English
Related papers

Related papers: Fine-Grained Evaluation for Implicit Discourse Rel…

200 papers

Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to recognize the discourse relations between the arguments with the absence of discourse connectives. The sense labels for each discourse relation follow…

Computation and Language · Computer Science 2023-05-09 Chunkit Chan , Xin Liu , Jiayang Cheng , Zihan Li , Yangqiu Song , Ginny Y. Wong , Simon See

While pre-trained language models (LMs) have brought great improvements in many NLP tasks, there is increasing attention to explore capabilities of LMs and interpret their predictions. However, existing works usually focus only on a certain…

Computation and Language · Computer Science 2022-07-29 Yaozong Shen , Lijie Wang , Ying Chen , Xinyan Xiao , Jing Liu , Hua Wu

We consider an unanswered question in the discourse processing community: why do relation classifiers trained on explicit examples (with connectives removed) perform poorly in real implicit scenarios? Prior work claimed this is due to…

Computation and Language · Computer Science 2024-04-02 Wei Liu , Stephen Wan , Michael Strube

Hate speech detection is a crucial area of research in natural language processing, essential for ensuring online community safety. However, detecting implicit hate speech, where harmful intent is conveyed in subtle or indirect ways,…

Computation and Language · Computer Science 2025-04-17 Yumin Kim , Hwanhee Lee

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Computation and Language · Computer Science 2023-10-10 Chung-Ming Chien , Mingjiamei Zhang , Ju-Chieh Chou , Karen Livescu

Implicit discourse relation recognition (IDRR) -- the task of identifying the implicit coherence relation between two text spans -- requires deep semantic understanding. Recent studies have shown that zero- or few-shot approaches…

Computation and Language · Computer Science 2025-03-27 Frances Yung , Varsha Suresh , Zaynab Reza , Mansoor Ahmad , Vera Demberg

Argument mining tasks require an informed range of low to high complexity linguistic phenomena and commonsense knowledge. Previous work has shown that pre-trained language models are highly effective at encoding syntactic and semantic…

Computation and Language · Computer Science 2022-10-25 João Rodrigues , Ruben Branco , António Branco

Recent years have seen rapid development in Information Extraction, as well as its subtask, Relation Extraction. Relation Extraction is able to detect semantic relations between entities in sentences. Currently, many efficient approaches…

Computation and Language · Computer Science 2024-03-19 Zhuang Li

Discourse analysis is an important task because it models intrinsic semantic structures between sentences in a document. Discourse markers are natural representations of discourse in our daily language. One challenge is that the markers as…

Computation and Language · Computer Science 2023-06-21 Dongyu Ru , Lin Qiu , Xipeng Qiu , Yue Zhang , Zheng Zhang

While the general task of textual sentiment classification has been widely studied, much less research looks specifically at sentiment between a specified source and target. To tackle this problem, we experimented with a state-of-the-art…

Computation and Language · Computer Science 2019-08-20 Ruiqi Zhong , Steven Shao , Kathleen McKeown

Existing discourse corpora are annotated based on different frameworks, which show significant dissimilarities in definitions of arguments and relations and structural constraints. Despite surface differences, these frameworks share basic…

Computation and Language · Computer Science 2024-04-09 Yingxue Fu

With a growing number of BERTology work analyzing different components of pre-trained language models, we extend this line of research through an in-depth analysis of discourse information in pre-trained and fine-tuned language models. We…

Computation and Language · Computer Science 2022-04-12 Patrick Huber , Giuseppe Carenini

In English semantic similarity tasks, classic word embedding-based approaches explicitly model pairwise "interactions" between the word representations of a sentence pair. Transformer-based pretrained language models disregard this notion,…

Computation and Language · Computer Science 2019-11-11 Yinan Zhang , Raphael Tang , Jimmy Lin

Discourse-annotated corpora are an important resource for the community, but they are often annotated according to different frameworks. This makes comparison of the annotations difficult, thereby also preventing researchers from searching…

Computation and Language · Computer Science 2018-03-16 Vera Demberg , Fatemeh Torabi Asr , Merel Scholman

Inferring implicit discourse relations in natural language text is the most difficult subtask in discourse parsing. Surface features achieve good performance, but they are not readily applicable to other languages without semantic lexicons.…

Computation and Language · Computer Science 2016-06-08 Attapol T. Rutherford , Vera Demberg , Nianwen Xue

Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…

Computation and Language · Computer Science 2022-09-12 Asahi Ushio , Jose Camacho-Collados , Steven Schockaert

In recent years, more research has been devoted to studying the subtask of the complete shallow discourse parsing, such as indentifying discourse connective and arguments of connective. There is a need to design a full discourse parser to…

Computation and Language · Computer Science 2017-11-01 Jingjing Xu

Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract. Previous work has used models with large numbers of features, evaluated on very small datasets. We propose to train models for…

Computation and Language · Computer Science 2018-04-16 Pengxiang Cheng , Katrin Erk

This paper introduces the first multi-lingual and multi-label classification model for implicit discourse relation recognition (IDRR). Our model, HArch, is evaluated on the recently released DiscoGeM 2.0 corpus and leverages hierarchical…

Computation and Language · Computer Science 2025-08-29 Nelson Filipe Costa , Leila Kosseim

Distantly supervised relation extraction is widely used to extract relational facts from text, but suffers from noisy labels. Current relation extraction methods try to alleviate the noise by multi-instance learning and by providing…

Computation and Language · Computer Science 2019-06-21 Christoph Alt , Marc Hübner , Leonhard Hennig