUSNELDA, a collection of corpus data built for linguistic research. This collection contains a number of linguistically annotated corpora which differ in various aspects such as language, text sorts / data types, encoded annotation levels, and linguistic theories underlying the annotation. The paper focuses on this variation on the one hand and the way how these heterogeneous data are integrated into one resource on the other hand.
We adopt Markert and Nissim (2005)’s approach of using the World Wide Web to resolve cases of coreferent bridging for German and discuss the strength and weaknesses of this approach. As the general approach of using surface patterns to get information on ontological relations between lexical items has only been tried on English, it is also interesting to see whether the approach works for German as well as it does for English and what differences between these languages need to be accounted for. We also present a novel approach for combining several patterns that yields an ensemble that outperforms the best-performing single patterns in terms of both precision and recall.
When a statistical parser is trained on one treebank, one usually tests it on another portion of the same treebank, partly due to the fact that a comparable annotation format is needed for testing. But the user of a parser may not be interested in parsing sentences from the same newspaper all over, or even wants syntactic annotations for a slightly different text type. Gildea (2001) for instance found that a parser trained on the WSJ portion of the Penn Treebank performs less well on the Brown corpus (the subset that is available in the PTB bracketing format) than a parser that has been trained only on the Brown corpus, although the latter one has only half as many sentences as the former. Additionally, a parser trained on both the WSJ and Brown corpora performs less well on the Brown corpus than on the WSJ one. This leads us to the following questions that we would like to address in this paper: - Is there a difference in usefulness of techniques that are used to improve parser performance between the same-corpus and the different-corpus case? - Are different types of parsers (rule-based and statistical) equally sensitive to corpus variation? To achieve this, we compared the quality of the parses of a hand-crafted constraint-based parser and a statistical PCFG-based parser that was trained on a treebank of German newspaper text.
In the past, a divide could be seen between ’deep’ parsers on the one hand, which construct a semantic representation out of their input, but usually have significant coverage problems, and more robust parsers on the other hand, which are usually based on a (statistical) model derived from a treebank and have larger coverage, but leave the problem of semantic interpretation to the user. More recently, approaches have emerged that combine the robustness of datadriven (statistical) models with more detailed linguistic interpretation such that the output could be used for deeper semantic analysis. Cahill et al. (2002) use a PCFG-based parsing model in combination with a set of principles and heuristics to derive functional (f-)structures of Lexical-Functional Grammar (LFG). They show that the derived functional structures have a better quality than those generated by a parser based on a state-of-the-art hand-crafted LFG grammar. Advocates of Dependency Grammar usually point out that dependencies already are a semantically meaningful representation (cf. Menzel, 2003). However, parsers based on dependency grammar normally create underspecified representations with respect to certain phenomena such as coordination, apposition and control structures. In these areas they are too "shallow" to be directly used for semantic interpretation. In this paper, we adopt a similar approach to Cahill et al. (2002) using a dependency-based analysis to derive functional structure, and demonstrate the feasibility of this approach using German data. A major focus of our discussion is on the treatment of coordination and other potentially underspecified structures of the dependency data input. F-structure is one of the two core levels of syntactic representation in LFG (Bresnan, 2001). Independently of surface order, it encodes abstract syntactic functions that constitute predicate argument structure and other dependency relations such as subject, predicate, adjunct, but also further semantic information such as the semantic type of an adjunct (e.g. directional). Normally f-structure is captured as a recursive attribute value matrix, which is isomorphic to a directed graph representation. Figure 5 depicts an example target f-structure. As mentioned earlier, these deeper-level dependency relations can be used to construct logical forms as in the approaches of van Genabith and Crouch (1996), who construct underspecified discourse representations (UDRSs), and Spreyer and Frank (2005), who have robust minimal recursion semantics (RMRS) as their target representation. We therefore think that f-structures are a suitable target representation for automatic syntactic analysis in a larger pipeline of mapping text to interpretation. In this paper, we report on the conversion from dependency structures to fstructure. Firstly, we evaluate the f-structure conversion in isolation, starting from hand-corrected dependencies based on the TüBa-D/Z treebank and Versley (2005)´s conversion. Secondly, we start from tokenized text to evaluate the combined process of automatic parsing (using Foth and Menzel (2006)´s parser) and f-structure conversion. As a test set, we randomly selected 100 sentences from TüBa-D/Z which we annotated using a scheme very close to that of the TiGer Dependency Bank (Forst et al., 2004). In the next section, we sketch dependency analysis, the underlying theory of our input representations, and introduce four different representations of coordination. We also describe Weighted Constraint Dependency Grammar (WCDG), the dependency parsing formalism that we use in our experiments. Section 3 characterises the conversion of dependencies to f-structures. Our evaluation is presented in section 4, and finally, section 5 summarises our results and gives an overview of problems remaining to be solved.
