Linguistik-Klassifikation
Refine
Year of publication
Document Type
- Preprint (53)
- Conference Proceeding (26)
- Article (13)
- Part of a Book (9)
- Book (8)
- Working Paper (4)
- Review (2)
- diplomthesis (1)
Language
- English (90)
- German (21)
- Portuguese (4)
- French (1)
Has Fulltext
- yes (116) (remove)
Is part of the Bibliography
- no (116)
Keywords
- Computerlinguistik (38)
- Japanisch (18)
- Deutsch (16)
- Maschinelle Übersetzung (12)
- Syntaktische Analyse (9)
- Multicomponent Tree Adjoining Grammar (8)
- Semantik (6)
- Lexicalized Tree Adjoining Grammar (5)
- Grammatik (4)
- Satzanalyse (4)
Institute
- Extern (90)
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 purpose of this article is to report on the work carried out during the research project "O trabalho de tradutor como fonte para a constituição de base de dados" (The translator´s work as a source for the constitution of a database). Through the restoration, organization and digitalization of the personal glossary and part of the books containing the translations made by the deceased public translator Gustavo Lohnefink, this research project intends to construct a digital database of German – Portuguese technical terms (for the language pair), which could then be used by other translators. In order to achieve this purpose, a specific methodology had to be developed, which could be used as a starting-point for the treatment and recovery of other similarly organized data-collections.
Um den schwierigen Wettbewerbsbedingungen im internationalen Vergleich entgegentreten zu können, benötigen kleine und mittlere Unternehmen nicht nur den Einsatz moderner Informationstechniken und eine kommerzielle Präsenz im multimedialen und grafikintensiven Teil des Internets, sondern auch eine an den Kunden angepasste Web-Präsenz. In diesem Sinne widmen wir uns in diesem Beitrag der wirtschaftlichen Notwendigkeit einer kontrastiven Hypertextgrammatik. In den letzten Jahren ist dank der zunehmenden Bedeutung des Internets als Handelsplattform eine grammatische Unterdisziplin entstanden, die zur Geschäftsoptimierung kleiner und mittlerer Unternehmen einen beachtlichen Beitrag leisten könnte: die kontrastive Hypertextgrammatik. Wir gehen hier der Frage nach, wie man bei einer kontrastiven hypertextgrammatischen Studie vorgehen könnte.
Dieser Beitrag basiert auf dem Forschungsprojekt DICONALE, das sich die Erstellung eines konzeptuell orientierten, zweisprachigen Wörterbuchs mit Online-Zugang für Verballexeme des Deutschen und Spanischen zum Ziel gesetzt hat. Das Anliegen dieses Beitrags ist es, die relevantesten Eigenschaften des geplanten Wörterbuchs exemplarisch anhand von zwei Verblexemen aus dem konzeptuellen Feld der KOGNITION vorzustellen. Neben der Beschreibung der paradigmatischen Sinnrelationen der Feldelemente zueinander wird besonderer Wert auf die syntagmatischen Inhalts- und Ausdrucksstrukturen und auf die kontrastive Analyse gelegt. Es wird versucht, einerseits einen Überblick über die wichtigsten Besonderheiten des Wörterbuchs anzubieten und andererseits die Relevanz solcher Kriterien für die heutige kontrastive Lexikographie Deutsch-Spanisch nachzuweisen.
The two papers included in this volume have developed from work with the CHILDES tools and the Media Editor in the two research projects, "Second language acquisition of German by Russian learners", sponsored by the Max Planck Institute for Psycholinguistics, Nijmegen, from 1998 to 1999 (directed by Ursula Stephany, University of Cologne, and Wolfgang Klein, Max Planck Institute for Psycholinguistics, Nijmegen) and "The age factor in the acquisition of German as a second language", sponsored by the German Science Foundation (DFG), Bonn, since 2000 (directed by Ursula Stephany, University of Cologne, and Christine Dimroth, Max Planck Institute for Psycholinguistics, Nijmegen). The CHILDES Project has been developed and is being continuously improved at Carnegie Mellon University, Pittsburgh, under the supervision of Brian MacWhinney. Having used the CHILDES tools for more than ten years for transcribing and analyzing Greek child data there it was no question that I would also use them for research into the acquisition of German as a second language and analyze the big amount of spontaneous speech gathered from two Russian girls with the help of the CLAN programs. When in the spring of 1997, Steven Gillis from the University of Antwerp (in collaboration with Gert Durieux) developed a lexicon-based automatic coding system based on the CLAN program MOR and suitable for coding languages with richer morphologies than English, such as Modern Greek. Coding huge amounts of data then became much quicker and more comfortable so that I decided to adopt this system for German as well. The paper "Working with the CHILDES Tools" is based on two earlier manuscripts which have grown out of my research on Greek child language and the many CHILDES workshops taught in Germany, Greece, Portugal, and Brazil over the years. Its contents have now been adapted to the requirements of research into the acquisition of German as a second language and for use on Windows.
