This paper presents a new model for the task of contrastive opinion summarization (COS) particularly for controversial issues. Traditional COS methods, which mainly rely on sentence similarity measures are not sufficient for a complex controversial issue. We therefore propose an Expert-Guided Contrastive Opinion Summarization (ECOS) model. Compared to previous methods, our model can (1) integra...

We study the effect of focus shift on prosodic features for Marathi, a major Indian language. In our analysis, we consider different focus locations and different focus widths. We report observations of fundamental frequency, intensity, and syllabic durations of constituent words of the utterance. F0 is studied via the accent commands of the Fujisaki model. We contrast statements containing nar...

The work presented in this paper proposes to identify contrast in the form of contrastive word pairs and prosodically signal it with emphatic accents in a Text-to-Speech (TTS) application using a Hidden-Markov-Model (HMM) based speech synthesis system. We first describe a novel method to automatically detect contrastive word pairs using textual features only and report its performance on a corp...

Previous research has shown that Germans produce contrastive topics with prenuclear accents exhibiting larger f0-excursions, later peaks, and longer durations than non-contrastive topics (Braun, 2006). Contrastive topic accents hence resemble L*+H, non-contrastive topic accents L+H*, but expert labelers experience difficulties in consistently labeling this distinction (ibid). Offline acceptabil...

To indicate that a referent is minimally distinguishable from a previously mentioned antecedent speakers can use contrastive intonation. Commonly, the antecedent is shared with the listener. However, in natural discourse interlocutors may not share all information. In a previous study we found that typically developing speakers can account for such perspective differences when producing contras...

One of the biggest difficulties in automatic speech recognition (ASR) is how to deal with variations of speech signals caused by non-linguistic information, such as age, gender, etc. Various methods have been proposed to compensate for the variations and one of them is speech structure [1]. Speech structure, which extracts only contrastive features and discards absolute features, is proved to b...

With the continual growth of the internet as a source of information, where a great amount of data is being uploaded every minute, the need for data compression is getting more important. This applies also to textual documents. As the amount of data grows, the probability of multiple similar documents is increasing. One way how to deal with this is to reduce the text, i.e. to use document summa...