1 code implementation • ACL 2022 • Nan Yu, Meishan Zhang, Guohong Fu, Min Zhang
Pre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current PLMs are obtained by sentence-level pre-training, which is different from the basic processing unit, i. e. element discourse unit (EDU). To this end, we propose a second-stage EDU-level pre-training approach in this work, which presents two novel tasks to learn effective EDU representations continually based on well pre-trained language models. Concretely, the two tasks are (1) next EDU prediction (NEP) and (2) discourse marker prediction (DMP). We take a state-of-the-art transition-based neural parser as baseline, and adopt it with a light bi-gram EDU modification to effectively explore the EDU-level pre-trained EDU representation. Experimental results on a benckmark dataset show that our method is highly effective, leading a 2. 1-point improvement in F1-score. All codes and pre-trained models will be released publicly to facilitate future studies.
1 code implementation • COLING 2022 • Nan Yu, Guohong Fu, Min Zhang
It is believed that speaker interactions are helpful for this task.
Ranked #2 on Discourse Parsing on STAC
no code implementations • Findings (EMNLP) 2021 • Yang Sun, Nan Yu, Guohong Fu
In this paper, we investigate the importance of discourse structures in handling informative contextual cues and speaker-specific features for ERMC.
Ranked #20 on Emotion Recognition in Conversation on EmoryNLP
no code implementations • 26 Oct 2022 • Dexin Kong, Nan Yu, Yun Yuan, Guohong Fu, Chen Gong
In this paper, we investigate the importance of discourse structures in handling utterance interactions and conversationspecific features for ECEC.
Ranked #5 on Causal Emotion Entailment on RECCON
1 code implementation • ACL 2021 • Yucheng Wang, Bowen Yu, Hongsong Zhu, Tingwen Liu, Nan Yu, Limin Sun
Named entity recognition (NER) remains challenging when entity mentions can be discontinuous.
1 code implementation • 2 Mar 2020 • Nicholas C. White, Sandra M. Troian, Jeffrey B. Jewell, Curt J. Cutler, Sheng-wey Chiow, Nan Yu
Here we present a numerical method based on finite differences for solution of the static CGG scalar field for a 2D axisymmetric Sun-Earth system and a 3D Cartesian Sun-Earth-Moon system.
Computational Physics
1 code implementation • COLING 2018 • Nan Yu, Meishan Zhang, Guohong Fu
Syntax has been a useful source of information for statistical RST discourse parsing.
Ranked #7 on Discourse Parsing on RST-DT
no code implementations • 25 Apr 2017 • Liner Yang, Meishan Zhang, Yang Liu, Nan Yu, Maosong Sun, Guohong Fu
While part-of-speech (POS) tagging and dependency parsing are observed to be closely related, existing work on joint modeling with manually crafted feature templates suffers from the feature sparsity and incompleteness problems.