Refine
Year of publication
Document Type
- Conference Proceeding (62)
- Part of a Book (19)
- Article (13)
- Working Paper (2)
- Book (1)
- Doctoral Thesis (1)
Keywords
- Automatische Sprachanalyse (29)
- Deutsch (20)
- Korpus <Linguistik> (17)
- Computerlinguistik (16)
- Frame-Semantik (15)
- Annotation (14)
- Semantische Analyse (14)
- Propositionale Einstellung (10)
- Beleidigung (9)
- sentiment analysis (9)
Publicationstate
- Veröffentlichungsversion (75)
- Zweitveröffentlichung (8)
- Postprint (5)
Reviewstate
Publisher
- Association for Computational Linguistics (13)
- European Language Resources Association (10)
- The Association for Computational Linguistics (9)
- German Society for Computational Linguistics & Language Technology und Friedrich-Alexander-Universität Erlangen-Nürnberg (4)
- Springer (4)
- European Language Resources Association (ELRA) (3)
- European language resources association (ELRA) (3)
- Oxford University Press (3)
- Universität Hildesheim (3)
- EACL (2)
This paper presents an annotation scheme for English modal verbs together with sense-annotated data from the news domain. We describe our annotation scheme and discuss problematic cases for modality annotation based on the inter-annotator agreement during the annotation. Furthermore, we present experiments on automatic sense tagging, showing that our annotations do provide a valuable training resource for NLP systems.
This paper presents a compositional annotation scheme to capture the clusivity properties of personal pronouns in context, that is their ability to construct and manage in-groups and out-groups by including/excluding the audience and/or non-speech act participants in reference to groups that also include the speaker. We apply and test our schema on pronoun instances in speeches taken from the German parliament. The speeches cover a time period from 2017-2021 and comprise manual annotations for 3,126 sentences. We achieve high inter-annotator agreement for our new schema, with a Cohen’s κ in the range of 89.7-93.2 and a percentage agreement of > 96%. Our exploratory analysis of in/exclusive pronoun use in the parliamentary setting provides some face validity for our new schema. Finally, we present baseline experiments for automatically predicting clusivity in political debates, with promising results for many referential constellations, yielding an overall 84.9% micro F1 for all pronouns.
Who is we? Disambiguating the referents of first person plural pronouns in parliamentary debates
(2021)
This paper investigates the use of first person plural pronouns as a rhetorical device in political speeches. We present an annotation schema for disambiguating pronoun references and use our schema to create an annotated corpus of debates from the German Bundestag. We then use our corpus to learn to automatically resolve pronoun referents in parliamentary debates. We explore the use of data augmentation with weak supervision to further expand our corpus and report preliminary results.
There is increasing interest in recognizing opinion inferences in addition to expressions of explicit sentiment. While different formalisms for representing inferential mechanisms are being developed and lexical resources are being built alongside, we here address the need for deeper investigation of the robustness of various aspects of opinion inference, performing crowdsourcing experiments with constructed stimuli as well as a corpus study of attested data.
We provide a unified account of semantic effects observable in attested examples of the German applicative (‘be-’) construction, e.g. Rollstuhlfahrer Poul Sehachsen aus Kopenhagen will den 1997 erschienenen Wegweiser Handiguide Europa fortführen und zusammen mit Movado Berlin berollen (‘Wheelchair user Poul Schacksen from Copenhagen wants to continue the guide ‘Handiguide Europe’, which came out in 1997, and roll Berlin together with Movado.’). We argue that these effects do not come from lexico-semantic operations on ‘input’ verbs, but are instead the products of a reconciliation procedure in which the meaning of the verb is integrated into the event-structure schema denoted by the applicative construction. We analyze the applicative pattern as an argument-structure construction, in terms of Goldberg (1995). We contrast this approach with that of Brinkmann (1997), in which properties associated with the applicative pattern (e.g. omissibility of the theme argument, holistic interpretation of the goal argument, and planar construal of the location argument) are attributed to general semantico-pragmatic principles. We undermine the generality of the principles as stated, and assert that these properties are instead construction-particular. We further argue that the constructional account provides an elegant model of the valence-creation and valence-augmentation functions of the prefix. We describe the constructional semantics as prototype-based: diverse implications of fee-predications, including iteration, transfer, affectedness, intensity and saturation, derive via regular patterns of semantic extension from the topological concept of coverage.