This paper is concerned with the tagging of spatial expressions in German newspaper articles, assigning a meaning to the expression and classifying the usages of the spatial expression and linking the derived referent to an event description. In our system, we implemented the activation of concepts in a very simple fashion, a concept is activated once (with a cost depending on the item that activated it) and is left activated thereafter. As an example, a city also activates the nodes for the region and the country it is part of, so that cities from one country are chosen over cities from different countries. A test corpus of 12 German newspaper articles was tested regarding several disambiguation strategies. Disambiguation was carried out via a beam search to find an approximately cost-optimal solution for the conflict set of potential grounding candidates for the tagged spatial expression. Test showed that the disambiguation strategies improved accuracy significantly.
Using a qualitative analysis of disagreements from a referentially annotated newspaper corpus, we show that, in coreference annotation, vague referents are prone to greater disagreement. We show how potentially problematic cases can be dealt with in a way that is practical even for larger-scale annotation, considering a real-world example from newspaper text.
We investigate methods to improve the recall in coreference resolution by also trying to resolve those definite descriptions where no earlier mention of the referent shares the same lexical head (coreferent bridging). The problem, which is notably harder than identifying coreference relations among mentions which have the same lexical head, has been tackled with several rather different approaches, and we attempt to provide a meaningful classification along with a quantitative comparison. Based on the different merits of the methods, we discuss possibilities to improve them and show how they can be effectively combined.
In this paper, we investigate the usefulness of a wide range of features for their usefulness in the resolution of nominal coreference, both as hard constraints (i.e. completely removing elements from the list of possible candidates) as well as soft constraints (where a cumulation of violations of soft constraints will make it less likely that a candidate is chosen as the antecedent). We present a state of the art system based on such constraints and weights estimated with a maximum entropy model, using lexical information to resolve cases of coreferent bridging.
In recent years, research in parsing has extended in several new directions. One of these directions is concerned with parsing languages other than English. Treebanks have become available for many European languages, but also for Arabic, Chinese, or Japanese. However, it was shown that parsing results on these treebanks depend on the types of treebank annotations used. Another direction in parsing research is the development of dependency parsers. Dependency parsing profits from the non-hierarchical nature of dependency relations, thus lexical information can be included in the parsing process in a much more natural way. Especially machine learning based approaches are very successful (cf. e.g.). The results achieved by these dependency parsers are very competitive although comparisons are difficult because of the differences in annotation. For English, the Penn Treebank has been converted to dependencies. For this version, Nivre et al. report an accuracy rate of 86.3%, as compared to an F-score of 92.1 for Charniaks parser. The Penn Chinese Treebank is also available in a constituent and a dependency representations. The best results reported for parsing experiments with this treebank give an F-score of 81.8 for the constituent version and 79.8% accuracy for the dependency version. The general trend in comparisons between constituent and dependency parsers is that the dependency parser performs slightly worse than the constituent parser. The only exception occurs for German, where F-scores for constituent plus grammatical function parses range between 51.4 and 75.3, depending on the treebank, NEGRA or TüBa-D/Z. The dependency parser based on a converted version of Tüba-D/Z, in contrast, reached an accuracy of 83.4%, i.e. 12 percent points better than the best constituent analysis including grammatical functions.
This paper profiles significant differences in syntactic distribution and differences in word class frequencies for two treebanks of spoken and written German: the TüBa-D/S, a treebank of transliterated spontaneous dialogues, and the TüBa-D/Z treebank of newspaper articles published in the German daily newspaper die tageszeitung´(taz). The approach can be used more generally as a means of distinguishing and classifying language corpora of different genres.
This paper profiles significant differences in syntactic distribution and differences in word class frequencies for two treebanks of spoken and written German: the TüBa-D/S, a treebank of transliterated spontaneous dialogs, and the TüBa-D/Z treebank of newspaper articles published in the German daily newspaper ´die tageszeitung´(taz). The approach can be used more generally as a means of distinguishing and classifying language corpora of different genres.
