Refine
Year of publication
- 2009 (49) (remove)
Document Type
- Conference Proceeding (17)
- Part of a Book (16)
- Article (11)
- Book (2)
- Contribution to a Periodical (1)
- Doctoral Thesis (1)
- Working Paper (1)
Language
- English (49) (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
- Elsevier (3)
- Acta Universitatis Upsaliensis (2)
- Benjamins (2)
- Narr (2)
- Niemeyer (2)
- Oxford University Press (2)
- Palgrave Macmillan (2)
- Springer (2)
- AAAI Press (1)
- Association for Computational Linguistics (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.