Chatgpt evaluation on sentence level relations: A focus on temporal, causal, and discourse relations

C Chan, J Cheng, W Wang, Y Jiang, T Fang… - arxiv preprint arxiv …, 2023 - arxiv.org
This paper aims to quantitatively evaluate the performance of ChatGPT, an interactive large
language model, on inter-sentential relations such as temporal relations, causal relations …

A survey of implicit discourse relation recognition

W **ang, B Wang - ACM Computing Surveys, 2023 - dl.acm.org
A discourse containing one or more sentences describes daily issues and events for people
to communicate their thoughts and opinions. As sentences are normally consist of multiple …

Connective prediction for implicit discourse relation recognition via knowledge distillation

H Wu, H Zhou, M Lan, Y Wu… - Proceedings of the 61st …, 2023 - aclanthology.org
Implicit discourse relation recognition (IDRR) remains a challenging task in discourse
analysis due to the absence of connectives. Most existing methods utilize one-hot labels as …

ConnPrompt: Connective-cloze prompt learning for implicit discourse relation recognition

W **ang, Z Wang, L Dai, B Wang - Proceedings of the 29th …, 2022 - aclanthology.org
Abstract Implicit Discourse Relation Recognition (IDRR) is to detect and classify relation
sense between two text segments without an explicit connective. Vanilla pre-train and fine …

A label dependence-aware sequence generation model for multi-level implicit discourse relation recognition

C Wu, L Cao, Y Ge, Y Liu, M Zhang, J Su - Proceedings of the AAAI …, 2022 - ojs.aaai.org
Implicit discourse relation recognition (IDRR) is a challenging but crucial task in discourse
analysis. Most existing methods train multiple models to predict multi-level labels …

Discourse-level representations can improve prediction of degree of anxiety

S Juhng, M Matero, V Varadarajan… - Proceedings of the …, 2023 - aclanthology.org
Anxiety disorders are the most common of mental illnesses, but relatively little is known
about how to detect them from language. The primary clinical manifestation of anxiety is …

Discoprompt: Path prediction prompt tuning for implicit discourse relation recognition

C Chan, X Liu, J Cheng, Z Li, Y Song, GY Wong… - arxiv preprint arxiv …, 2023 - arxiv.org
Implicit Discourse Relation Recognition (IDRR) is a sophisticated and challenging task to
recognize the discourse relations between the arguments with the absence of discourse …

ASER: Towards large-scale commonsense knowledge acquisition via higher-order selectional preference over eventualities

H Zhang, X Liu, H Pan, H Ke, J Ou, T Fang, Y Song - Artificial Intelligence, 2022 - Elsevier
Commonsense knowledge acquisition and reasoning have long been a core artificial
intelligence problem. However, in the past, there has been a lack of scalable methods to …

Facilitating contrastive learning of discourse relational senses by exploiting the hierarchy of sense relations

W Long, B Webber - arxiv preprint arxiv:2301.02724, 2023 - arxiv.org
Implicit discourse relation recognition is a challenging task that involves identifying the
sense or senses that hold between two adjacent spans of text, in the absence of an explicit …

Infusing hierarchical guidance into prompt tuning: A parameter-efficient framework for multi-level implicit discourse relation recognition

H Zhao, R He, M **ao, J Xu - arxiv preprint arxiv:2402.15080, 2024 - arxiv.org
Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical
discourse relations among arguments. Previous methods achieve the promotion through …