Refine
Year of publication
- 2009 (46) (remove)
Document Type
- Conference Proceeding (17)
- Part of a Book (15)
- Article (10)
- Book (1)
- Contribution to a Periodical (1)
- Doctoral Thesis (1)
- Working Paper (1)
Language
- English (46) (remove)
Has Fulltext
- yes (46)
Is part of the Bibliography
- no (46) (remove)
Keywords
- Korpus <Linguistik> (11)
- Deutsch (9)
- Computerlinguistik (8)
- Annotation (5)
- Automatische Sprachanalyse (4)
- Natürliche Sprache (3)
- Syntaktische Analyse (3)
- Verb (3)
- Algorithmus (2)
- Bildung (2)
Publicationstate
- Veröffentlichungsversion (21)
- Postprint (9)
- Zweitveröffentlichung (4)
Reviewstate
Publisher
- Acta Universitatis Upsaliensis (2)
- Benjamins (2)
- Elsevier (2)
- Narr (2)
- Niemeyer (2)
- Oxford University Press (2)
- Springer (2)
- AAAI Press (1)
- Association for Computational Linguistics (1)
- Association for Computing Machinery (1)
“Linguistic Landscapes” (LL) is a research method which has become increasingly popular in recent years. In this paper, we will first explain the method itself and discuss some of its fundamental assumptions. We will then recall the basic traits of multilingualism in the Baltic States, before presenting results from our project carried out together with a group of Master students of Philology in several medium-sized towns in the Baltic States, focussing on our home town of Rēzekne in the highly multilingual region of Latgale in Eastern Latvia. In the discussion of some of the results, we will introduce the concept of “Legal Hypercorrection” as a term for the stricter compliance of language laws than necessary. The last part will report on advantages of LL for educational purposes of multilingualism, and for developing discussions on multilingualism among the general public.
This dossier consists of an introduction to the region under study, followed by six sections each dealing with a specific level of the education system. These brief descriptions contain factual information presented in a readily accessible way. Sections eight to ten cover research, prospects, and summary statistics. For detailed information and political discussions about language use at the various levels of education, the reader is referred to other sources with a list of publications.
Beyond the stars: exploiting free-text user reviews to improve the accuracy of movie recommendations
(2009)
In this paper we show that the extraction of opinions from free-text reviews can improve the accuracy of movie recommendations. We present three approaches to extract movie aspects as opinion targets and use them as features for the collaborative filtering. Each of these approaches requires different amounts of manual interaction. We collected a data set of reviews with corresponding ordinal (star) ratings of several thousand movies to evaluate the different features for the collaborative filtering. We employ a state-of-the-art collaborative filtering engine for the recommendations during our evaluation and compare the performance with and without using the features representing user preferences mined from the free-text reviews provided by the users. The opinion mining based features perform significantly better than the baseline, which is based on star ratings and genre information only.
This paper introduces LRTwiki, an improved variant of the Likelihood Ratio Test (LRT). The central idea of LRTwiki is to employ a comprehensive domain specific knowledge source as additional “on-topic” data sets, and to modify the calculation of the LRT algorithm to take advantage of this new information. The knowledge source is created on the basis of Wikipedia articles. We evaluate on the two related tasks product feature extraction and keyphrase extraction, and find LRTwiki to yield a significant improvement over the original LRT in both tasks.
The purpose of this paper is to describe the functions of ‘where’-based relative elements' in six Balkan languages, paying particular attention to non-standard varieties.2 Relative elements based on an originally interrogative pronoun meaning ‘where’ are attested in all Balkan languages and, more generally, in all European languages. In accordance with the locative meaning of the original pronoun, ‘where’-based relative elements are primarily used to relativize locatives. However, it will be shown that in some Balkan languages, and especially in non-standard varieties, these elements have extended their functional domain. This process does not appear to be random, but rather to pattern with the following hierarchy: locative > unspecific connector > other syntactic positions (indirect/direct object, subject).3 Additionally, ‘where’-based relative elements will be compared with ‘what’-based ones in order to highlight common patterns of development.
Concurrent standardization as a necessity: The genesis of the new official orthographic guidelines
(2009)
The new official orthographic guidelines were brought into force by the official state authorities on August 1st, 1998 and its principle goals were a standardized representation of the guidelines and a «gentle simplification in respect of content». This regulation was not supported by the public and in fact it was the starting point for a struggle for conceptual solutions and a quest for the achievement of' a consensus between different possible norms. Since orthography is an officially codified standard taking up a prominent position among linguistic standards, it is of particular socio-political importance. It was the foremost task of the Council for German Orthography (Rat für deutsche Rechtschreibung), instituted in December 2004, to elaborate a compromise in order to bring the «Orthographical war» (Die Zeit) to an end, which was led enthusiastically for more than a decade. - The concern of this article is to classify historically the agreement reached in 2006. Against this background, it can be stated that official guidelines will only be accepted, if they are based upon the usage in writing and if they take into account the interests of the reader. Both principles are characterizing the proposal made by the Council for German Orthography. An outlook on the Council's activities concerning orthographic standardization expected in the future will conclude this article.
Using concurrent electroencephalogram and eye movement measures to track natural reading, this study shows that N400 effects reflecting predictability are dissociable from those owing to spreading activation. In comparing predicted sentence endings with related and unrelated unpredicted endings in antonym constructions (‘the opposite of black is white/yellow/nice’), fixation-related potentials at the critical word revealed a predictability-based N400 effect (unpredicted vs. predicted words). By contrast, event-related potentials time locked to the last fixation before the critical word showed an N400 only for the nonrelated unpredicted condition (nice). This effect is attributed to a parafoveal mismatch between the critical word and preactivated lexical features (i.e. features of the predicted word and its associates). In addition to providing the first demonstration of a parafoveally induced N400 effect, our results support the view that the N400 is best viewed as a component family.
This paper shows that the phenomenon of plesionymy deserves greater attention and needs to be approached outside its traditional framework, which considered it to be a subtype of synonymy (Cruse, 1986, 2002; Croft and Cruse, 2004). This view suggested that pairs of terms such as foggy–misty, fearless–brave exhibit significant shared semantic traits that are more salient than their differences. Differing properties were considered to be subordinate. These are sometimes contextually foregrounded resulting in occasional oppositeness. Corpus studies show that this view is a broad generalization. This study sheds new light on German plesionyms by employing a corpus-linguistic approach. In particular, terms designating gradable properties (e.g. kritisch–ernst ‘critical–serious’, sauber–rein ‘clean–unsoiled/immaculate’) at neighboring positions of gradable scales show variable behavior and do not show a stronger affinity for synonymy. The position taken is that a relation of synonymy and contrast are equally a matter of construal. Both types of semantic relations are part of the conceptual and lexical knowledge and subject to a cognitive principle. This work also examines how plesionym relations are realized in discourse. This article demonstrates that plesionyms are co-occurrences within typical lexico-syntactic sequences. Following Jones’ (2002) and Murphy’s (2006) observations, these patterns (e.g. nicht X, eher Y; mehr X als Y; etc.) have specific discourse functions and are evidence to account for a construction-based view.
The paper discusses particular logical consistency conditions satisfied by German proposition-embedding predicates which determine the question type (external and internal whether-form as well as exhaustive and non-exhaustive wh-form), the correlate type (es- or da-correlate) as well as the impact of the correlate on the respective consistency condition. It will turn out that some consistency conditions also determine the embedding of verb second and subject-control.
TePaCoC - A Testsuite for Testing Parser Performance on Complex German Grammatical Constructions
(2009)
We present MaJo, a toolkit for supervised Word Sense Disambiguation (WSD), with an interface for Active Learning. Our toolkit combines a flexible plugin architecture which can easily be extended, with a graphical user interface which guides the user through the learning process. MaJo integrates off-the-shelf NLP tools like POS taggers, treebank-trained statistical parsers, as well as linguistic resources like WordNet and GermaNet. It enables the user to systematically explore the benefit gained from different feature types for WSD. In addition, MaJo provides an Active Learning environment, where the
system presents carefully selected instances to a human oracle. The toolkit supports manual annotation of the selected instances and re-trains the system on the extended data set. MaJo also provides the means to evaluate the performance of the system against a gold standard. We illustrate the usefulness of our system by learning the frames (word senses) for three verbs from the SALSA corpus, a version of the TiGer treebank with an additional layer of frame-semantic annotation. We show how MaJo can be used to tune the feature set for specific target words and so improve performance for these targets. We also show that syntactic features, when carefully tuned to the target word, can lead to a substantial increase in performance.
Though polarity classification has been extensively explored at document level, there has been little work investigating feature design at sentence level. Due to the small number of words within a sentence, polarity classification at sentence level differs substantially from document-level classification in that resulting bag-of-words feature vectors tend to be very sparse resulting in a lower classification accuracy.
In this paper, we show that performance can be improved by adding features specifically designed for sentence-level polarity classification. We consider both explicit polarity information and various linguistic features. A great proportion of the improvement that can be obtained by using polarity information can also be achieved by using a set of simple domain-independent linguistic features.
In opinion mining, there has been only very little work investigating semi-supervised machine learning on document-level polarity classification. We show that semi-supervised learning performs significantly better than supervised learning when only few labelled data are available. Semi-supervised polarity classifiers rely on a predictive feature set. (Semi-)Manually built polarity lexicons are one option but they are expensive to obtain and do not necessarily work in an unknown domain. We show that extracting frequently occurring adjectives & adverbs of an unlabeled set of in-domain documents is an inexpensive alternative which works equally well throughout different domains.
From Proof Texts to Logic. Discourse Representation Structures for Proof Texts in Mathematics
(2009)
We present an extension to Discourse Representation Theory that can be used to analyze mathematical texts written in the commonly used semi-formal language of mathematics (or at least a subset of it). Moreover, we describe an algorithm that can be used to check the resulting Proof Representation Structures for their logical validity and adequacy as a proof.
We compare the use of überhaupt and sowieso in Dutch and German. We use the world-wide web as the main resource and pursue a zigzag strategy, trying to find usages going back and forth between dictionaries, intuitions and real data obtained through web search. To our surprise, the results more or less confirm the decision of Dutch dictionaries to consider überhaupt and sowieso synonymous. In German, we find no synonymy, but only a great overlap of usage conditions in declarative sentences.
In this paper we present an approach to faceted search in large language resource repositories. This kind of search which enables users to browse through the repository by choosing their personal sequence of facets heavily relies on the availability of descriptive metadata for the objects in the repository. This approach therefore informs the collection of a minimal set of metatdata for language resources. The work described in this paper has been funded by the EC within the ESFRI infrastructure project CLARIN.
While written corpora can be exploited without any linguistic annotations, speech corpora need at least a basic transcription to be of any use for linguistic research. The basic annotation of speech data usually consists of time-aligned orthographic transcriptions. To answer phonetic or phonological research questions, phonetic transcriptions are needed as well. However, manual annotation is very time-consuming and requires considerable skill and near-native competence. Therefore it can take years of speech corpus compilation and annotation before any analyses can be carried out. In this paper, approaches that address the transcription bottleneck of speech corpus exploitation are presented and discussed, including crowdsourcing the orthographic transcription, automatic phonetic alignment, and query-driven annotation. Currently, query-driven annotation and automatic phonetic alignment are being combined and applied in two speech research projects at the Institut für Deutsche Sprache (IDS), whereas crowdsourcing the orthographic transcription still awaits implementation.
In spite of the obvious importance that is accorded to the notion grammatical construction in any approach that sees itself as a construction grammar (CxG), there is as yet no generally accepted definition of the term across different variants of the framework. In particular, there are different assumptions about which additional requirements a given structure has to meet in order to be recognized as a construction besides being a ‘form-meaning pair’. Since the choice of a particular definition will determine the range of both relevant phenomena and concrete observations to be considered in empirical research within the framework, the issue is not just a mere terminological quibble but has important methodological repercussions especially for quantitative research in areas such as corpus linguistics. The present study illustrates some problems in identifying and delimiting such patterns in naturally occurring text and presents arguments for a usage-based interpretation of the term grammatical construction.
TEI Feature Structures as a Representation Format for Multiple Annotation and Generic XML Documents
(2009)
Feature structures are mathematical entities (rooted labeled directed acyclic graphs) that can be represented as graph displays, attribute value matrices or as XML adhering to the constraints of a specialized TEI tag set. We demonstrate that this latter ISO-standardized format can be used as an integrative storage and exchange format for sets of multiple annotation XML documents. This specific domain of application is rooted in the approach of multiple annotations, which marks a possible solution for XML-compliant markup in scenarios with conflicting annotation hierarchies. A more extreme proposal consists in the possible use as a meta-representation format for generic XML documents. For both scenarios our strategy concerning pertinent feature structure representations is grounded on the XDM (XQuery 1.0 and XPath 2.0 Data Model). The ubiquitous hierarchical and sequential relationships within XML documents are represented by specific features that take ordered list values. The mapping to the TEI feature structure format has been implemented in the form of an XSLT 2.0 stylesheet. It can be characterized as exploiting aspects of both the push and pull processing paradigm as appropriate. An indexing mechanism is provided with regard to the multiple annotation documents scenario. Hence, implicit links concerning identical primary data are made explicit in the result format. In comparison to alternative representations, the TEI-based format does well in many respects, since it is both integrative and well-formed XML. However, the result documents tend to grow very large depending on the size of the input documents and their respective markup structure. This may also be considered as a downside regarding the proposed use for generic XML documents. On the positive side, it may be possible to achieve a hookup to methods and applications that have been developed for feature structure representations in the fields of (computational) linguistics and knowledge representation.
The paper presents the results of a joint effort of a group of multimodality researchers and tool developers to improve the interoperability between several tools used for the annotation and analysis of multimodality. Each of the tools has specific strengths so that a variety of different tools, working on the same data, can be desirable for project work. However this usually requires tedious conversion between formats. We propose a common exchange format for multimodal annotation, based on the annotation graph (AG) formalism, which is supported by import and export routines in the respective tools. In the current version of this format the common denominator information can be reliably exchanged between the tools, and additional information can be stored in a standardized way.
We present data-driven methods for the acquisition of LFG resources from two German treebanks. We discuss problems specific to semi-free word order languages as well as problems arising from the data structures determined by the design of the different treebanks. We compare two ways of encoding semi-free word order, as done in the two German treebanks, and argue that the design of the TiGer treebank is more adequate for the acquisition of LFG resources. Furthermore, we describe an architecture for LFG grammar acquisition for German, based on the two German treebanks, and compare our results with a hand-crafted German LFG grammar.
Manual development of deep linguistic resources is time-consuming and costly and therefore often described as a bottleneck for traditional rule-based NLP. In my PhD thesis I present a treebank-based method for the automatic acquisition of LFG resources for German. The method automatically creates deep and rich linguistic presentations from labelled data (treebanks) and can be applied to large data sets. My research is based on and substantially extends previous work on automatically acquiring wide-coverage, deep, constraint-based grammatical resources from the English Penn-II treebank (Cahill et al.,2002; Burke et al., 2004; Cahill, 2004). Best results for English show a dependency f-score of 82.73% (Cahill et al., 2008) against the PARC 700 dependency bank, outperforming the best hand-crafted grammar of Kaplan et al. (2004). Preliminary work has been carried out to test the approach on languages other than English, providing proof of concept for the applicability of the method (Cahill et al., 2003; Cahill, 2004; Cahill et al., 2005). While first results have been promising, a number of important research questions have been raised. The original approach presented first in Cahill et al. (2002) is strongly tailored to English and the datastructures provided by the Penn-II treebank (Marcus et al., 1993). English is configurational and rather poor in inflectional forms. German, by contrast, features semi-free word order and a much richer morphology. Furthermore, treebanks for German differ considerably from the Penn-II treebank as regards data structures and encoding schemes underlying the grammar acquisition task. In my thesis I examine the impact of language-specific properties of German as well as linguistically motivated treebank design decisions on PCFG parsing and LFG grammar acquisition. I present experiments investigating the influence of treebank design on PCFG parsing and show which type of representations are useful for the PCFG and LFG grammar acquisition tasks. Furthermore, I present a novel approach to cross-treebank comparison, measuring the effect of controlled error insertion on treebank trees and parser output from different treebanks. I complement the cross-treebank comparison by providing a human evaluation using TePaCoC, a new testsuite for testing parser performance on complex grammatical constructions. Manual evaluation on TePaCoC data provides new insights on the impact of flat vs. hierarchical annotation schemes on data-driven parsing. I present treebank-based LFG acquisition methodologies for two German treebanks. An extensive evaluation along different dimensions complements the investigation and provides valuable insights for the future development of treebanks.
