paper-with-me

Papers

Learning to Explicitate Connectives with Seq2Seq Network for Implicit Discourse Relation Classification

2018-11-05 · WS 2019 5 · Wei Shi, Vera Demberg

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 relational arguments. Therefore, an effective encoding of the relational arguments is of crucial importance. We here propose a new model for implicit discourse relation classification, which consists of a classifier, and a sequence-to-sequence model which is trained to generate a representation of the discourse relational arguments by trying to predict the relational arguments including a suitable implicit connective. Training is possible because such implicit connectives have been annotated as part of the PDTB corpus. Along with a memory network, our model could generate more refined representations for the task. And on the now standard 11-way classification, our method outperforms previous state of the art systems on the PDTB benchmark on multiple settings including cross validation.

📄 PDF Abstract BibTeX arXiv:1811.01697

Code (0)

등록된 구현이 없습니다.

Tasks

ClassificationDiscourse ParsingGeneral ClassificationImplicit Discourse Relation ClassificationRelationRelation Classification

Similar Papers 제목 키워드 기반

Acquiring Annotated Data with Cross-lingual Explicitation for Implicit Discourse Relation Classification

2018-08-30 · WS 2019 6 · Wei Shi, Frances Yung, Vera Demberg

Implicit discourse relation classification is one of the most challenging and important tasks in discourse parsing, due to the lack of connective as strong linguistic cues. A principle bottleneck to further improvement i…

16kDiscourse ParsingGeneral ClassificationImplicit Discourse Relation Classification+4

Annotation-Inspired Implicit Discourse Relation Classification with Auxiliary Discourse Connective Generation

2023-06-10 · Wei Liu, Michael Strube

Implicit discourse relation classification is a challenging task due to the absence of discourse connectives. To overcome this issue, we design an end-to-end neural model to explicitly generate discourse connectives for …

Implicit Discourse Relation ClassificationRelationRelation Classification

Adversarial Connective-exploiting Networks for Implicit Discourse Relation Classification

2017-04-01 · ACL 2017 7 · Lianhui Qin, Zhisong Zhang, Hai Zhao, Zhiting Hu 외

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 …

ClassificationGeneral ClassificationImplicit Discourse Relation ClassificationRelation+2

Employing the Correspondence of Relations and Connectives to Identify Implicit Discourse Relations via Label Embeddings

2019-07-01 · ACL 2019 7 · Linh The Nguyen, Linh Van Ngo, Khoat Than, Thien Huu Nguyen

It has been shown that implicit connectives can be exploited to improve the performance of the models for implicit discourse relation recognition (IDRR). An important property of the implicit connectives is that they can…

Multi-Task LearningTransfer Learning

Adapting BERT to Implicit Discourse Relation Classification with a Focus on Discourse Connectives

2020-05-01 · LREC 2020 5 · Yudai Kishimoto, Yugo Murawaki, Sadao Kurohashi

BERT, a neural network-based language model pre-trained on large corpora, is a breakthrough in natural language processing, significantly outperforming previous state-of-the-art models in numerous tasks. However, there h…

General ClassificationImplicit Discourse Relation ClassificationLanguage ModelingLanguage Modelling+3