CVAE-based Re-anchoring for Implicit Discourse Relation Classification

2021-11-01 · Findings (EMNLP) 2021 11 · Zujun Dou, Yu Hong, Yu Sun, Guodong Zhou

Training implicit discourse relation classifiers suffers from data sparsity. Variational AutoEncoder (VAE) appears to be the proper solution. It is because ideally VAE is capable of generating inexhaustible varying samples, and this facilitates selective data augmentation. However, our experiments show that coupling VAE with the RoBERTa-based classifier results in severe performance degradation. We ascribe the unusual phenomenon to erroneous sampling that would happen when VAE pursued variations. To overcome the problem, we develop a re-anchoring strategy, where Conditional VAE (CVAE) is used for estimating the risk of erroneous sampling, and meanwhile migrating the anchor to reduce the risk. The test results on PDTB v2.0 illustrate that, compared to the RoBERTa-based baseline, re-anchoring yields substantial improvements. Besides, we observe that re-anchoring can cooperate with other auxiliary strategies (transfer learning and interactive attention mechanism) to further improve the baseline, obtaining the F-scores of about 55%, 63%, 80% and 44% for the four main relation types (Comparison, Contingency, Expansion, Temporality) in the binary classification (Yes/No) scenario.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Binary Classification Classification Data AugmentationImplicit Discourse Relation ClassificationRelationRelation Classification Transfer Learning

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 re…

Classification Discourse Parsing General Classification Implicit Discourse Relation Classification+2

Implicit Discourse Relation Classification via Multi-Task Neural Networks

2016-03-09 · Yang Liu, Sujian Li, Xiaodong Zhang, Zhifang Sui

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse frame…

Classification General Classification Implicit Discourse Relation Classification Multi-Task Learning+2

Beyond The Wall Street Journal: Anchoring and Comparing Discourse Signals across Genres

2019-09-02 · WS 2019 6 · Yang Liu

Recent research on discourse relations has found that they are cued not only by discourse markers (DMs) but also by other textual signals and that signaling information is indicative of genres. While several corpora exis…

Let's be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction

2021-06-06 · Murathan Kurfali, Robert Östling

In implicit discourse relation classification, we want to predict the relation between adjacent sentences in the absence of any overt discourse connectives. This is challenging even for humans, leading to shortage of ann…

Classification Implicit Discourse Relation Classification Implicit Relations Language Modeling+4

Let’s be explicit about that: Distant supervision for implicit discourse relation classification via connective prediction

2021-08-01 · ACL (unimplicit) 2021 8 · Murathan Kurfali, Robert Östling