We provide a unified account of semantic effects observable in attested examples of the German applicative (‘be-’) construction, e.g. Rollstuhlfahrer Poul Sehachsen aus Kopenhagen will den 1997 erschienenen Wegweiser Handiguide Europa fortführen und zusammen mit Movado Berlin berollen (‘Wheelchair user Poul Schacksen from Copenhagen wants to continue the guide ‘Handiguide Europe’, which came out in 1997, and roll Berlin together with Movado.’). We argue that these effects do not come from lexico-semantic operations on ‘input’ verbs, but are instead the products of a reconciliation procedure in which the meaning of the verb is integrated into the event-structure schema denoted by the applicative construction. We analyze the applicative pattern as an argument-structure construction, in terms of Goldberg (1995). We contrast this approach with that of Brinkmann (1997), in which properties associated with the applicative pattern (e.g. omissibility of the theme argument, holistic interpretation of the goal argument, and planar construal of the location argument) are attributed to general semantico-pragmatic principles. We undermine the generality of the principles as stated, and assert that these properties are instead construction-particular. We further argue that the constructional account provides an elegant model of the valence-creation and valence-augmentation functions of the prefix. We describe the constructional semantics as prototype-based: diverse implications of fee-predications, including iteration, transfer, affectedness, intensity and saturation, derive via regular patterns of semantic extension from the topological concept of coverage.
This article presents a discussion on the main linguistic phenomena which cause difficulties in the analysis of user-generated texts found on the web and in social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework of syntactic analysis. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this article is twofold: (1) to provide a condensed, though comprehensive, overview of such treebanks—based on available literature—along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The overarching goal of this article is to provide a common framework for researchers interested in developing similar resources in UD, thus promoting cross-linguistic consistency, which is a principle that has always been central to the spirit of UD.
The paper presents a discussion on the main linguistic phenomena of user-generated texts found in web and social media, and proposes a set of annotation guidelines for their treatment within the Universal Dependencies (UD) framework. Given on the one hand the increasing number of treebanks featuring user-generated content, and its somewhat inconsistent treatment in these resources on the other, the aim of this paper is twofold: (1) to provide a short, though comprehensive, overview of such treebanks - based on available literature - along with their main features and a comparative analysis of their annotation criteria, and (2) to propose a set of tentative UD-based annotation guidelines, to promote consistent treatment of the particular phenomena found in these types of texts. The main goal of this paper is to provide a common framework for those teams interested in developing similar resources in UD, thus enabling cross-linguistic consistency, which is a principle that has always been in the spirit of UD.
This paper addresses the task of finding antecedents for locally uninstantiated arguments. To resolve such null instantiations, we develop a weakly supervised approach that investigates and combines a number of linguistically motivated strategies that are inspired by work on semantic role labeling and corefence resolution. The performance of the system is competitive with the current state-of-the-art supervised system.
We present a major step towards the creation of the first high-coverage lexicon of polarity shifters. In this work, we bootstrap a lexicon of verbs by exploiting various linguistic features. Polarity shifters, such as ‘abandon’, are similar to negations (e.g. ‘not’) in that they move the polarity of a phrase towards its inverse, as in ‘abandon all hope’. While there exist lists of negation words, creating comprehensive lists of polarity shifters is far more challenging due to their sheer number. On a sample of manually annotated verbs we examine a variety of linguistic features for this task. Then we build a supervised classifier to increase coverage. We show that this approach drastically reduces the annotation effort while ensuring a high-precision lexicon. We also show that our acquired knowledge of verbal polarity shifters improves phrase-level sentiment analysis.
