Modelling the similarity of discourse connectives
نویسنده
چکیده
Discourse connectives enable discourse coherence relations to be studies empirically. This paper presents two experiments on the semantic similarity of discourse connectives. Subjects are found to agree significantly on the similarity of pairs of connectives, and their similarity judgements are related to the ability of the connectives to be used to paraphrase each other. Subjects’ similarity judgements are also found to correlate positively with the distributional similarity of the connectives.
منابع مشابه
Modelling the Substitutability of Discourse Connectives
Processing discourse connectives is important for tasks such as discourse parsing and generation. For these tasks, it is useful to know which connectives can signal the same coherence relations. This paper presents experiments into modelling the substitutability of discourse connectives. It shows that substitutability effects distributional similarity. A novel variancebased function for compari...
متن کاملThe automatic acquisition of knowledge about discourse connectives
This thesis considers the automatic acquisition of knowledge about discourse connectives. It focuses in particular on their semantic properties, and on the relationships that hold between them. There is a considerable body of theoretical and empirical work on discourse connectives. For example, Knott (1996) motivates a taxonomy of discourse connectives based on relationships between them, such ...
متن کاملMinimally Supervised Event Causality Identification
This paper develops a minimally supervised approach, based on focused distributional similarity methods and discourse connectives, for identifying of causality relations between events in context. While it has been shown that distributional similarity can help identifying causality, we observe that discourse connectives and the particular discourse relation they evoke in context provide additio...
متن کاملModelling the Interpretation of Discourse Connectives by Bayesian Pragmatics
We propose a framework to model human comprehension of discourse connectives. Following the Bayesian pragmatic paradigm, we advocate that discourse connectives are interpreted based on a simulation of the production process by the speaker, who, in turn, considers the ease of interpretation for the listener when choosing connectives. Evaluation against the sense annotation of the Penn Discourse ...
متن کاملHow Comparable are Parallel Corpora? Measuring the Distribution of General Vocabulary and Connectives
In this paper, we question the homogeneity of a large parallel corpus by measuring the similarity between various sub-parts. We compare results obtained using a general measure of lexical similarity based on χ and by counting the number of discourse connectives. We argue that discourse connectives provide a more sensitive measure, revealing differences that are not visible with the general meas...
متن کامل