IMPLICIT DISCOURSE RELATION CLASSIFICATION WITH CONTEXTUALIZED WORD REPRESENTATIONA method includes: initializing a list of token embeddings, each of the token embeddings corresponding to a tokenized word from text in a corpus of text; generating a graph for a group of consecutive words s from the ...
0 订阅 Parsing a text into a set of discourse relations between two adjacent or non-adjacent discourse units in the absence of explicit connectives, such as 'but' or 'however', and classifying those relations. (Source: Adapted from https://www.cs.brandeis.edu/~clp/conll15st/intro.html) ...
Let us consider the following implicit discourse relation (comparison): (1) Our competitors say we overbid them, (but) who cares. Obviously, the words “competitors, overbid, cares” are more persuasive than the others for relation recognition. Intuitively, discourse relations should be ...
Discourse analysisLinguistically informed features are provably useful in classifying implicit discourse relations among adjacent text spans. However the state of the art methods in this area suffer from either sparse natively implicit relation corpus or counter-intuitive artificially implicit one, and ...
Implicit discourse relation classificationHierarchical deep semanticsMutual learning neural networkThis paper presents a mutual learning method using hierarchical deep semantics for the classification of implicit discourse relations in English. With the absence of explicit discourse markers, tradit...
Implicit discourse relation classification is of great challenge due to the lack of connectives as strong linguistic cues, which motivates the use of annotated implicit connectives to improve the recognition. We propose a feature imitation framework in which an implicit relation network is driven to ...
We present a new system using zero-shot transfer learning for implicit discourse relation classification, where the only resource used for the target language is unannotated parallel text. This system is evaluated on the discourse-annotated TED-MDB parallel corpus, where it obtains good results for ...
Scha, R., et al., “An Augmented Context Free Grammar for Discourse,” Proceedings of the 12th Conference on Computational Linguistics—vol. 2, Computational Linguistics, Aug. 22-27, 1988, pp. 573-577, Morristown, NJ, http://dx.doi.org/10.3115/991719.991756. International Search Report and...
Implicit discourse relation classification, identifying relationships between arguments without explicit linguistic cues, is a challenging task. Previous studies have shown that connectives are important for recognizing implicit discourse relations. Most previous works applied connective prediction as an auxiliary...
Implicit discourse relation classification with contextualized word representationA method includes: initializing a list of token embeddings, each of the token embeddings corresponding to a tokenized word from text in a corpus of text; generating a graph for a group of consecutive words s from the ...