Deep Enhanced Representation for Implicit Discourse Relation Recognition

Abstract

Implicit discourse relation recognition is a challenging task as the relation prediction without explicit connectives in discourse parsing needs understanding of text spans and cannot be easily derived from surface features from the input sentence pairs. Thus, properly representing the text is very crucial to this task. In this paper, we propose a model augmented with different grained text representations, including character, subword, word, sentence, and sentence pair levels. The proposed deeper model is evaluated on the benchmark treebank and achieves state-of-the-art accuracy with greater than 48% in 11-way and $F_1$ score greater than 50% in 4-way classifications for the first time according to our best knowledge.

arXiv comment13(10) pages, accepted by COLING 2018

References in corpus (7)

• A Structured Self-attentive Sentence Embedding
• Training Very Deep Networks
• Language Modeling with Gated Convolutional Networks
• Character-Aware Neural Language Models
• A large annotated corpus for learning natural language inference
• Neural Word Segmentation Learning for Chinese
• Scaling Recurrent Neural Network Language Models

Cited by in corpus (9)

• Modeling Multi-turn Conversation with Deep Utterance Aggregation
• Explicit Contextual Semantics for Text Comprehension
• Subword-augmented Embedding for Cloze Reading Comprehension
• A Full End-to-End Semantic Role Labeler, Syntax-agnostic Over Syntax-aware?
• Consistency and Coherency Enhanced Story Generation
• Dialogue Graph Modeling for Conversational Machine Reading
• Extending Implicit Discourse Relation Recognition to the PDTB-3
• Effective Character-augmented Word Embedding for Machine Reading Comprehension
• Chinese Pinyin Aided IME, Input What You Have Not Keystroked Yet