The Child Language Data Exchange System (CHILDES) consists of Codes for the Human Analysis of Transcripts (CHAT), Computerized Language Analysis (CLAN), and a database. There is also an online manual which includes the CHILDES bibliography, the database, and the CHAT conventions as well as the CLAN instructions. The first three parts of this paper concern the CHAT format of transcription, grammatical coding, and analyzing transcripts by using the CLAN programs. The fourth part shows examples of transcribed and coded data.
The project WBLUX (Wortbildung des moselfränkisch-luxemburgischen Raumes) at the University of Luxembourg aims at the investigation of Luxembourgish word formation through different text sorts and genres. In order to achieve this goal the compilation of an annotated corpus is needed. This article gives an example for benefits of using a corpus with annotations like parts of speech, lemmata and word formation affixes in the analysis of productivity of some selected word formation affixes of Luxembourgish. Then it describes how one can achieve such a corpus from a technical point of view. This includes the choice of corpus format, of a database platform and the designing of programs needed for the annotation process of word formation itself. This article also suggests new corpus linguistic approaches for research of word formation like analyzing the usage of word formation bases in the entire corpus or performing context analysis in order to determine semantical functions of each suffix.
In this paper we show an approach to the customization of GermaNet to the German HPSG grammar lexicon developed in the Verbmobil project. GermaNet has a broad coverage of the German base vocabulary and fine-grained semantic classification; while the HPSG grammar lexicon is comparatively small und has a coarse-grained semantic classification. In our approach, we have developed a mapping algorithm to relate the synsets in GermaNet with the semantic sorts in HPSG. The evaluation result shows that this approach is useful for the lexical extension of our deep grammar development to cope with real-world text understanding.
Ein einer Äußerung können Nullpronomina aus mehreren [...] Gruppen vorkommen. Die [...] Gruppen können auf die Ebenen eines Schicht-Dialogmodells bezogen werden; andererseits können sie Hinweise geben, welche Informationen in einem Dialogmodell verfügbar sein sollten. Dies wird in der Folgezeit genauer zu untersuchen sein. Im folgenden werden die genannten Typen von Nullpronomina genauer dargestellt und Lösungsverfahren zum Auffinden der Referenten genannt.
Die Entwicklung eines individuellen Standards „vom grünen Tisch“ führt selten zu zufriedenstellenden Ergebnissen. Bei der automatischen Prüfung stellt man schnell fest, dass die „ausgedachten“ Regeln einer systematischen Anwendung nicht standhalten. Bei der Implementierung solcher Richtlinien stellt man fest, dass sie oft zu wenig konkret formuliert sind, wie z.B. „formulieren Sie Handlungsanweisungen knapp und präzise“. Wie jedoch kann ein Standard entwickelt werden, der zu einem Unternehmen, seiner Branche und Zielgruppen passt und für die automatische Prüfung implementiert werden kann? Sprachtechnologie hilft effizient bei der Entwicklung individueller Richtlinien. Durch Datenanalyse, Satzcluster und Parametrisierung entsteht ein textspezifischer individueller Standard. Ist damit aber der Gegensatz von Kreativität und Standardisierung aufgehoben?
Japanese is often taken to be strictly head-final in its syntax. In our work on a broad-coverage, precision implemented HPSG for Japanese, we have found that while this is generally true, there are nonetheless a few minor exceptions to the broad trend. In this paper, we describe the grammar engineering project, present the exceptions we have found, and conclude that this kind of phenomenon motivates on the one hand the HPSG type hierarchical approach which allows for the statement of both broad generalizations and exceptions to those generalizations and on the other hand the usefulness of grammar engineering as a means of testing linguistic hypotheses.
We present a broad coverage Japanese grammar written in the HPSG formalism with MRS semantics. The grammar is created for use in real world applications, such that robustness and performance issues play an important role. It is connected to a POS tagging and word segmentation tool. This grammar is being developed in a multilingual context, requiring MRS structures that are easily comparable across languages.
