State-of-the-art generalisation research in NLP: a taxonomy and review
The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …
DisCut and DiscReT: MELODI at DISRPT 2023
This paper presents the results obtained by the MELODI team for the three tasks proposed
within the DISRPT 2023 shared task on discourse: segmentation, connective identification …
within the DISRPT 2023 shared task on discourse: segmentation, connective identification …
Why can't discourse parsing generalize? A thorough investigation of the impact of data diversity
Recent advances in discourse parsing performance create the impression that, as in other
NLP tasks, performance for high-resource languages such as English is finally becoming …
NLP tasks, performance for high-resource languages such as English is finally becoming …
Rst discourse parsing as text-to-text generation
Previous studies have made great advances in RST discourse parsing through specific
neural frameworks or features, but they usually split the parsing process into two subtasks …
neural frameworks or features, but they usually split the parsing process into two subtasks …
Incorporating distributions of discourse structure for long document abstractive summarization
For text summarization, the role of discourse structure is pivotal in discerning the core
content of a text. Regrettably, prior studies on incorporating Rhetorical Structure Theory …
content of a text. Regrettably, prior studies on incorporating Rhetorical Structure Theory …
GCDT: A Chinese RST treebank for multigenre and multilingual discourse parsing
A lack of large-scale human-annotated data has hampered the hierarchical discourse
parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse …
parsing of Chinese. In this paper, we present GCDT, the largest hierarchical discourse …
[HTML][HTML] Generating EDU extracts for plan-guided summary re-ranking
Two-step approaches, in which summary candidates are generated-then-reranked to return
a single summary, can improve ROUGE scores over the standard single-step approach. Yet …
a single summary, can improve ROUGE scores over the standard single-step approach. Yet …
What's Hard in English RST Parsing? Predictive Models for Error Analysis
Despite recent advances in Natural Language Processing (NLP), hierarchical discourse
parsing in the framework of Rhetorical Structure Theory remains challenging, and our …
parsing in the framework of Rhetorical Structure Theory remains challenging, and our …
RST-LoRA: A Discourse-Aware Low-Rank Adaptation for Long Document Abstractive Summarization
For long document summarization, discourse structure is important to discern the key
content of the text and the differences in importance level between sentences. Unfortunately …
content of the text and the differences in importance level between sentences. Unfortunately …
End-to-end argument mining over varying rhetorical structures
E Chistova - arXiv preprint arXiv:2401.11218, 2024 - arxiv.org
Rhetorical Structure Theory implies no single discourse interpretation of a text, and the
limitations of RST parsers further exacerbate inconsistent parsing of similar structures …
limitations of RST parsers further exacerbate inconsistent parsing of similar structures …