The present paper describes a methodology for automatic text summarisation of Greek texts which combines terminology extraction and sentence spotting. Since generating abstracts has proven a hard NLP task of questionable effectiveness, the paper focuses on the production of a special kind of abstracts, called extracts: sets of sentences taken from the original text. These sentences are selected...

We outline how utterances in dialogs can be interpreted using a partial rst order logic. We exploit the capability of this logic to talk about the truth status of formulae to de ne a notion of coherence between utterances and explain how this coherence relation can serve for the construction of AND/OR trees that represent the segmentation of the dialog. In a BDI model we formalize basic assumpt...

This paper reports on the beginnings of some work whose aim is to investigate the role of punctuation in signalling discourse structure. This is part of a larger enterprise motivated by the view that natural language processing systems, whether generating or understanding language, should take account of the physical manifestation of language: in the context of written language, this means taki...

In this paper, to clarify acoustic features for predicting the ends of utterances, we investigated prosodic features that project transition relevance places in Japanese spontaneous conversation. Acoustic parameters used as the prosodic features are the fundamental frequency, power, and mora duration of accentual phrases and words. Results showed that the fundamental frequency and power at the ...

The current study investigates acoustic correlates to perceived hesitation based on previous work showing that pause duration and final lengthening both contribute to the perception of hesitation. It is the total duration increase that is the valid cue rather than the contribution by either factor. The present experiment using speech synthesis was designed to evaluate F0 slope and presence vs. ...

This work aims to extract causal relations that exist between two events expressed by noun phrases or sentences. The previous works for the causality made use of causal patterns such as causal verbs. We concentrate on the information obtained from other causal event pairs. If two event pairs share some lexical pairs and one of them is revealed to be causally related, the causal probability of a...

Most text displays an internal coherence structure, which can be analyzed as a tree structure of relations that hold between short segments of text. We present a machine-learning governed approach to such an analysis in the framework of Rhetorical Structure Theory. Our rhetorical analyzer observes a variety of textual properties, such as cue phrases, part-of-speech information, rhetorical conte...

Mining causality knowledge will induce knowledge of reasoning beneficial for our daily use in diagnosis. This framework is for discovering causality existing between causative antecedent and effective consequent discourse units. There are two main problems in causality extraction; causeeffect identification and cause-effect boundary determination. The causeeffect identification problem can be s...

Sequence Models and Ranking Methods for Discourse Parsing A dissertation presented to the Faculty of the Graduate School of Arts and Sciences of Brandeis University, Waltham, Massachusetts by Ben Wellner Many important aspects of natural language reside beyond the level of a single sentence or clause, at the level of the discourse, including: reference relations such anaphora, notions of topic/...

methamphetamine (ma) is a highly addictive psychostimulant drug with crucial impacts on individuals on various levels. exposure to methamphetamine-associated cues in laboratory can elicit measureable craving and autonomic reactivity in most individuals with methamphetamine dependence and the cue reactivity can model how craving would result in continued drug seeking behaviors and relapse in rea...