Coherence Modeling Improves Implicit Discourse Relation Recognition
The research described in this paper examines how to learn linguistic knowledge associated with discourse relations from unlabeled corpora. We introduce an unsupervised learning method on text coherence that could produce numerical representations that improve implicit discourse relation recognition in a semi-supervised manner. We also empirically examine two variants of coherence modeling: order-oriented and topic-oriented negative sampling, showing that, of the two, topic-oriented negative sampling tends to be more effective.
Code (0)
등록된 구현이 없습니다.
Tasks
Implicit Discourse Relation ClassificationRelationTransfer LearningSimilar Papers 제목 키워드 기반
Joint Modeling of Entities and Discourse Relations for Coherence Assessment
In linguistics, coherence can be achieved by different means, such as by maintaining reference to the same set of entities across sentences and by establishing discourse relations between them. However, most existing wor…
Coherence EvaluationResource-Lean Modeling of Coherence in Commonsense Stories
We present a resource-lean neural recognizer for modeling coherence in commonsense stories. Our lightweight system is inspired by successful attempts to modeling discourse relations and stands out due to its simplicity a…
Cloze TestReading ComprehensionSemantic Role LabelingNeural Discourse Modeling of Conversations
Deep neural networks have shown recent promise in many language-related tasks such as the modeling of conversations. We extend RNN-based sequence to sequence models to capture the long range discourse across many turns o…
Discourse Coherence: Concurrent Explicit and Implicit Relations
Theories of discourse coherence posit relations between discourse segments as a key feature of coherent text. Our prior work suggests that multiple discourse relations can be simultaneously operative between two segments…
Discourse ParsingImplicit RelationsLearning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification
Implicit discourse relation classification is one of the most difficult steps in discourse parsing. The difficulty stems from the fact that the coherence relation must be inferred based on the content of the discourse re…
ClassificationDiscourse ParsingGeneral ClassificationImplicit Discourse Relation Classification+2