A deep sequential model for discourse parsing on multi-party dialogues

Z Shi, M Huang - Proceedings of the AAAI Conference on Artificial …, 2019 - aaai.org
Discourse structures are beneficial for various NLP tasks such as dialogue understanding,
question answering, sentiment analysis, and so on. This paper presents a deep sequential …

Transition-based neural RST parsing with implicit syntax features

N Yu, M Zhang, G Fu - … of the 27th International Conference on …, 2018 - aclanthology.org
Abstract Syntax has been a useful source of information for statistical RST discourse
parsing. Under the neural setting, a common approach integrates syntax by a recursive …

RST discourse parsing with second-stage EDU-level pre-training

N Yu, M Zhang, G Fu, M Zhang - … of the 60th Annual Meeting of …, 2022 - aclanthology.org
Pre-trained language models (PLMs) have shown great potentials in natural language
processing (NLP) including rhetorical structure theory (RST) discourse parsing. Current …

A unified linear-time framework for sentence-level discourse parsing

X Lin, S Joty, P Jwalapuram, MS Bari - arXiv preprint arXiv:1905.05682, 2019 - arxiv.org
We propose an efficient neural framework for sentence-level discourse analysis in
accordance with Rhetorical Structure Theory (RST). Our framework comprises a discourse …

Adversarial learning for discourse rhetorical structure parsing

L Zhang, F Kong, G Zhou - … of the 59th Annual Meeting of the …, 2021 - aclanthology.org
Text-level discourse rhetorical structure (DRS) parsing is known to be challenging due to the
notorious lack of training data. Although recent top-down DRS parsers can better leverage …

Appdia: A discourse-aware transformer-based style transfer model for offensive social media conversations

K Atwell, S Hassan, M Alikhani - arXiv preprint arXiv:2209.08207, 2022 - arxiv.org
Using style-transfer models to reduce offensiveness of social media comments can help
foster a more inclusive environment. However, there are no sizable datasets that contain …

Transformers go for the LOLs: Generating (humourous) titles from scientific abstracts end-to-end

Y Chen, S Eger - arXiv preprint arXiv:2212.10522, 2022 - arxiv.org
We consider the end-to-end abstract-to-title generation problem, exploring seven recent
transformer based models (including ChatGPT) fine-tuned on more than 30k abstract-title …

Top-down RST parsing utilizing granularity levels in documents

N Kobayashi, T Hirao, H Kamigaito… - Proceedings of the …, 2020 - ojs.aaai.org
Some downstream NLP tasks exploit discourse dependency trees converted from RST trees.
To obtain better discourse dependency trees, we need to improve the accuracy of RST trees …

DisCoDisCo at the DISRPT2021 shared task: A system for discourse segmentation, classification, and connective detection

L Gessler, S Behzad, YJ Liu, S Peng, Y Zhu… - arXiv preprint arXiv …, 2021 - arxiv.org
This paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit
Segmentation, Connective Detection, and Relation Classification. Our system, called …

A top-down neural architecture towards text-level parsing of discourse rhetorical structure

L Zhang, Y Xing, F Kong, P Li, G Zhou - arXiv preprint arXiv:2005.02680, 2020 - arxiv.org
Due to its great importance in deep natural language understanding and various down-
stream applications, text-level parsing of discourse rhetorical structure (DRS) has been …