In this text, we describe the development of a broad coverage grammar for Japanese that has been built for and used in different application contexts. The grammar is based on work done in the Verbmobil project (Siegel 2000) on machine translation of spoken dialogues in the domain of travel planning. The second application for JACY was the automatic email response task. Grammar development was described in Oepen et al. (2002a). Third, it was applied to the task of understanding material on mobile phones available on the internet, while embedded in the project DeepThought (Callmeier et al. 2004, Uszkoreit et al. 2004). Currently, it is being used for treebanking and ontology extraction from dictionary definition sentences by the Japanese company NTT (Bond et al. 2004).
Das Problem des Transfers in der maschinellen Übersetzung von Japanisch nach Englisch ist fehlende Information über Numerus und Definitheit im Japanischen, die für die Wahl der englischen Artikel und die Nomenmarkierung gebraucht wird. Obwohl dieses Problem signifikant ist, beschäftigt sich die Forschungsliteratur kaum damit. [...] Wir bsaieren unsere Untersuchungen auf experimentell erhobenen Daten aus einem Experiment über deutsch-japanische gedolmetschte Terminaushandlungsdialoge [...]. Auf diese Weise können Phänomene bestimmt werden, die für die Domäne von VERBMOBIL relevant sind. Wir sehen unser Vorgehen in Übereinstimmung mit dem 'Sublanguage'-Ansatz [...].
Eins der signifikanten Probleme in der maschinellen Übersetzung japanische in deutsche Sprache ist die fehlende Information und Definitheit im japanischen Analyse-Output. Eine effiziente Lösung dieses Problems ist es, die Suche nach der relevanten Information in den Transfer zu integrieren. Transferregeln werden mit Präferenzregeln und Default-Regeln kombiniert. Dadurch wird Information über lexikalische Restriktionen der Zielsprache, über die Domäne und über den Diskurs zugänglich.
Die Domäne in VERBMOBIL sind Terminaushandlungsdialoge. Für die Syntax bedeutet das zunächst, daß die Sytnax sich an gesprochener Sprache orientieren muß. Das beinhaltet Nullanaphern, Phrasen, die auf die Kommunikationssituation bezogen sind und Phrasen, die für geschriebene Sprache als nicht wohlgeformt bezeichnet werden. Weitergehend gibt es einige domänenspezifische syntaktische besonderheiten, wie zum Biepsiel die Realisierung von Zeitangaben.
We present a solution for the representation of Japanese honorifical information in the HPSG framework. Basically, there are three dimensions of honorification. We show that a treatment is necessary that involves both the syntactic and the contextual level of information. The japanese grammar is part of a machine translation system.
Preferences and defaults for definiteness and number in japanese to german machine translation
(1996)
A significant problem when translating Japanese dialogues into German is the missing information on number and definiteness in the Japanese analysis output. The integration of the search for such information into the transfer process provides an efficient solution. General transfer includes conditions to make it possible to consider external knowledge. Thereby, grammatical and lexical knowledge of the source language, knowledge of lexical restrictions on the target language, domain knowledge and discourse knowledge are accessible.
A comprehensive investigation of Japanese particle was missing up to now. General implications were set up without the fact that a comprehensive analysis was carried out. [...] We offer a lexicalist treatment of the problem. Instead of assuming different phrase structure rules we state a type hierarchy of Japanese particles. This makes a uniform treatment of phrase structure as well as a differentiation of subcategorization patterns possible.
Particles fullfill several distinct central roles in the Japanese language. They can mark arguments as well as adjuncts, can be functional or have semantic functions. There is, however, no straightforward matching from particles to functions, as, e.g., 'ga' can mark the subject, the object or the adjunct of a sentence. Particles can cooccur. Verbal arguments that could be identified by particles can be eliminated in the Japanese sentence. And finally, in spoken language particles are often omitted. A proper treatment of particles is thus necessary to make an analysis of Japanese sentences possible. Our treatment is based on an empirical investigation of 800 dialogues. We set up a type hierarchy of particles motivated by their subcategorizational and modificational behaviour. This type hierarchy is part of the Japanese syntax in VERBMOBIL.