In the paper we investigate the impact of data size on a Word Sense Disambiguation task (WSD). We question the assumption that the knowledge acquisition bottleneck, which is known as one of the major challenges for WSD, can be solved by simply obtaining more and more training data. Our case study on 1,000 manually annotated instances of the German verb drohen (threaten) shows that the best performance is not obtained when training on the full data set, but by carefully selecting new training instances with regard to their informativeness for the learning process (Active Learning). We present a thorough evaluation of the impact of different sampling methods on the data sets and propose an improved method for uncertainty sampling which dynamically adapts the selection of new instances to the learning progress of the classifier, resulting in more robust results during the initial stages of learning. A qualitative error analysis identifies problems for automatic WSD and discusses the reasons for the great gap in performance between human annotators and our automatic WSD system.
Both for psychology and linguistics, emotion concepts are a continuing challenge for analysis in several respects. In this contribution, we take up the language of emotion as an object of study from several angles. First, we consider how frame semantic analyses of this domain by the FrameNet project have been developing over time, due to theory-internal as well as application-oriented goals, towards ever more fine-grained distinctions and greater within-frame consistency. Second, we compare how FrameNet’s linguistically oriented analysis of lexical items in the emotion domain compares to the analysis by domain experts of the experiences that give rise (directly or indirectly) to the lexical items. And finally, we consider to what extent frame semantic analysis can capture phenomena such as connotation and inference about attitudes, which are important in the field of sentiment analysis and opinion mining, even if they do not involve the direct evocation of emotion.
This dissertation investigates discourse-pragmatic differences between variably linked arguments appearing in alternating argument structure constructions in the sense of Goldberg (1995) and Kay (manuscript). The properties that are studied include givenness, pragmatic relation (topic/focus), salience of referents, animacy, and others. They derive from the literature on sentence-type constructions such as topicalization and from research on the referential properties of NP form types.
The research carried out here has multiple uses. At the most basic level, it serves as an empirical check on existing characterizations of the pragmatic properties of the relevant arguments that are the result of syntactic and semantic analysis based on introspection alone. For instance, for the epistemic raising alternation involving verbs like seem, the predicted topicality difference between the subjects of the raised and unraised constructions (Langacker 1995) could not be confirmed.
This dissertation also addresses the question what kinds of pragmatic factors, if any, are relevant to argument structure constructions. Based on the evidence of the dative alternation, it does not seem to be the case that the kind of pragmatic influences on argument structure constructions are different or limited compared to the ones found to be relevant to sentence-type constructions.
The kind of research undertaken here can also inform the syntactic and semantic analysis of constructions. In the case of the dative alternation, the discourse-pragmatic characteristics of the variably linked arguments provide evidence that Basilico’s (1998) analysis of the difference between the alternates in terms of VP-shells and a difference between thetic and categorical ‘inner’ predication, on the one hand does not account for all the data and on the other can be re-stated in pragmatic terms other than the thetic-categorical distinction.
In addition to studies of valence alternations, this dissertation also discusses various null instantiation phenomena, which provide further evidence for the need to specify discourse-pragmatic properties as part of argument structure constructions and lexical entries.
Finally, it is suggested that the use of randomly sampled corpus data and statistical modelling throughout this dissertation improves both empirical and analytical coverage.
We present a method for detecting annotation errors in manually and automatically annotated dependency parse trees, based on ensemble parsing in combination with Bayesian inference, guided by active learning. We evaluate our method in different scenarios: (i) for error detection in dependency treebanks and (ii) for improving parsing accuracy on in- and out-of-domain data.
Historical cabinet protocols are a useful resource which enable historians to identify the opinions expressed by politicians on different subjects and at different points of time. While cabinet protocols are often available in digitized form, so far the only method to access their information content is by keyword-based search, which often returns sub-optimal results. We present a method for enriching German cabinet protocols with information about the originators of statements. This requires automatic speaker attribution. In order to avoid costly manual annotation of training data, we design a rule-based system which exploits morpho-syntactic cues. Unlike many other approaches, our method can also deal with cases in which the speaker is not explicitly identified in the sentence itself. This is an important capability as 45% of all sentences in the data constitute reported speech whose speakers are not explicitly marked. Our system is able to detect implicit speakers by taking into account signals of speaker continuity. We show that such a system obtains good results, especially with respect to recall which is particularly important for information access.
