Temporal Structure of Discourse (original) (raw)

Defining discourse formulae: computational approach

In this paper, we address the problem of automatic extraction of discourse formulae. By discourse formulae (DF) we mean a special type of constructions at the discourse level, which have a fixed form and serve as a typical response in the dialogue. Unlike traditional constructions [4, 5, 6], they do not contain variables within the sequence; their slots can be found in the left-hand or right-hand statements of the speech act. We have developed the system that extracts DF from drama texts. We have compared token-based and clause- based approaches and found the latter performing better. The clause-based model involves a uniform weight vote of four classifiers and currently shows the precision of 0.30 and the recall of 0.73 (F1-score 0.42).The created module was used to extract a list of DF from 420 drama texts of XIX-XXI centuries [1, 7]. The final list contains 3000 DF, 1800 of which are unique. Further development of the project includes enhancing the module by extracting left conte...

A Linguistically-based Approach to Discourse Relations Recognition

Proceedings of the 4th International Workshop on Natural Language Processing and Cognitive Science, 2007

We present an unsupervised linguistically-based approach to discourse relations recognition, which uses publicly available resources like manually annotated corpora (Discourse Graphbank, Penn Discourse Treebank, RST-DT), as well as empirically derived data from "causally" annotated lexica like LCS, to produce a rule-based algorithm. In our approach we use the subdivision of Discourse Relations into four subsets-CONTRAST, CAUSE, CONDITION , ELABORATION, proposed by [7] in their paper, where they report results obtained with a machine-learning approach from a similar experiment, against which we compare our results. Our approach is fully symbolic and is partially derived from the system called GETARUNS, for text understanding, adapted to a specific task: recognition of Causality Relations in free text. We show that in order to achieve better accuracy, both in the general task and in the specific one, semantic information needs to be used besides syntactic structural information. Our approach outperforms results reported in previous papers [9].

The optimization of discourse anaphora

Linguistics and Philosophy, 2004

In this paper the Centering model of anaphora resolution and discourse coherence Weinstein, 1983, 1995) is reformulated in terms of Optimality Theory (ot) . One version of the reformulated model is proven to be descriptively equivalent to an earlier algorithmic statement of Centering due to . However, the new model is stated declaratively, and makes clearer the status of the various constraints used in the theory. In the second part of the paper, the model is extended, demonstrating the advantages of the ot reformulation, and capturing formally ideas originally described by Grosz, Joshi and Weinstein. Three new applications of the extended ot Centering model are described: generation of linguistic forms from meanings, the evaluation and optimization of extended texts, and the interpretation of accented pronouns.

Easily Identifiable Discourse Relations

We present a corpus study of local dis- course relations based on the Penn Dis- course Tree Bank, a large manually anno- tated corpus of explicitly or implicitly re- alized relations. We show that while there is a large degree of ambiguity in temporal explicit discourse connectives, overall con- nectives are mostly unambiguous and al- low high-accuracy prediction of discourse relation type. We achieve 93.09% accu- racy in classifying the explicit relations and 74.74% accuracy overall. In addition, we show that some pairs of relations oc- cur together in text more often than ex- pected by chance. This finding suggests that global sequence classification of the relations in text can lead to better results, especially for implicit relations.

Contextual Filtering of Rhetorical Relations in Discourse Structuring

2008

The goal of this workshop series is to provide a forum for presenting recent research on constraints in discourse. The target areas include the recognition of discourse structure as well as the interpretation and generation of discourse in a broad variety of domains. The workshop is open to talks that further our theoretical understanding of the role of constraints in discourse, as well as empirical studies that shed light on their empirical validity. The workshop is explicitly intended for discussion and comparison of theoretical accounts that lay the ground for applications. Berry Claus: Comprehending descriptions of non-factual desired situations: Discourse referents and motor actions 3 Laurence Danlos: D-STAG: Parsing discourse with Synchronous TAG and SDRT background 5 Julia Hirschberg: A question of questions: Prosodic cues to question form and function 7 Paul Piwek: Constraints in natural language generation 9 Regular Papers Maria Averintseva-Klisch, Sebastian Buecking: What&...

How to infer temporal relations in discourse?

2007

This paper is devoted to the following question: how can readers and listeners infer temporal relations in discourse? This question presupposes that one of the basic inferential task in utterance and discourse interpretation consists in inferring time direction, that is, in determining the time of the event relative to the thread of discourse. In this paper, I reduce time direction to two temporal relations: forward inference (FI) and backward inference (BI). I show that the computation of directional inference is neither the result of principles of discourse, nor the consequence of discourse type, but the interaction of information coming from different sources, that is, contextual information and linguistic information. Moreover, I distinguish within linguistic information between conceptual and procedural information. A general pragmatic device is proposed, whose goal is to balance the different types of information during the computation of directional inferences. The purpose of this device is to explain why some sequences of discourse are more optimal than other, with no requirement of any principles of discourse analysis. The main issue of the paper is to argue for a pragmatic approach to discourse phenomena which requires no specific device, but uses the standard cognitive pragmatic framework, introduced by Relevance Theory.

Discourse Deixis: Reference to Discourse Segments

1988

Computational approaches to discourse understanding have a two-part goal: (1) to identify those aspects of discourse understanding that require process-based accounts, andS(2) to characterize the processes and data structures they involve. To date, in the area of reference, process-hased ac.omnts have been developed for subsequent reference via anaphoric pronouns and reference via definite descriptors. In this paper, I propose and argue for a process-based account of subsequent reference via deiedc expressions. A significant feature of this account is that it attributes distinct mental reality to units of text often called discourse segments, a reality that is distinct from that of the entities deem therein.

Contextual Filtering of Rhetorical Relations for Discourse Structuring in Dialogue

In this paper we propose an alternative to the Segmented Discourse Representation Theory (SDRT) mechanism for dealing with ambiguous rhetorical connections between utterances. Thus, starting from the observation that the SDRT mechanism for ordering discourse structures (the Maximize Discourse Coherence - MDC principle) relies on a fragile scalar interpretation of rhetorical relations in terms of their quality, we propose a reduction of the discourse structures to abstract attribute grammars (AAG) that will allow us to check the constraints they impose on the paths to the utterances, in the discourse structure. Thus, the non-unifiability of the restriction sets determined by the AAGs for each particular utterance represent a criterion for ruling out the rhetorical relations that contributed the AAGs with non- unifiable restriction sets. This "contextual filtering" approach is first presented, theoretically grounded and discussed with respect to several potential weak points...