The paper contributes to the raising vs. control debate with respect to modals through (A) novel data; (B) the investigation of a domain in which it has proven particularly problematic: volitional modality. We analyze oblique arguments of experiencer verbs embedded under German wollen ‘want’ and propose that they support both generalized raising and the abandonment of the classical version of the Theta Criterion. Byproducts of the analysis include a syntactic account involved in a class of datives in the language together with the initial characterization of a related modal in German which is expressed through the same item as volition and which we term weak.
Generative lexicalized parsing models, which are the mainstay for probabilistic parsing of English, do not perform as well when applied to languages with different language-specific properties such as free(r) word order or rich morphology. For German and other non-English languages, linguistically motivated complex treebank transformations have been shown to improve performance within the framework of PCFG parsing, while generative lexicalized models do not seem to be as easily adaptable to these languages. In this paper, we show a practical way to use grammatical functions as first-class citizens in a discriminative model that allows to extend annotated treebank grammars with rich feature sets without having to suffer from sparse data problems. We demonstrate the flexibility of the approach by integrating unsupervised PP attachment and POS-based word clusters into the parser.
Complex common names such as Indian elephant or green tea denote a certain type of entity, viz. kinds. Moreover, those kinds are always subkinds of the kind denoted by their head noun. Establishing such subkinds is essentially the task of classifying modifiers that are a defining trait of endocentrically structured complex common names. Examining complex common names of different lexico-syntactic types(NN compounds, N+N syntagmas, NP/PP syntagmas, A+N syntagmas) and from different languages (particularly English, German and French) it can be shown that complex common names are subject to language- independent formal and semantic constraints. In particular, complex common names qualify as name-like expressions in that they tend to be deficient in terms of formal complexity and semantic compositionality.
In this paper we address the question of what is needed, in terms of morphosyntactic encoding, to relate a so-called verb-specific modifier to a nominal head. For the purposes of this paper we shall assume that the notion of a verb-specific modifier includes adverbs and their phrasal or clausal projections, adpositional phrases, and noun phrases featuring a particular semantic case such as locative or instrumental. Noun-specific modifiers, in turn, are considered to be first and foremost adjectives and adjective phrases, next participles and their phrasal projections and, finally, relative clauses.1 The basic motivation underlying this distinction relates to markedness.
This introductory tutorial describes a strictly corpus-driven approach for uncovering indications for aspects of use of lexical items. These aspects include ‘(lexical) meaning’ in a very broad sense and involve different dimensions, they are established in and emerge from respective discourses. Using data-driven mathematical-statistical methods with minimal (linguistic) premises, a word’s usage spectrum is summarized as a collocation profile. Self-organizing methods are applied to visualize the complex similarity structure spanned by these profiles. These visualizations point to the typical aspects of a word’s use, and to the common and distinctive aspects of any two words.
This article introduces the topic of ‘‘Multilingual language resources and interoperability’’. We start with a taxonomy and parameters for classifying language resources. Later we provide examples and issues of interoperatability, and resource architectures to solve such issues. Finally we discuss aspects of linguistic formalisms and interoperability.
We report on finished work in a project that is concerned with providing methods, tools, best practice guidelines, and solutions for sustainable linguistic resources. The article discusses several general aspects of sustainability and introduces an approach to normalizing corpus data and metadata records. Moreover, the architecture of the sustainability platform implemented by the authors is described.
The paper discusses from various angles the morphosyntactic annotation of DeReKo, the Archive of General Reference Corpora of Contemporary Written German at the Institut für Deutsche Sprache (IDS), Mannheim. The paper is divided into two parts. The first part covers the practical and technical aspects of this endeavor. We present results from a recent evaluation of tools for the annotation of German text resources that have been applied to DeReKo. These tools include commercial products, especially Xerox' Finite State Tools and the Machinese products developed by the Finnish company Connexor Oy, as well as software for which academic licenses are available free of charge for academic institutions, e.g. Helmut Schmid's Tree Tagger. The second part focuses on the linguistic interpretability of the corpus annotations and more general methodological considerations concerning scientifically sound empirical linguistic research. The main challenge here is that unlike the texts themselves, the morphosyntactic annotations of DeReKo do not have the status of observed data; instead they constitute a theory and implementation-dependent interpretation. In addition, because of the enormous size of DeReKo, a systematic manual verification of the automatic annotations is not feasible. In consequence, the expected degree of inaccuracy is very high, particularly wherever linguistically challenging phenomena, such as lexical or grammatical variation, are concerned. Given these facts, a researcher using the annotations blindly will run the risk of not actually studying the language but rather the annotation tool or the theory behind it. The paper gives an overview of possible pitfalls and ways to circumvent them and discusses the opportunities offered by using annotations in corpus-based and corpus-driven grammatical research against the background of a scientifically sound methodology.
This article shows that the TEI tag set for feature structures can be adopted to represent a heterogeneous set of linguistic corpora. The majority of corpora is annotated using markup languages that are based on the Annotation Graph framework, the upcoming Linguistic Annotation Format ISO standard, or according to tag sets defined by or based upon the TEI guidelines. A unified representation comprises the separation of conceptually different annotation layers contained in the original corpus data (e.g. syntax, phonology, and semantics) into multiple XML files. These annotation layers are linked to each other implicitly by the identical textual content of all files. A suitable data structure for the representation of these annotations is a multi-rooted tree that again can be represented by the TEI and ISO tag set for feature structures. The mapping process and representational issues are discussed as well as the advantages and drawbacks associated with the use of the TEI tag set for feature structures as a storage and exchange format for linguistically annotated data.
Speech Act Verbs
(2009)
Eduard Rudolf Thurneysen
(2009)
Julius Pokorny
(2009)
We present a morphological analyzer for Spanish called SMM. SMM is implemented in the grammar development framework Malaga, which is based on the formalism of Left-Associative Grammar. We briefly present the Malaga framework, describe the implementation decisions for some interesting morphological phenomena of Spanish, and report on the evaluation results from the analysis of corpora. SMM was originally only designed for analyzing word forms; in this article we outline two approaches for using SMM and the facilities provided by Malaga to also generate verbal paradigms. SMM can also be embedded into applications by making use of the Malagaprogramming interface; we briefly discuss some application scenarios.
In this paper we present an evaluation of rule-based morphological components for German for use in an interactive editing environment. The criteria for the evaluation are deduced from the intended use of these components, namely availability, performance, programming interfaces, and analysis quality. We evaluated systems developed and maintained since decades as well as new systems. However, we note serious general shortcomings when looking closer at recent implementations and come to the conclusion that the oldest system is the only one that satisfies our requirements.
This paper presents EXMARaLDA, a system for the computer-assisted creation and analysis of spoken
language corpora. The first part contains some general observations about technological and methodological requirements for doing corpus-based pragmatics. The second part explains the systems architecture and gives an overview of its most important software components a transcription editor, a corpus management tool and a corpus query tool. The last part presents some corpora which have been or are currently being compiled with the help of EXMARaLDA.
Spoken language corpora— as used in conversation analytic research, language acquisition studies and dialectology— pose a number of challenges that are rarely addressed by corpus linguistic methodology and technology. This paper starts by giving an overview of the most important methodological issues distinguishing spoken language corpus workfrom the work with written data. It then shows what technological challenges these methodological issues entail and demonstrates how they are dealt with in the architecture and tools of the EXMARaLDA system.