This paper presents an approach to the question whether it is possible to construct a parser based on ideas from case-based reasoning. Such a parser would employ a partial analysis of the input sentence to select a (nearly) complete syntax tree and then adapt this tree to the input sentence. The experiments performed on German data from the Tüba-D/Z treebank and the KaRoPars partial parser show that a wide range of levels of generality can be reached, depending on which types of information are used to determine the similarity between input sentence and training sentences. The results are such that it is possible to construct a case-based parser. The optimal setting out of those presented here need to be determined empirically.
Quantitative evaluation of parsers has traditionally centered around the PARSEVAL measures of crossing brackets, (labeled) precision, and (labeled) recall. However, it is well known that these measures do not give an accurate picture of the quality of the parsers output. Furthermore, we will show that they are especially unsuited for partial parsers. In recent years, research has concentrated on dependencybased evaluation measures. We will show in this paper that such a dependency-based evaluation scheme is particularly suitable for partial parsers. TüBa-D, the treebank used here for evaluation, contains all the necessary dependency information so that the conversion of trees into a dependency structure does not have to rely on heuristics. Therefore, the dependency representations are not only reliable, they are also linguistically motivated and can be used for linguistic purposes.
The purpose of this paper is to describe the TüBa-D/Z treebank of written German and to compare it to the independently developed TIGER treebank (Brants et al., 2002). Both treebanks, TIGER and TüBa-D/Z, use an annotation framework that is based on phrase structure grammar and that is enhanced by a level of predicate-argument structure. The comparison between the annotation schemes of the two treebanks focuses on the different treatments of free word order and discontinuous constituents in German as well as on differences in phrase-internal annotation.
The ACL 2008 Workshop on Parsing German features a shared task on parsing German. The goal of the shared task was to find reasons for the radically different behavior of parsers on the different treebanks and between constituent and dependency representations. In this paper, we describe the task and the data sets. In addition, we provide an overview of the test results and a first analysis.
The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, we define the tasks of the different tracks and describe how the data sets were created from existing treebanks for ten languages. In addition, we characterize the different approaches of the participating systems, report the test results, and provide a first analysis of these results.
Recent approaches to Word Sense Disambiguation (WSD) generally fall into two classes: (1) information-intensive approaches and (2) information-poor approaches. Our hypothesis is that for memory-based learning (MBL), a reduced amount of data is more beneficial than the full range of features used in the past. Our experiments show that MBL combined with a restricted set of features and a feature selection method that minimizes the feature set leads to competitive results, outperforming all systems that participated in the SENSEVAL-3 competition on the Romanian data. Thus, with this specific method, a tightly controlled feature set improves the accuracy of the classifier, reaching 74.0% in the fine-grained and 78.7% in the coarse-grained evaluation.
Das Chunkparsing bietet einen besonders vielversprechenden Ansatz zum robusten, partiellen Parsing mit dem Ziel einer breiten Datenabdeckung. Ziel beim Chunkparsing ist eine partielle, nicht-rekursive syntaktische Struktur. Dieser extrem effiziente Parsing-Ansatz läßt sich als Kaskade endlicher Transducer realisieren. In diesem Beitrag wird TüSBL vorgestellt, ein System, bei dem die Eingabe aus spontaner, gesprochener Spache besteht, die dem Parser in Form eines Worthypothesengraphen aus einem Spracherkenner zur Verfügung gestellt wird. Chunkparsing ist für eine solche Anwendung besonders geeignet, da es fragmentarische oder nicht wohlgeformte Äußerungen robust behandeln kann. Des weiteren wird eine Baumkonstruktionskomponente vorgestellt, die die partiellen Chunkstrukturen zu vollständigen Bäumen mit grammatischen Funktionen erweitert. Das System wird anhand manuell überprüfter Systemeingaben evaluiert, da sich die üblichen Evaluationsparameter hierfür nicht eignen.
