The 50 most recently published documents
Traditionally, research on language change has been a post-mortem activity, focused on isolated changes that are complete and often only documented in written texts. In the 1960s the field was advanced considerably by Labovian sociolinguistics and the investigation of “change in progress” adduced through patterns of community-internal linguistic variation correlated with external facts about speakers such as age and class (see Labov 1994 for an overview). However, despite the many benefits of such work on “dynamic synchrony,” we still know relatively little about how language change unfolds over the lifetimes of individual speakers, that is, in real time (cf. Bailey et al. 1991). The logistical challenges of such research are, of course, considerable. Whereas it is straightforward for psycholinguists to observe language development in children over the course of a few years, documenting changes in the verbal behavior of individuals over several decades is by contrast much less feasible. Nevertheless, present theoretical models of language change could be considerably improved by the results of real-time studies.
Berichtet wird aus einem Forschungsprojekt des Instituts für deutsche Sprache, Mannheim, das sich zum Ziel gesetzt hat, Sprachwandel in statu nascendi zu beobachten, den Sprecher und die individuellen Veränderungen seines Sprechens und seiner Einstellung zur Sprache nach Ablauf von etwa vier Jahrzehnten in den Blick zu nehmen. Erneut interviewt werden Sprecher deutscher Dialekte oder Umgangssprachen, die in verschiedenen Forschungsprojekten in den 50er und 60er Jahren aufgenommen wurden und von denen eine Tonbandaufnahme im Deutschen Spracharchiv archiviert ist. Im Rahmen einer dem Forschungsprojekt vorgeschalteten inzwischen abgeschlossenen Pilotstudie wurde ein umfängliches methodisches Instrumentarium erprobt, um aussagekräftiges Vergleichsmaterial und Sprachbiographien einiger ausgewählter Sprecher elizitieren zu können. Auf der Basis dieser Studie werden das Projektdesign und die Analysekategorien für die Hauptuntersuchung festgelegt.
In this paper, we describe MLSA, a publicly available multi-layered reference corpus for German-language sentiment analysis. The construction of the corpus is based on the manual annotation of 270 German-language sentences considering three different layers of granularity. The sentence-layer annotation, as the most coarse-grained annotation, focuses on aspects of objectivity, subjectivity and the overall polarity of the respective sentences. Layer 2 is concerned with polarity on the word- and phrase-level, annotating both subjective and factual language. The annotations on Layer 3 focus on the expression-level, denoting frames of private states such as objective and direct speech events. These three layers and their respective annotations are intended to be fully independent of each other. At the same time, exploring for and discovering interactions that may exist between different layers should also be possible. The reliability of the respective annotations was assessed using the average pairwise agreement and Fleiss’ multi-rater measures. We believe that MLSA is a beneficial resource for sentiment analysis research, algorithms and applications that focus on the German language.
We use a convolutional neural network to perform authorship identification on a very homogeneous dataset of scientific publications. In order to investigate the effect of domain biases, we obscure words below a certain frequency threshold, retaining only their POS-tags. This procedure improves test performance due to better generalization on unseen data. Using our method, we are able to predict the authors of scientific publications in the same discipline at levels well above chance.
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.
Bootstrapping Supervised Machine-learning Polarity Classifiers with Rule-based Classification
(2010)
In this paper, we explore the effectiveness of bootstrapping supervised machine-learning polarity classifiers using the output of domain-independent rule-based classifiers. The benefit of this method is that no labeled training data are required. Still, this method allows to capture in-domain knowledge by training the supervised classifier on in-domain features, such as bag of words.
We investigate how important the quality of the rule-based classifier is and what features are useful for the supervised classifier. The former addresses the issue in how far relevant constructions for polarity classification, such as word sense disambiguation, negation modeling, or intensification, are important for this self-training approach. We not only compare how this method relates to conventional semi-supervised learning but also examine how it performs under more difficult settings in which classes are not balanced and mixed reviews are included in the dataset.
Opinion holder extraction is one of the important subtasks in sentiment analysis. The effective detection of an opinion holder depends on the consideration of various cues on various levels of representation, though they are hard to formulate explicitly as features. In this work, we propose to use convolution kernels for that task which identify meaningful fragments of sequences or trees by themselves. We not only investigate how different levels of information can be effectively combined in different kernels but also examine how the scope of these kernels should be chosen. In general relation extraction, the two candidate entities thought to be involved in a relation are commonly chosen to be the boundaries of sequences and trees. The definition of boundaries in opinion holder extraction, however, is less straightforward since there might be several expressions beside the candidate opinion holder to be eligible for being a boundary.
This paper presents a survey on hate speech detection. Given the steadily growing body of social media content, the amount of online hate speech is also increasing. Due to the massive scale of the web, methods that automatically detect hate speech are required. Our survey describes key areas that have been explored to automatically recognize these types of utterances using natural language processing. We also discuss limits of those approaches.
