Browse State-of-the-Art › Discourse Parsing
Discourse Parsing
57 papers with code · 4 benchmarks · 10 datasets archive 2025-07-28
Benchmarks archive 2025-07-28
4 leaderboard tables shown for this task, 4 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
| Dataset | Best model (first row in archive order) | Paper | Code | Syntology | Compare |
|---|---|---|---|---|---|
| RST-DT (40 rows) | Bottom-up Llama 2 (70B) | Can we obtain significant success in RST discourse parsing by... | code | Syntology ran 0 of 2 samples · 2 unverified | Compare |
| Instructional-DT (Instr-DT) (12 rows) | Bottom-up (DeBERTa) | A Simple and Strong Baseline for End-to-End Neural RST-style... | code | — | Compare |
| Molweni (7 rows) | DP | Multi-tasking Dialogue Comprehension with Discourse Parsing | code | — | Compare |
| STAC (7 rows) | Structured | Structured Dialogue Discourse Parsing | code | — | Compare |
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
10 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
3 subtasks in the archive's task tree.
Most implemented papers archive 2025-07-28
30 shown of 57 papers with code (189 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.
-
21 Mar 2022 4 repositories listed Syntology ran 2 of 5 samples · 3 unverifiedOur results not only motivate our proposal and help us to understand its limitations, but also provide insight on the properties of discourse models and datasets which improve performance in domain adaptation.
-
10 May 2015 4 repositories listedIn recent years, There has been a variety of research on discourse parsing, particularly RST discourse parsing.
-
22 Jun 2021 2 repositories listedOn DeSSE, which has a more even balance of complex sentence types, our model achieves higher accuracy on the number of atomic sentences than an encoder-decoder baseline.
-
14 May 2019 2 repositories listedWe propose an efficient neural framework for sentence-level discourse analysis in accordance with Rhetorical Structure Theory (RST).
-
10 Jun 2025 1 repository listedDiscourse parsing is an important task useful for NLU applications such as summarization, machine comprehension, and emotion recognition.
-
1 Nov 2024 1 repository listedWork on shallow discourse parsing in English has focused on the Wall Street Journal corpus, the only large-scale dataset for the language in the PDTB framework.
-
23 Sep 2024 1 repository listedDiscourse parsing is a crucial task in natural language processing that aims to reveal the higher-level relations in a text.
-
30 May 2024 1 repository listedThe interaction between these two structures has not been considered for joint modeling and mutual learning.
-
8 Mar 2024 1 repository listed Syntology ran 0 of 2 samples · 2 unverified · 2 pointer-only (licence)Recently, decoder-only pre-trained large language models (LLMs), with several tens of billion parameters, have significantly impacted a wide range of natural language processing (NLP) tasks.
-
1 Nov 2023 1 repository listedEssentially, our method seamlessly injects knowledge relevant to discourse relation into pre-trained language models through prompt-based connective prediction.
-
23 Oct 2023 1 repository listedQuestions Under Discussion (QUD) is a versatile linguistic framework in which discourse progresses as continuously asking questions and answering them.
-
10 Sep 2023 1 repository listedDespite recent advances in Natural Language Processing (NLP), hierarchical discourse parsing in the framework of Rhetorical Structure Theory remains challenging, and our understanding of the reasons for this are as yet…
-
26 Jun 2023 1 repository listedIn addition, unlike in previous work, we do not rely on hand-crafted features; this improves the model's robustness.
-
3 Jun 2023 1 repository listedWe evaluate state-of-the-art NLP systems on GENTLE and find severe degradation for at least some genres in their performance on all tasks, which indicates GENTLE's utility as an evaluation dataset for NLP systems.
-
24 May 2023 1 repository listedTopic segmentation and outline generation strive to divide a document into coherent topic sections and generate corresponding subheadings, unveiling the discourse topic structure of a document.
-
15 May 2023 1 repository listedIn this paper, we aim to systematically inspect ChatGPT's performance in two discourse analysis tasks: topic segmentation and discourse parsing, focusing on its deep semantic understanding of linear and hierarchical…
-
13 Feb 2023 1 repository listedTo our knowledge, this study is the first to fully evaluate cross-corpus RST parsing generalizability on complete trees, examine between-genre degradation within an RST corpus, and investigate the impact of genre…
-
19 Oct 2022 1 repository listedA lack of large-scale human-annotated data has hampered the hierarchical discourse parsing of Chinese.
-
15 Oct 2022 1 repository listedTo promote and further develop RST-style discourse parsing models, we need a strong baseline that can be regarded as a reference for reporting reliable experimental results.
-
1 Oct 2022 1 repository listedConversational discourse parsing aims to construct an implicit utterance dependency tree to reflect the turn-taking in a multi-party conversation.
-
1 Oct 2022 1 repository listedIt is believed that speaker interactions are helpful for this task.
-
1 May 2022 1 repository listedPre-trained language models (PLMs) have shown great potentials in natural language processing (NLP) including rhetorical structure theory (RST) discourse parsing.
-
1 Dec 2021 1 repository listedOur framework is unsupervised and domain-independent.
-
1 Nov 2021 1 repository listedThis paper demonstrates discopy, a novel framework that makes it easy to design components for end-to-end shallow discourse parsing.
-
9 Oct 2021 1 repository listed Syntology ran 1 of 1 samples · 0 unverified · 1 pointer-only (licence)While previous work significantly improves the performance of RST discourse parsing, they are not readily applicable to practical use cases: (1) EDU segmentation is not integrated into most existing tree parsing…
-
9 Oct 2021 1 repository listedWhile multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be…
-
7 Oct 2021 1 repository listedMulti-party dialogue machine reading comprehension (MRC) raises an even more challenging understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC.
-
20 Sep 2021 1 repository listedThis paper describes our submission to the DISRPT2021 Shared Task on Discourse Unit Segmentation, Connective Detection, and Relation Classification.
-
1 Aug 2021 1 repository listedConversational discourse structures aim to describe how a dialogue is organised, thus they are helpful for dialogue understanding and response generation.
-
25 Jun 2021 1 repository listedOver the past years, interest in discourse analysis and discourse parsing has steadily grown, and many discourse-annotated corpora and, as a result, discourse parsers have been built.
Syntology lines on 3 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections