A PDTB-styled end-to-end discourse parser

Abstract

We have developed a full discourse parser in the Penn Discourse Treebank (PDTB) style. Our trained parser first identifies all discourse and non-discourse relations, locates and labels their arguments, and then classifies their relation types. When appropriate, the attribution spans to these relations are also determined. We present a comprehensive evaluation from both component-wise and error-cascading perspectives.

Recognizing Reputation Defence Strategies in Critical Political Exchanges

“…While Nguyen and Litman (2016)'s work focused on only the attack and support relations between argumentative components in a paragraph, nonetheless, we believe that discourse relations can be informative features for identifying reputation defence strategies. Here we use shallow discourse relations (Class level), including Comparison, Contingency, and Expansion between the question and answer pairs (extracted using End-to-End PDTB-Styled Discourse Parser (Lin et al, 2014)). 4 For example, consider the question and answer pair in Table 6, where the discourse relation (parts in bold) between the question and answer is Comparison and indicates the denial strategy.…”

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

“…Figure 1 shows the components and the relations among them. Different from the traditional approach (i.e., Lin et al (2014)), considering the interaction between argument labeler and explicit sense classifier, co-occurrence relation between explicit and non-explicit discourse relations in a text, our system does not employ a complete sequential pipeline framework.…”

“…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.…”

The DCU Discourse Parser: A Sense Classification Task

“…Production features are proposed in (Lin et al, 2014) and word-pair features are reported in (Lin et al, 2014;. Heuristic features, which is specific for explicit sense classification, are described in (Lin et al, 2014). We consider the embedding models which lead to two different types of intermediate representations.…”