A Graph-based Approach to Implicit Discourse Relation Classification

old_uid12027
titleA Graph-based Approach to Implicit Discourse Relation Classification
start_date2013/01/25
schedule11h-12h30
onlineno
summaryCurrent approaches to recognizing discourse relations rely on a combination of shallow, surface-based features (e.g., bigrams, word pairs), and rather specialized hand-crafted features. As a way to avoid both the shallowness of word-based representations and the lack of coverage of specialized linguistic features, we use a graph-based representation of discourse segments, which allows for a more abstract (and hence generalizable) notion of syntactic (and partially of semantic) structure. Empirical evaluation on a hand-annotated corpus of German discourse relations shows that our graph- based approach not only provides a suitable representation for the linguistic factors that are needed in disambiguating discourse relations, but also improves results over a strong state-of-the-art baseline.
responsiblesCandito