When a noise verb is used to indicate verbal communication, factors from both the source domain of the verb (perception) and the target domain (communication) play a role in determining the argument structure of the sentence. While the target domain supplies a syntactic structure, the source domain’s semantics constrain the degree to which that syntactic structure can be exploited. This can be determined by comparing noise verbs in this use with manner-of-communication verbs, which are superficially similar, but native to communication. Data for these two classes of verbs were drawn from the British National Corpus. The data were annotated with frame-semantic markup, as described in the Berkeley FrameNet Project. We compared the presence, type of syntactic realization, and position of the semantically annotated arguments for both classes of verbs. We found that noise and manner verbs show statistically significant differences in these three areas. For instance, noise verbs are more focused on the form of the message than manner verbs: noise verbs appear more frequently with a quoted message. In addition, there are differences other than the complementation patterns: certain noise verbs are biased with respect to speakers’ genders, message types, and even orthography in quoted messages
We examine different features and classifiers for the categorization of opinion words into actor and speaker view. To our knowledge, this is the first comprehensive work to address sentiment views on the word level taking into consideration opinion verbs, nouns and adjectives. We consider many high-level features requiring only few labeled training data. A detailed feature analysis produces linguistic insights into the nature of sentiment views. We also examine how far global constraints between different opinion words help to increase classification performance. Finally, we show that our (prior) word-level annotation correlates with contextual sentiment views.
We describe the SemEval-2010 shared task on “Linking Events and Their Participants in Discourse”. This task is an extension to the classical semantic role labeling task. While semantic role labeling is traditionally viewed as a sentence-internal task, local semantic argument structures clearly interact with each other in a larger context, e.g., by sharing references to specific discourse entities or events. In the shared task we looked at one particular aspect of cross-sentence links between argument structures, namely linking locally uninstantiated roles to their co-referents in the wider discourse context (if such co-referents exist). This task is potentially beneficial for a number of NLP applications, such as information extraction, question answering or text summarization.
Current work on sentiment analysis is characterized by approaches with a pragmatic focus, which use shallow techniques in the interest of robustness but often rely on ad-hoc creation of data sets and methods. We argue that progress towards deep analysis depends on a) enriching shallow representations with linguistically motivated, rich information, and b) focussing different branches of research and combining ressources to create synergies with related work in NLP. In the paper, we propose SentiFrameNet, an extension to FrameNet, as a novel representation for sentiment analysis that is tailored to these aims.
Scales and Scores. An evaluation of methods to determine the intensity of subjective expressions
(2015)
In this contribution, we present a survey of several methods that have been applied to the ordering of various types of subjective expressions (e.g. good < great), in particular adjectives and adverbs. Some of these methods use linguistic regularities that can be observed in large text corpora while others rely on external grounding in metadata, in particular the star ratings associated with product reviews. We discuss why these methods do not work uniformly across all types of expressions. We also present the first application of some of these methods to the intensity ordering of nouns (e.g. moron < dummy).
Reframing FrameNet Data
(2004)
The Berkeley FrameNet Project (http://www.icsi.berkeley.edu/~framenet) is building an on-line lexical resource for contemporary English. The database provides information about the semantic and syntactic combinatorial possibilities (valences) of each item analyzed. This paper describes the conceptual basis for what has been called reframing of data in the FrameNet database and exemplifies two new frame-to-frame relations, Causative_of and Inchoative_of, the implementation of which came about as a result of reanalysis of certain frames and lexical units. The new relations are characterized with respect to a triple of frames involving the notion of attaching, and entering them into the database is demonstrated using the Frame Relations Editor. The two relations allow FrameNet to make frame-wise distinctions that capture fairly systematic semantic relationships across sets of lexical units. While the Inheritance and Subframe relations are of particular interest to the NLP research community, Causative_of and Inchoative_of may be more relevant to lexicography.