Sprachtechnologie für übersetzungsgerechtes Schreiben am Beispiel Deutsch, Englisch, Japanisch
(2009)
Wir [...] haben uns zur Aufgabe gesetzt, Wege zu finden, wie linguistisch basierte Software den Prozess des Schreibens technischer Dokumentation unterstützen kann. Dabei haben wir einerseits die Schwierigkeiten im Blick, die japanische und deutsche Autoren (und andere Nicht-Muttersprachler des Englischen) beim Schreiben englischer Texte haben. Besonders japanische Autoren haben mit Schwierigkeiten zu kämpfen, weil sie hochkomplexe Ideen in einer Sprache ausdrücken müssen, die von Informationsstandpunkt her sehr unterschiedlich zu ihrer Muttersprache ist. Andererseits untersuchen wir technische Dokumentation, die von Autoren in ihrer Muttersprache geschrieben wird. Obwohl hier die fremdsprachliche Komponente entfällt, ist doch auch erhebliches Verbesserungspotential vorhanden. Das Ziel ist hier, Dokumente verständlich, konsistent und übersetzungsgerecht zu schreiben. Der fundamentale Ansatz in der Entwicklung linguistisch-basierter Software ist, dass gute linguistische Software auf Datenmaterial basiert und sich an den konkreten Zielen der besseren Dokumentation orientiert.
Der Übersetzungsprozess der Technischen Dokumentation wird zunehmend mit Maschineller Übersetzung (MÜ) unterstützt. Wir blicken zunächst auf die Ausgangstexte und erstellen automatisch prüfbare Regeln, mit denen diese Texte so editiert werden können, dass sie optimale Ergebnisse in der MÜ liefern. Diese Regeln basieren auf Forschungsergebnissen zur Übersetzbarkeit, auf Forschungsergebnissen zu Translation Mismatches in der MÜ und auf Experimenten.
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.
Der Beitrag behandelt zunächst die Frage, welche Vorteile elektronische Wörterbücher gegenüber traditionell gedruckten Wörterbüchern besitzen. Danach werden drei Online-Programme zur automatischen Übersetzung (Babelfish, Google Übersetzer, Bing Translator) vorgestellt. Beispieltexte werden mit diesen Programmen übersetzt, danach wird die jeweilige Qualität der Übersetzungen beurteilt. Schließlich diskutiert der Beitrag noch die Folgen, die durch die Möglichkeiten automatischen Übersetzens für die Auslandsgermanistik zu erwarten sind. Dabei zeigt sich, dass Programme für das automatische Übersetzen künftig durchaus ernstzunehmende Auswirkungen auf die philologischen Wissenschaften haben können.
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.
In this paper, I revisit the arguments against the use of fuzzy logic in linguistics (or more generally, against a truth-functional account of vagueness). In part, this is an exercise to explain to fuzzy logicians why linguists have shown little interest in their research paradigm. But, the paper contains more than this interdisciplinary service effort that I started out on: In fact, this seems an opportune time for revisiting the arguments against fuzzy logic in linguistics since three recent developments affect the argument. First, the formal apparatus of fuzzy logic has been made more general since the 1970s, specifically by Hajek [6], and this may make it possible to define operators in a way to make fuzzy logic more suitable for linguistic purposes. Secondly, recent research in philosophy has examined variations of fuzzy logic ([18, 19]). Since the goals of linguistic semantics seem sometimes closer to those of some branches of philosophy of language than they are to the goals of mathematical logic, fuzzy logic work in philosophy may mark the right time to reexamine fuzzy logic from a linguistic perspective as well. Finally, the reasoning used to exclude fuzzy logic in linguistics has been tied to the intuition that p and not p is a contradiction. However, this intuition seems dubious especially when p contains a vague predicate. For instance, one can easily think of circumstances where 'What I did was smart and not smart.' or 'Bea is both tall and not tall.' don’t sound like senseless contradictions. In fact, some recent experimental work that I describe below has shown that contradictions of classical logic aren’t always felt to be contradictory by speakers. So, it is important to see to what extent the argument against fuzzy logic depends on a specific stance on the semantics of contradictions. In sum then, there are three good reasons to take another look at fuzzy logic for linguistic purposes.
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.
Based on a detailed case study of parallel grammar development distributed across two sites, we review some of the requirements for regression testing in grammar engineering, summarize our approach to systematic competence and performance profiling, and discuss our experience with grammar development for a commercial application. If possible, the workshop presentation will be organized around a software demonstration.
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.
This paper proposes an annotating scheme that encodes honorifics (respectful words). Honorifics are used extensively in Japanese, reflecting the social relationship (e.g. social ranks and age) of the referents. This referential information is vital for resolving zero
pronouns and improving machine translation outputs. Annotating honorifics is a complex task that involves identifying a predicate with honorifics, assigning ranks to referents of the
predicate, calibrating the ranks, and connecting referents with their predicates.
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.
