Linguistik-Klassifikation
Refine
Year of publication
Document Type
- Preprint (53) (remove)
Has Fulltext
- yes (53)
Is part of the Bibliography
- no (53)
Keywords
- Deutsch (11)
- Multicomponent Tree Adjoining Grammar (8)
- Syntaktische Analyse (8)
- Lexicalized Tree Adjoining Grammar (5)
- Semantik (4)
- German (3)
- Kongress (3)
- Range Concatenation Grammar (3)
- Satzanalyse (3)
- Syntax (3)
Institute
- Extern (49)
Der TUSNELDA-Standard : ein Korpusannotierungsstandard zur Unterstützung linguistischer Forschung
(2001)
Die Verwendung von Standards für die Annotierung größerer Sammlungen elektronischer Texte (Korpora) ist eine Voraussetzung für eine mögliche Wiederverwendung dieser Korpora. Dieser Artikel stellt einen Korpusannotierungsstandard vor, der die Anforderungen der Untersuchung unterschiedlichster linguistischer Phänomene berücksichtigt. Der Standard wurde im SFB 441 an der Universität Tübingen entwickelt. Er geht von bestehenden Standards, insbesondere CES und TEI, aus, die sich als teilweise zu ausführlich und zu wenig restriktiv,teilweise auch als nicht ausdrucksstark genug erweisen, um den Bedürfnissen korpusbasierter linguistischer Forschung gerecht zu werden.
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.
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.
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.
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.
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.
Die Prosodie der Mundarten wurde schon früh als auffälliges und distinktes Merkmal wahrgenommen und in mehreren Arbeiten zur Grammatik des Schweizerdeutschen mittels Musiknoten festgehalten (u. a. J. Vetsch 1910, E. Wipf 1910, K. Schmid 1915, W. Clauss 1927, A. Weber 1948), wobei schon A. Weber (1948, S. 53) anmerkt, "dass sich der musikalische Gang der Rede nicht ohne Gewaltsamkeit mit der üblichen Notenschrift darstellen lässt". Da also eine adäquate Kodierung, eine theoretische Grundlage und die notwendigen phonetischen Instrumente zur Intonationsforschung fehlten, wurden diese ersten Ansätze nicht aus- und weitergeführt. Erst in der Mitte des 20. Jahrhunderts brachte die technische Entwicklung Instrumente zur Messung der Prosodie hervor, die nun durch die Popularisierung der entsprechenden Computerprogramme im Übergang zum 21. Jahrhundert für die linguistische Forschung intensiv und breit genutzt werden können.
LTAG semantics for questions
(2004)
This papers presents a compositional semantic analysis of interrogatives clauses in LTAG (Lexicalized Tree Adjoining Grammar) that captures the scopal properties of wh- and nonwh-quantificational elements. It is shown that the present approach derives the correct semantics for examples claimed to be problematic for LTAG semantic approaches based on the derivation tree. The paper further provides an LTAG semantics for embedded interrogatives.
This paper develops a framework for TAG (Tree Adjoining Grammar) semantics that brings together ideas from different recent approaches.Then, within this framework, an analysis of scope is proposed that accounts for the different scopal properties of quantifiers, adverbs, raising verbs and attitude verbs. Finally, including situation variables in the semantics, different situation binding possibilities are derived for different types of quantificational elements.
In this paper we will explore the similarities and differences between two feature logic-based approaches to the composition of semantic representations. The first approach is formulated for Lexicalized Tree Adjoining Grammar (LTAG, Joshi and Schabes 1997), the second is Lexical Ressource Semantics (LRS, Richter and Sailer 2004) and was first defined in Head-driven Phrase Structure Grammar. The two frameworks have several common characteristics that make them easy to compare: 1 They use languages of two sorted type theory for semantic representations. 2. They allow underspecification. LTAG uses scope constraints while LRS provides component-of contraints. 3 They use feature logics for computing semantic representations. 4. they are designed for computational applications. By comparing the two frameworks we will also point outsome characteristics and advantages of feature logic-based semantic computation in genereal.
In this paper, we introduce an extension of the XMG system (eXtensibleMeta-Grammar) in order to allow for the description of Multi-Component Tree Adjoining Grammars. In particular, we introduce the XMG formalism and its implementation, and show how the latter makes it possible to extend the system relatively easily to different target formalisms, thus opening the way towards multi-formalism.
TT-MCTAG lets one abstract away from the relative order of co-complements in the final derived tree, which is more appropriate than classic TAG when dealing with flexible word order in German. In this paper, we present the analyses for sentential complements, i.e., wh-extraction, thatcomplementation and bridging, and we work out the crucial differences between these and respective accounts in XTAG (for English) and V-TAG (for German).
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.
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.
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.
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.
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.
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.
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.
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.