We examine predicative adjectives as an unsupervised criterion to extract subjective adjectives. We do not only compare this criterion with a weakly supervised extraction method but also with gradable adjectives, i.e. another highly subjective subset of adjectives that can be extracted in an unsupervised fashion. In order to prove the robustness of this extraction method, we will evaluate the extraction with the help of two different state-of-the-art sentiment lexicons (as a gold standard).
Overview of the IGGSA 2016 Shared Task on Source and Target Extraction from Political Speeches
(2016)
We present the second iteration of IGGSA’s Shared Task on Sentiment Analysis for German. It resumes the STEPS task of IGGSA’s 2014 evaluation campaign: Source, Subjective Expression and Target Extraction from Political Speeches. As before, the task is focused on fine-grained sentiment analysis, extracting sources and targets with their associated subjective expressions from a corpus of speeches given in the Swiss parliament. The second iteration exhibits some differences, however; mainly the use of an adjudicated gold standard and the availability of training data. The shared task had 2 participants submitting 7 runs for the full task and 3 runs for each of the subtasks. We evaluate the results and compare them to the baselines provided by the previous iteration. The shared task homepage can be found at http://iggsasharedtask2016.github.io/.
We present the pilot edition of the GermEval Shared Task on the Identification of Offensive Language. This shared task deals with the classification of German tweets from Twitter. It comprises two tasks, a coarse-grained binary classification task and a fine-grained multi-class classification task. The shared task had 20 participants submitting 51 runs for the coarse-grained task and 25 runs for the fine-grained task. Since this is a pilot task, we describe the process of extracting the raw-data for the data collection and the annotation schema. We evaluate the results of the systems submitted to the shared task. The shared task homepage can be found at https://projects.cai. fbi.h-da.de/iggsa/
We present the second edition of the GermEval Shared Task on the Identification of Offensive Language. This shared task deals with the classification of German tweets from Twitter. Two subtasks were continued from the first edition, namely a coarse-grained binary classification task and a fine-grained multi-class classification task. As a novel subtask, we introduce the classification of offensive tweets as explicit or implicit.
The shared task had 13 participating groups submitting 28 runs for the coarse-grained
task, another 28 runs for the fine-grained task, and 17 runs for the implicit-explicit
task.
We evaluate the results of the systems submitted to the shared task. The shared task homepage can be found at https://projects.fzai.h-da.de/iggsa/
In recent years, theoretical and computational linguistics has paid much attention to linguistic items that form scales. In NLP, much research has focused on ordering adjectives by intensity (tiny < small). Here, we address the task of automatically ordering English adverbs by their intensifying or diminishing effect on adjectives (e.g. extremely small < very small). We experiment with 4 different methods: 1) using the association strength between adverbs and adjectives; 2) exploiting scalar patterns (such as not only X but Y); 3) using the metadata of product reviews; 4) clustering. The method that performs best is based on the use of metadata and ranks adverbs by their scaling factor relative to unmodified adjectives.
We present an approach to the new task of opinion holder and target extraction on opinion compounds. Opinion compounds (e.g. user rating or victim support) are noun compounds whose head is an opinion noun. We do not only examine features known to be effective for noun compound analysis, such as paraphrases and semantic classes of heads and modifiers, but also propose novel features tailored to this new task. Among them, we examine paraphrases that jointly consider holders and targets, a verb detour in which noun heads are replaced by related verbs, a global head constraint allowing inferencing between different compounds, and the categorization of the sentiment view that the head conveys.
Opinion Holder and Target Extraction for Verb-based Opinion Predicates – The Problem is Not Solved
(2015)
We offer a critical review of the current state of opinion role extraction involving opinion verbs. We argue that neither the currently available lexical resources nor the manually annotated text corpora are sufficient to appropriately study this task. We introduce a new corpus focusing on opinion roles of opinion verbs from the Subjectivity Lexicon and show potential benefits of this corpus. We also demonstrate that state-of-the-art classifiers perform rather poorly on this new dataset compared to the standard dataset for the task showing that there still remains significant research to be done.