The purpose of this paper is to describe recent developments in the morphological, syntactic, and semantic annotation of the TüBa-D/Z treebank of German. The TüBa-D/Z annotation scheme is derived from the Verbmobil treebank of spoken German [4, 10], but has been extended along various dimensions to accommodate the characteristics of written texts. TüBa-D/Z uses as its data source the "die tageszeitung" (taz) newspaper corpus. The Verbmobil treebank annotation scheme distinguishes four levels of syntactic constituency: the lexical level, the phrasal level, the level of topological fields, and the clausal level. The primary ordering principle of a clause is the inventory of topological fields, which characterize the word order regularities among different clause types of German, and which are widely accepted among descriptive linguists of German [3, 6]. The TüBa-D/Z annotation relies on a context-free backbone (i.e. proper trees without crossing branches) of phrase structure combined with edge labels that specify the grammatical function of the phrase in question. The syntactic annotation scheme of the TüBa-D/Z is described in more detail in [12, 11]. TüBa-D/Z currently comprises approximately 15 000 sentences, with approximately 7 000 sentences being in the correction phase. The latter will be released along with an updated version of the existing treebank before the end of this year. The treebank is available in an XML format, in the NEGRA export format [1] and in the Penn treebank bracketing format. The XML format contains all types of information as described above, the NEGRA export format contains all sentenceinternal information while the Penn treebank format includes only those layers of information that can be expressed as pure tree structures. Over the course of the last year, more fine grained linguistic annotations have been added along the following dimensions: 1. the basic Stuttgart-Tübingen tagset, STTS, [9] labels have been enriched by relevant features of inflectional morphology, 2. named entity information has been encoded as part of the syntactic annotation, and 3. a set of anaphoric and coreference relations has been added to link referentially dependent noun phrases. In the following sections, we will describe each of these innovations in turn and will demonstrate how the additional annotations can be incorporated into one comprehensive annotation scheme.
Part-of-Speech tagging is generally performed by Markov models, based on bigram or trigram models. While Markov models have a strong concentration on the left context of a word, many languages require the inclusion of right context for correct disambiguation. We show for German that the best results are reached by a combination of left and right context. If only left context is available, then changing the direction of analysis and going from right to left improves the results. In a version of MBT (Daelemans et al., 1996) with default parameter settings, the inclusion of the right context improved POS tagging accuracy from 94.00% to 96.08%, thus corroborating our hypothesis. The version with optimized parameters reaches 96.73%.
The definition of similarity between sentences is formulated on the levels of words, POS tags, and chunks (Abney 91; Abney 96). The evaluation of this approach shows that while precision and recall based on the PARSEVAL measures (Black et al. 91) do not reach state of the art Parsers yet (F1=87.19 on syntactic constituents, F1=77.78 including functionargument structure), the parser shows a very reliable performance where function-argument structure is concerned (F1=96.52). The lower F-scores are very often due to unattached constituents.
The problem of vocalization, or diacritization, is essential to many tasks in Arabic NLP. Arabic is generally written without the short vowels, which leads to one written form having several pronunciations with each pronunciation carrying its own meaning(s). In the experiments reported here, we define vocalization as a classification problem in which we decide for each character in the unvocalized word whether it is followed by a short vowel. We investigate the importance of different types of context. Our results show that the combination of using memory-based learning with only a word internal context leads to a word error rate of 6.64%. If a lexical context is added, the results deteriorate slowly.
In syntax, the trend nowadays is towards lexicalized grammar formalisms. It is now widely accepted that dividing words into wordclasses may serve as a laborsaving mechanism - but at the same time, it discards all detailed information on the idiosyncratic behavior of words. And that is exactly the type of information that may be necessary in order to parse a sentence. For learning approaches, however, lexicalized grammars represent a challenge for the very reason that they include so much detailed and specific information, which is difficult to learn. This paper will present an algorithm for learning a link grammar of German. The problem of data sparseness is tackled by using all the available information from partial parses as well as from an existing grammar fragment and a tagger. This is a report about work in progress so there are no representative results available yet.
This paper presents a comparative study of probabilistic treebank parsing of German, using the Negra and TüBa-D/Z treebanks. Experiments with the Stanford parser, which uses a factored PCFG and dependency model, show that, contrary to previous claims for other parsers, lexicalization of PCFG models boosts parsing performance for both treebanks. The experiments also show that there is a big difference in parsing performance, when trained on the Negra and on the TüBa-D/Z treebanks. Parser performance for the models trained on TüBa-D/Z are comparable to parsing results for English with the Stanford parser, when trained on the Penn treebank. This comparison at least suggests that German is not harder to parse than its West-Germanic neighbor language English.
