Annette Hautli-Janisz

Visual linguistic analysis of political discussions: Measuring deliberative quality

This article reports on a Digital Humanities research project which is concerned with the automated linguistic and visual analysis of political discourses with a particular focus on the concept of deliberative communication. According to the theory of deliberative communication as discussed within political science, political debates should be inclusive and stakeholders participating in these debates are required to justify their positions rationally and respectfully and should eventually defer to the better argument. The focus of the article is on the novel interactive visualizations that combine linguistic and statistical cues to analyze the deliberative quality of communication automatically. In particular, we quantify the degree of deliberation for four dimensions of communication: Participation, Respect, Argumentation and Justification, and Persuasiveness. Yet, these four dimensions have not been linked within a combined linguistic and visual framework, but each single dimension helps determining the degree of deliberation independently from each other. Since at its core, deliberation requires sustained and appropriate modes of communication, our main contribution is the automatic annotation and disambiguation of causal connectors and discourse particles.

Automatic Detection of Causal Relations in German Multilogs

This paper introduces a linguisticallymotivated, rule-based annotation system for causal discourse relations in transcripts of spoken multilogs in German. The overall aim is an automatic means of determining the degree of justification provided by a speaker in the delivery of an argument in a multiparty discussion. The system comprises of two parts: A disambiguation module which differentiates causal connectors from their other senses, and a discourse relation annotation system which marks the spans of text that constitute the reason and the result/conclusion expressed by the causal relation. The system is evaluated against a gold standard of German transcribed spoken dialogue. The results show that our system performs reliably well with respect to both tasks.

Interactive Visual Analysis of Transcribed Multi-Party Discourse.

We present the first web-based Visual Analytics framework for the analysis of multi-party discourse data using verbatim text transcripts. Our framework supports a broad range of server-based processing steps, ranging from data mining and statistical analysis to deep linguistic parsing of English and German. On the client-side, browser-based Visual Analytics components enable multiple perspectives on the analyzed data. These interactive visualizations allow exploratory content analysis, argumentation pattern review and speaker interaction modeling.

Rhetorical strategies in German argumentative dialogs

An important factor of argument mining in dialog or multilog data is the framing with which interlocutors put forth their arguments. By using rhetorical devices such as hedging or reference to the Common Ground, speakers relate themselves to their interlocutors, their arguments, and the ongoing discourse. Capitalizing on theoretical linguistic insights into the semantics and pragmatics of discourse particles in German, we propose a categorization of rhetorical information that is highly relevant in natural transcribed speech. In order to shed light on the rhetorical strategies of different interlocutors in large amounts of real mediation data, we use a method from Visual Analytics which allows for an exploration of the rhetorical patterns via an interactive visual interface. With this innovative combination of theoretical linguistics, argument mining and information visualization, we offer a novel way of analyzing framing strategies in large amounts of multi-party argumentative discourse in German.

Pushpak Bhattacharyya: Machine translation

Machine Translation by Pushpak Bhattacharyya is a textbook for students who have a prior knowledge of core concepts of natural language processing and machine translation and are familiar with Indian languages. The book’s focus lies on illustrating the three main paradigms of MT, namely rule-based machine translation (RBMT), example-based machine translation (EBMT) and statistical machine translation (SMT), discussing them in the light of the properties of Indian languages, in particular Hindi, Sanskrit, Marathi, Bengali, Tamil and Manipuri, among others. The book is the first of its kind focusing on MT between Indian languages and those that are more widely discussed, e.g. English or German, and is therefore a highly laudable undertaking in working and teaching on the lesser-resourced languages in NLP. The book has seven chapters, each of which features a section on further reading, and is available in hard-copy and as ebook. Chapter 1 starts out with an example in the style of Kevin Knight’s (1997) famous Centauri to Arcturan translation, followed by a detailed discussion of the Vauquois triangle and the challenges of Indian languages with respect to the different levels of processing depth. In the light of the languages at issue, the chapter then offers a slightly more linguistic section, where language divergences between Hindi/Maharati and English, with a particular focus of syntactic and lexical semantic differences, are described. The chapter is complemented by an overview of the three main paradigms of MT, namely RBMT, EBMT and SMT, and briefly mentions some basic facts of evaluating MT output, in particular regarding the criteria of adequacy and fluency and the standard measures of precision, recall and F-score.