We present an approach for opinion role induction for verbal predicates. Our model rests on the assumption that opinion verbs can be divided into three different types where each type is associated with a characteristic mapping between semantic roles and opinion holders and targets. In several experiments, we demonstrate the relevance of those three categories for the task. We show that verbs can easily be categorized with semi-supervised graphbased clustering and some appropriate similarity metric. The seeds are obtained through linguistic diagnostics. We evaluate our approach against a new manually-compiled opinion role lexicon and perform in-context classification.
Naming and titling have been discussed in sociolinguistics as markers of status or solidarity. However, these functions have not been studied on a larger scale or for social media data. We collect a corpus of tweets mentioning presidents of six G20 countries by various naming forms. We show that naming variation relates to stance towards the president in a way that is suggestive of a framing effect mediated by respectfulness. This confirms sociolinguistic theory of naming and titling as markers of status.
We present an approach for modeling German negation in open-domain fine grained sentiment analysis. Unlike most previous work in sentiment analysis, we assume that negation can be conveyed by many lexical units (and not only common negation words) and that different negation words have different scopes. Our approach is examined on a new dataset comprising sentences with mentions of polar expressions and various negation words. We identify different types of negation words that have the same scopes. We show that already negation modeling based on these types largely outperforms traditional negation models which assume the same scope for all negation words and which employ a window-based scope detection rather than a scope detection based on syntactic information.
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 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.
We introduce a system that learns the participants of arbitrary given scripts. This system processes data from web experiments, in which each participant can be realized with different expressions. It computes participants by encoding semantic similarity and global structural information into an Integer Linear Program. An evaluation against a gold standard shows that we significantly outperform two informed baselines.
I’ve got a construction looks funny – representing and recovering non-standard constructions in UD
(2020)
The UD framework defines guidelines for a crosslingual syntactic analysis in the framework of dependency grammar, with the aim of providing a consistent treatment across languages that not only supports multilingual NLP applications but also facilitates typological studies. Until now, the UD framework has mostly focussed on bilexical grammatical relations. In the paper, we propose to add a constructional perspective and discuss several examples of spoken-language constructions that occur in multiple languages and challenge the current use of basic and enhanced UD relations. The examples include cases where the surface relations are deceptive, and syntactic amalgams that either involve unconnected subtrees or structures with multiply-headed dependents. We argue that a unified treatment of constructions across languages will increase the consistency of the UD annotations and thus the quality of the treebanks for linguistic analysis.
Corpora with high-quality linguistic annotations are an essential component in many NLP applications and a valuable resource for linguistic research. For obtaining these annotations, a large amount of manual effort is needed, making the creation of these resources time-consuming and costly. One attempt to speed up the annotation process is to use supervised machine-learning systems to automatically assign (possibly erroneous) labels to the data and ask human annotators to correct them where necessary. However, it is not clear to what extent these automatic pre-annotations are successful in reducing human annotation effort, and what impact they have on the quality of the resulting resource. In this article, we present the results of an experiment in which we assess the usefulness of partial semi-automatic annotation for frame labeling. We investigate the impact of automatic pre-annotation of differing quality on annotation time, consistency and accuracy. While we found no conclusive evidence that it can speed up human annotation, we found that automatic pre-annotation does increase its overall quality.
The sentiment polarity of a phrase does not only depend on the polarities of its words, but also on how these are affected by their context. Negation words (e.g. not, no, never) can change the polarity of a phrase. Similarly, verbs and other content words can also act as polarity shifters (e.g. fail, deny, alleviate). While individually more sparse, they are far more numerous. Among verbs alone, there are more than 1200 shifters. However, sentiment analysis systems barely consider polarity shifters other than negation words. A major reason for this is the scarcity of lexicons and corpora that provide information on them. We introduce a lexicon of verbal polarity shifters that covers the entirety of verbs found in WordNet. We provide a fine-grained annotation of individual word senses, as well as information for each verbal shifter on the syntactic scopes that it can affect.
We study the influence of information structure on the salience of subjective expressions for human readers. Using an online survey tool, we conducted an experiment in which we asked users to rate main and relative clauses that contained either a single positive or negative or a neutral adjective. The statistical analysis of the data shows that subjective expressions are more prominent in main clauses where they are asserted than in relative clauses where they are presupposed. A corpus study suggests that speakers are sensitive to this differential salience in their production of subjective expressions.