How to compare treebanks
(2008)
Recent years have seen an increasing interest in developing standards for linguistic annotation, with a focus on the interoperability of the resources. This effort, however, requires a profound knowledge of the advantages and disadvantages of linguistic annotation schemes in order to avoid importing the flaws and weaknesses of existing encoding schemes into the new standards. This paper addresses the question how to compare syntactically annotated corpora and gain insights into the usefulness of specific design decisions. We present an exhaustive evaluation of two German treebanks with crucially different encoding schemes. We evaluate three different parsers trained on the two treebanks and compare results using EVALB, the Leaf-Ancestor metric, and a dependency-based evaluation. Furthermore, we present TePaCoC, a new testsuite for the evaluation of parsers on complex German grammatical constructions. The testsuite provides a well thought-out error classification, which enables us to compare parser output for parsers trained on treebanks with different encoding schemes and provides interesting insights into the impact of treebank annotation schemes on specific constructions like PP attachment or non-constituent coordination.
In the last decade, the Penn treebank has become the standard data set for evaluating parsers. The fact that most parsers are solely evaluated on this specific data set leaves the question unanswered how much these results depend on the annotation scheme of the treebank. In this paper, we will investigate the influence which different decisions in the annotation schemes of treebanks have on parsing. The investigation uses the comparison of similar treebanks of German, NEGRA and TüBa-D/Z, which are subsequently modified to allow a comparison of the differences. The results show that deleted unary nodes and a flat phrase structure have a negative influence on parsing quality while a flat clause structure has a positive influence.
Transforming constituent-based annotation into dependency-based annotation has been shown to work for different treebanks and annotation schemes (e.g. Lin (1995) has transformed the Penn treebank, and Kübler and Telljohann (2002) the Tübinger Baumbank des Deutschen (TüBa-D/Z)). These ventures are usually triggered by the conflict between theory-neutral annotation, that targets most needs of a wider audience, and theory-specific annotation, that provides more fine-grained information for a smaller audience. As a compromise, it has been pointed out that treebanks can be designed to support more than one theory from the start (Nivre, 2003). We argue that information can also be added to an existing annotation scheme so that it supports additional theory-specific annotations. We also argue that such a transformation is useful for improving and extending the original annotation scheme with respect to both ambiguous annotation and annotation errors. We show this by analysing problems that arise when generating dependency information from the constituent-based TüBa-D/Z.
Chunk parsing has focused on the recognition of partial constituent structures at the level of individual chunks. Little attention has been paid to the question of how such partial analyses can be combined into larger structures for complete utterances. Such larger structures are not only desirable for a deeper syntactic analysis. They also constitute a necessary prerequisite for assigning function-argument structure. The present paper offers a similaritybased algorithm for assigning functional labels such as subject, object, head, complement, etc. to complete syntactic structures on the basis of prechunked input. The evaluation of the algorithm has concentrated on measuring the quality of functional labels. It was performed on a German and an English treebank using two different annotation schemes at the level of function argument structure. The results of 89.73% correct functional labels for German and 90.40%for English validate the general approach.
In this paper, we investigate the role of sub-optimality in training data for part-of-speech tagging. In particular, we examine to what extent the size of the training corpus and certain types of errors in it affect the performance of the tagger. We distinguish four types of errors: If a word is assigned a wrong tag, this tag can belong to the ambiguity class of the word (i.e. to the set of possible tags for that word) or not; furthermore, the major syntactic category (e.g. "N" or "V") can be correctly assigned (e.g. if a finite verb is classified as an infinitive) or not (e.g. if a verb is classified as a noun). We empirically explore the decrease of performance that each of these error types causes for different sizes of the training set. Our results show that those types of errors that are easier to eliminate have a particularly negative effect on the performance. Thus, it is worthwhile concentrating on the elimination of these types of errors, especially if the training corpus is large.