We present a gold standard for semantic relation extraction in the food domain for German. The relation types that we address are motivated by scenarios for which IT applications present a commercial potential, such as virtual customer advice in which a virtual agent assists a customer in a supermarket in finding those products that satisfy their needs best. Moreover, we focus on those relation types that can be extracted from natural language text corpora, ideally content from the internet, such as web forums, that are easy to retrieve. A typical relation type that meets these requirements are pairs of food items that are usually consumed together. Such a relation type could be used by a virtual agent to suggest additional products available in a shop that would potentially complement the items a customer has already in their shopping cart. Our gold standard comprises structural data, i.e. relation tables, which encode relation instances. These tables are vital in order to evaluate natural language processing systems that extract those relations.
Der Beitrag beschäftigt sich mit der Interaktion zwischen blinden und sehenden Personen bei der kooperativen Anfertigung einer Audiodeskription. Eine Audio-deskription ist die verbale Beschreibung visueller Inhalte für Sehbeeinträchtigte und stellt eine Sonderform der Translation dar. Auf der Basis von Videodaten wird die Kooperation eines Dreierteams mit den Verfahren der multimodalen Interaktionsanalyse untersucht. Ein Charakteristikum dieser Kooperation besteht darin, dass eines der Teammitglieder blind ist und die beiden anderen sehen können. Das Erkenntnisinteresse richtet sich besonders auf die professionelle Beteiligung des blinden Teammitglieds an der Interaktion. Die Analyse zeigt, wie Blindheit als Ressource für die kooperative Herstellung der Audiodeskription genutzt wird und wie die Beteiligten in einer visuell asymmetrischen Situation interagieren. Der Beitrag ist eine der seltenen Untersuchungen, die sich mit professioneller Interaktion zwischen Blinden und Sehenden beschäftigen. Er diskutiert Aspekte von genereller Relevanz für die weitere Entwicklung der empirischen Interaktionsforschung, vor allem in Bezug auf eine Erweiterung von Beteiligungsperspektiven in Richtung Inklusion.
Bibliographie
(1980)
Automatic Food Categorization from Large Unlabeled Corpora and Its Impact on Relation Extraction
(2014)
We present a weakly-supervised induction method to assign semantic information to food items. We consider two tasks of categorizations being food-type classification and the distinction of whether a food item is composite or not. The categorizations are induced by a graph-based algorithm applied on a large unlabeled domain-specific corpus. We show that the usage of a domain-specific corpus is vital. We do not only outperform a manually designed open-domain ontology but also prove the usefulness of these categorizations in relation extraction, outperforming state-of-the-art features that include syntactic information and Brown clustering.
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.
In order to automatically extract opinion holders, we propose to harness the contexts of prototypical opinion holders, i.e. common nouns, such as experts or analysts, that describe particular groups of people whose profession or occupation is to form and express opinions towards specific items. We assess their effectiveness in supervised learning where these contexts are regarded as labelled training data and in rule-based classification which uses predicates that frequently co-occur with mentions of the prototypical opinion holders. Finally, we also examine in how far knowledge gained from these contexts can compensate the lack of large amounts of labeled training data in supervised learning by considering various amounts of actually labeled training sets.
We investigate the task of detecting reliable statements about food-health relationships from natural language texts. For that purpose, we created a specially annotated web corpus from forum entries discussing the healthiness of certain food items. We examine a set of task-specific features (mostly) based on linguistic insights that are instrumental in finding utterances that are commonly perceived as reliable. These features are incorporated in a supervised classifier and compared against standard features that are widely used for various tasks in natural language processing, such as bag of words, part-of speech and syntactic parse information.
In this paper, we examine methods to automatically extract domain-specific knowledge from the food domain from unlabeled natural language text. We employ different extraction methods ranging from surface patterns to co-occurrence measures applied on different parts of a document. We show that the effectiveness of a particular method depends very much on the relation type considered and that there is no single method that works equally well for every relation type. We also examine a combination of extraction methods and also consider relationships between different relation types. The extraction methods are applied both on a domain-specific corpus and the domain-independent factual knowledge base Wikipedia. Moreover, we examine an open-domain lexical ontology for suitability.
In this paper, we investigate the role of predicates in opinion holder extraction. We will examine the shape of these predicates, investigate what relationship they bear towards opinion holders, determine what resources are potentially useful for acquiring them, and point out limitations of an opinion holder extraction system based on these predicates. For this study, we will carry out an evaluation on a corpus annotated with opinion holders. Our insights are, in particular, important for situations in which no labelled training data are available and only rule-based methods can be applied.
In this paper, we compare three different generalization methods for in-domain and cross-domain opinion holder extraction being simple unsupervised word clustering, an induction method inspired by distant supervision and the usage of lexical resources. The generalization methods are incorporated into diverse classifiers. We show that generalization causes significant improvements and that the impact of improvement depends on the type of classifier and on how much training and test data differ from each other. We also address the less common case of opinion holders being realized in patient position and suggest approaches including a novel (linguistically-informed) extraction method how to detect those opinion holders without labeled training data as standard datasets contain too few instances of this type.
