Using syntax to disambiguate explicit discourse connectives in text

Abstract

Discourse connectives are words or phrases such as once, since, and on the contrary that explicitly signal the presence of a discourse relation. There are two types of ambiguity that need to be resolved during discourse processing. First, a word can be ambiguous between discourse or non-discourse usage. For example, once can be either a temporal discourse connective or a simply a word meaning "formerly". Secondly, some connectives are ambiguous in terms of the relation they mark. For example since can serve as either a temporal or causal connective. We demonstrate that syntactic features improve performance in both disambiguation tasks. We report state-ofthe-art results for identifying discourse vs. non-discourse usage and human-level performance on sense disambiguation.

Shallow Discourse Parsing with Syntactic and (a Few) Semantic Features

“…Explicit connective classification is usually done beforehand. (Pitler and Nenkova, 2009) achieved an F-Score of 94.19% which was extended by (Lin et al, 2014) to get an F-score of 95.36%. Various approaches have been used for argument span labelling.…”

The SoNLP-DP System in the CoNLL-2015 shared Task

“…Then every connective candidate is Figure 1: Framework of our end-to-end shallow discourse parser checked whether it functions as a discourse connective. Pitler and Nenkova (2009) showed that syntactic features extracted from constituent parse trees are very useful in disambiguating discourse connectives. Followed their work, Lin et al (2014) found that a connective's context and part-ofspeech (POS) are also helpful.…”

“…Although the same connective may carry different semantics under different contexts, only a few connectives are ambiguous (Pitler and Nenkova, 2009). Following the work of Lin et al (2014), we introduce three features to train a sense classifier: the connective itself, its POS and the previous word of the connective.…”

“…Verbs: Following the work of Pitler et al (2009), we extract the pairs of verbs from the given adjacent sentence pair (i.e., Arg1 and Arg2). Besides that, the number of verb pairs which have the same highest VerbNet verb class (Kipper et al, 2006) is included as a feature.…”

“…As the largest discourse corpus, the Penn Discourse TreeBank (PDTB) corpus (Prasad et al, 2008) adds a layer of discourse annotations on the top of the Penn TreeBank (PTB) corpus (Marcus et al, 1993) and has been attracting more and more attention recently (Elwell and Baldridge, 2008;Pitler and Nenkova, 2009;Prasad et al, 2010;Ghosh et al, 2011;Kong et al, 2014;Lin et al, 2014). Different from another famous discourse corpus, the Rhetorical Structure Theory(RST) Treebank corpus (Carlson et al, 2001), the PDTB focuses on shallow discourse relations either lexically grounded in explicit discourse connectives or associated with sentential adjacency.…”