Some requirements for a VERBMOBIL system capable of processing Japanese dialogue input have been explored. Based on a pilot study in the VERBMOBIL domain, dialogues between 2 participants and a professional Japanese interpreter have been analyzed with respect to a very typical and frequent feature: zero pronouns. Zero pronouns in Japanese texts or dialogues as well as overt pronouns in English texts or dialogues are an important element of discourse coherence. As to translation, this difference in the use of pronouns is a case of translation mismatch: information not explicitly expressed in the source language is needed in the target language. (Verb argument positions, normally obligatory in English, are rather frequently omitted in Japanese. Furthermore, verbs in Japanese are not marked with respect to features necessary for pronoun selection in English.)
Seit einiger Zeit ist zu beobachten, dass zu dem Handwerkszeug eines DaF-Lerners […] nicht mehr Grammatiken und Wörterbücher im klassischen Sinne gehören. Das Nachschlagen in Printwerken wird auf allen Stufen und für alle Benutzersituationen durch die Konsultation in den unterschiedlichsten über Internet frei zugänglichen Materialien ersetzt. […] So scheint es, dass gerade im DaF-Bereich die Printnachschlagewerke bald schon zu einem Relikt anderer Zeiten angehören werden. Aber genauso wie für die Benutzung von Printwörterbüchern, benötigt der DaF-Lerner durch die ganz neu entstehenden online-Nachschlagetechniken (Engelberg/Lemnitzer 2009, 111) genügend Information und Schulung, um für seine jeweilige Benutzersituation in dem dafür am besten geeigneten Konsultationssystem die jeweils adäquateste Rechercheoption auszuwählen. […] Das gilt gleichermaßen für Print- wie für Onlineressourcen, wobei allerdings gerade bei Internetwörterbüchern bei der Suchanfrage das Risiko des Orientierungsverlustes („lost in hyperspace“) verstärkt auftreten kann (cfr. Haß/Schmitz 2010, 4). Es ist daher Aufgabe der Lehrenden, die entsprechende Orientierung und Hilfestellung zu leisten. Leider ist zu bemerken, dass im DaF-Bereich die nötige lexikographische Kompetenz nicht genügend vermittelt wird, was nicht zuletzt oft an der mangelnden lexikographischen Vorbildung der DaF-Lehrer liegt. Ziel des Beitrages ist es daher, einige Internetwörterbücher (IWB) mit freiem Zugang für die Deutsche Sprache in groben Zügen vorzustellen und für ihren Nutzen in unterschiedliche Benutzersituationen im Bereich DaF zu kommentieren, um dem DaF-Lerner und Lehrer die Auswahl aus dem inzwischen recht unübersichtlichen Angebot für seine jeweiligen Bedürfnisse zu erleichtern. In Anlehnung an die vorgeschlagenen Kriterien von Engelberg/Lemnitzer (42009, 220ff.), Storrer (2010) und das Evaluationsraster zur Beurteilung von online-WB von Kemmer (2010) sollen verschiedene aktuelle IWB der deutschen Gegenwartssprache beurteilt werden. Zur Wörterbuch-Typologisierung orientiere ich mich an den Vorschlägen von Engelberg/Lemnitzer (42009), beschränke aber in diesem Rahmen den Gegenstandsbereich auf zweisprachige IWB, spezifische einsprachige DaF-IWB und einige modularisierte allgemeinsprachige Wörterbuchportale, in denen verschiedene IWB miteinander verlinkt sind.
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).
MED (Media EDitor) is a program designed to facilitate the transcription of digitized soundfiles into textfiles. It was written by Hans Drexler and Daan Broeder, Max Planck Institute for Psycholinguistics, Nijmegen, The Netherlands. [...] The aim of MED is to facilitate the transcription of sound into text using a single program. It works on the principle of the coexistence and interaction of two basic elements, the waveform display window and the text window. [...] This means that you no longer need to use both a sound editor and a word processor at the same time in order to transcribe digitized speech files. Instead, you can directly type the sound you hear (and see) via MED into the text window. Furthermore, you can directly link sound portions of the waveform display window to text portions of the text window, so that you can easily locate and listen to the original source of your transcription once the links have been set. In this function the waveform display window and the text window virtually interact with each other.
This paper discusses an attempt to write a computer program that would properly model the phonological development of Chinese from Middle Chinese to Modern Peking Mandarin, using the rules in Chen 1976. Several problems are encountered, the most significant being that the rules cannot apply in the same order for all lexical items. The significance of this in terms of the implementation of sound change is briefly discussed.
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.