We address the detection of abusive words. The task is to identify such words among a set of negative polar expressions. We propose novel features employing information from both corpora and lexical resources. These features are calibrated on a small manually annotated base lexicon which we use to produce a large lexicon. We show that the word-level information we learn cannot be equally derived from a large dataset of annotated microposts. We demonstrate the effectiveness of our (domain-independent) lexicon in the crossdomain detection of abusive microposts.
Both compounds and multi-word expressions are complex lexical units, made up of at least two constituents. The most basic difference is that the former are morphological objects and the latter result from syntactic processes. However, the exact demarcation between compounds and multi-word expressions differs greatly from language to language and is often a matter of debate in and across languages. Similarly debated is whether and how these two different kinds of units complement or compete with each other.
The volume presents an overview of compounds and multi-word expressions in a variety of European languages. Central questions that are discussed for each language concern the formal distinction between compounds and multi-word expressions, their formation and their status in lexicon and grammar.
The volume contains chapters on German, English, Dutch, French, Italian, Spanish, Greek, Russian, Polish, Finnish, and Hungarian as well as a contrastive overview with a focus on German. It brings together insights from word-formation theory, phraseology and theory of grammar and aims to contribute to the understanding of the lexicon, both from a language-specific and cross-linguistic perspective.
Based on the empirical data of 97 fourth-graders from three districts of Braunschweig in Germany, this paper investigates the possibility of changing semantic frames in multilingual communities. The focus of study is the verb field of self-motion. In a free-sorting task involving 52 verbs, Turkish-speaking students, in particular, placed the verbs schleichen (‘to sneak’) and kommen (‘to come’) in the same group. When explaining the perceived similarity they also used the word schleichen (‘to sneak’), in a specific grammatical construction that is not found in Standard German. This paper suggests that semantic frames may change along with grammatical constructions when typologically distinct languages come into close contact.
Defining groups and affiliating the self and the other with specific social categories is an important part of constructing a colonial conceptualization of societies. Many written documents from the colonial period attest to this practice. The current paper focuses on missionaries’ ways of positioning themselves and others within the colonial context. The German speaking Rheinische Missionsgesellschaft (RMG, Rhenish Mission Society) established mission stations in the Astrolabe Bay area of New Guinea, an area that was under German domination between 1884 and 1914. The paper analyzes how RMG missionaries, by means of language, construct, define, and position different population groups, and it investigates what patterns emerge from these language practices.
We report on the two systems we built for Task 1 of the German Sentiment Analysis Shared Task, the task on Source, Subjective Expression and Target Extraction from Political Speeches (STEPS). The first system is a rule-based system relying on a predicate lexicon specifying extraction rules for verbs, nouns and adjectives, while the second is a translation-based system that has been obtained with the help of the (English) MPQA corpus.
We present the German Sentiment Analysis Shared Task (GESTALT) which consists of two main tasks: Source, Subjective Expression and Target Extraction from Political Speeches (STEPS) and Subjective Phrase and Aspect Extraction from Product Reviews (StAR). Both tasks focused on fine-grained sentiment analysis, extracting aspects and targets with their associated subjective expressions in the German language. STEPS focused on political discussions from a corpus of speeches in the Swiss parliament. StAR fostered the analysis of product reviews as they are available from the website Amazon.de. Each shared task led to one participating submission, providing baselines for future editions of this task and highlighting specific challenges. The shared task homepage can be found at https://sites.google.com/site/iggsasharedtask/.
Terminological resources play a central role in the organization and retrieval of scientific texts. Both simple keyword lists and advanced modelings of relationships between terminological concepts can make a most valuable contribution to the analysis, classification, and finding of appropriate digital documents, either on the web or within local repositories. This seems especially true for long-established scientific fields with elusive theoretical and historical branches, where the use of terminology within documents from different origins is often far from being consistent. In this paper, we report on the progress of a linguistically motivated project on the onomasiological re-modeling of the terminological resources for the grammatical information system grammis. We present the design principles and the results of their application. In particular, we focus on new features for the authoring backend and discuss how these innovations help to evaluate existing, loosely structured terminological content, as well as to efficiently deal with automatic term extraction. Furthermore, we introduce a transformation to a future SKOS representation. We conclude with a positioning of our resources with regard to the Knowledge Organization discourse and discuss how a highly complex information environment like grammis benefits from the re-designed terminological KOS.
This paper critically examines some recent performativist conceptions of analysing and describing interpretation of explicit performatives. In an alternative constativist approach the paper tries to determine the illocutionary point of explicit performatives on the basis of sentence mood, lexical information (i.e. the meaning of the speech act verb), utterance meaning, speaker’s authority, and some general principles of social behaviour.