Prepositional phrase (PP) attachment is one of the major sources for errors in traditional statistical parsers. The reason for that lies in the type of information necessary for resolving structural ambiguities. For parsing, it is assumed that distributional information of parts-of-speech and phrases is sufficient for disambiguation. For PP attachment, in contrast, lexical information is needed. The problem of PP attachment has sparked much interest ever since Hindle and Rooth (1993) formulated the problem in a way that can be easily handled by machine learning approaches: In their approach, PP attachment is reduced to the decision between noun and verb attachment; and the relevant information is reduced to the two possible attachment sites (the noun and the verb) and the preposition of the PP. Brill and Resnik (1994) extended the feature set to the now standard 4-tupel also containing the noun inside the PP. Among many publications on the problem of PP attachment, Volk (2001; 2002) describes the only system for German. He uses a combination of supervised and unsupervised methods. The supervised method is based on the back-off model by Collins and Brooks (1995), the unsupervised part consists of heuristics such as ”If there is a support verb construction present, choose verb attachment”. Volk trains his back-off model on the Negra treebank (Skut et al., 1998) and extracts frequencies for the heuristics from the ”Computerzeitung”. The latter also serves as test data set. Consequently, it is difficult to compare Volk’s results to other results for German, including the results presented here, since not only he uses a combination of supervised and unsupervised learning, but he also performs domain adaptation. Most of the researchers working on PP attachment seem to be satisfied with a PP attachment system; we have found hardly any work on integrating the results of such approaches into actual parsers. The only exceptions are Mehl et al. (1998) and Foth and Menzel (2006), both working with German data. Mehl et al. report a slight improvement of PP attachment from 475 correct PPs out of 681 PPs for the original parser to 481 PPs. Foth and Menzel report an improvement of overall accuracy from 90.7% to 92.2%. Both integrate statistical attachment preferences into a parser. First, we will investigate whether dependency parsing, which generally uses lexical information, shows the same performance on PP attachment as an independent PP attachment classifier does. Then we will investigate an approach that allows the integration of PP attachment information into the output of a parser without having to modify the parser: The results of an independent PP attachment classifier are integrated into the parse of a dependency parser for German in a postprocessing step.
Maschinelles Lernen wird häufig zur effzienten Annotation großer Datenmengen eingesetzt. Die Forschung zu maschinellen Lernverfahren beschränkt sich i.a. darauf unterschiedliche Lernverfahren zu vergelichen oder die optimale größe der Trainingsdaten zu bestimmen. Bisher wurde jedoch nicht untersucht, in wie weit sich linguistisches Wissen bei der Aufgabendefinition positiv auswirken kann. Dies soll hier anhand des Lernens von Base-Nominalphrasen mit drei unterschiedlichen Definitionen untersucht werden. Die Definitionen unterscheiden sich im Grad der linguistisch motivierten Erweiterungen, die zu einer eher praktisch motivierten ersten Definition hinzu kamen. Die Untersuchungen ergaben, dass sich die Anzahl der falsch klasssifizierten Wörter um ein Drittel reduzieren lässt.
This report explores the question of compatibility between annotation projects including translating annotation formalisms to each other or to common forms. Compatibility issues are crucial for systems that use the results of multiple annotation projects. We hope that this report will begin a concerted effort in the field to track the compatibility of annotation schemes for part of speech tagging, time annotation, treebanking, role labeling and other phenomena.
This paper reports on the SYN-RA (SYNtax-based Reference Annotation) project, an on-going project of annotating German newspaper texts with referential relations. The project has developed an inventory of anaphoric and coreference relations for German in the context of a unified, XML-based annotation scheme for combining morphological, syntactic, semantic, and anaphoric information. The paper discusses how this unified annotation scheme relates to other formats currently discussed in the literature, in particular the annotation graph model of Bird and Liberman (2001) and the pie-in-thesky scheme for semantic annotation.
Chunk parsing has focused on the recognition of partial constituent structures at the level of individual chunks. Little attention has been paid to the question of how such partial analyses can be combined into larger structures for complete utterances. The TüSBL parser extends current chunk parsing techniques by a tree-construction component that extends partial chunk parses to complete tree structures including recursive phrase structure as well as function-argument structure. TüSBLs tree construction algorithm relies on techniques from memory-based learning that allow similarity-based classification of a given input structure relative to a pre-stored set of tree instances from a fully annotated treebank. A quantitative evaluation of TüSBL has been conducted using a semi-automatically constructed treebank of German that consists of appr. 67,000 fully annotated sentences. The basic PARSEVAL measures were used although they were developed for parsers that have as their main goal a complete analysis that spans the entire input.This runs counter to the basic philosophy underlying TüSBL, which has as its main goal robustness of partially analyzed structures.