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.
Semantic argument structures are often incomplete in that core arguments are not locally instantiated. However, many of these implicit arguments can be linked to referents in the wider context. In this paper we explore a number of linguistically motivated strategies for identifying and resolving such null instantiations (NIs). We show that a more sophisticated model for identifying definite NIs can lead to noticeable performance gains over the state-of-the- art for NI resolution.
This paper presents experiments on sentence boundary detection in transcripts of spoken dialogues. Segmenting spoken language into sentence-like units is a challenging task, due to disfluencies, ungrammatical or fragmented structures and the lack of punctuation. In addition, one of the main bottlenecks for many NLP applications for spoken language is the small size of the training data, as the transcription and annotation of spoken language is by far more time-consuming and labour-intensive than processing written language. We therefore investigate the benefits of data expansion and transfer learning and test different ML architectures for this task. Our results show that data expansion is not straightforward and even data from the same domain does not always improve results. They also highlight the importance of modelling, i.e. of finding the best architecture and data representation for the task at hand. For the detection of boundaries in spoken language transcripts, we achieve a substantial improvement when framing the boundary detection problem as a sentence pair classification task, as compared to a sequence tagging approach.
Implicitly abusive language – What does it actually look like and why are we not getting there?
(2021)
Abusive language detection is an emerging field in natural language processing which has received a large amount of attention recently. Still the success of automatic detection is limited. Particularly, the detection of implicitly abusive language, i.e. abusive language that is not conveyed by abusive words (e.g. dumbass or scum), is not working well. In this position paper, we explain why existing datasets make learning implicit abuse difficult and what needs to be changed in the design of such datasets. Arguing for a divide-and-conquer strategy, we present a list of subtypes of implicitly abusive language and formulate research tasks and questions for future research.
We examine the task of detecting implicitly abusive comparisons (e.g. “Your hair looks like you have been electrocuted”). Implicitly abusive comparisons are abusive comparisons in which abusive words (e.g. “dumbass” or “scum”) are absent. We detail the process of creating a novel dataset for this task via crowdsourcing that includes several measures to obtain a sufficiently representative and unbiased set of comparisons. We also present classification experiments that include a range of linguistic features that help us better understand the mechanisms underlying abusive comparisons.
Accurate opinion mining requires the exact identification of the source and target of an opinion. To evaluate diverse tools, the research community relies on the existence of a gold standard corpus covering this need. Since such a corpus is currently not available for German, the Interest Group on German Sentiment Analysis decided to create such a resource and make it available to the research community in the context of a shared task. In this paper, we describe the selection of textual sources, development of annotation guidelines, and first evaluation results in the creation of a gold standard corpus for the German language.
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/.
We address the task of distinguishing implicitly abusive sentences on identity groups (“Muslims contaminate our planet”) from other group-related negative polar sentences (“Muslims despise terrorism”). Implicitly abusive language are utterances not conveyed by abusive words (e.g. “bimbo” or “scum”). So far, the detection of such utterances could not be properly addressed since existing datasets displaying a high degree of implicit abuse are fairly biased. Following the recently-proposed strategy to solve implicit abuse by separately addressing its different subtypes, we present a new focused and less biased dataset that consists of the subtype of atomic negative sentences about identity groups. For that task, we model components that each address one facet of such implicit abuse, i.e. depiction as perpetrators, aspectual classification and non-conformist views. The approach generalizes across different identity groups and languages.
We present a quantitative approach to disambiguating flat morphological analyses and producing more deeply structured analyses. Based on existing morphological segmentations, possible combinations of resulting word trees for the next level are filtered first by criteria of linguistic plausibility and then by weighting procedures based on the geometric mean. The frequencies for weighting are derived from three different sources (counts of morphs in a lexicon, counts of largest constituents in a lexicon, counts of token frequencies in a corpus) and can be used either to find the best analysis on the level of morphs or on the next higher constituent level. The evaluation shows that for this task corpus-based frequency counts are slightly superior to counts of lexical data.