{"url":"/task/coherence-evaluation","name":"Coherence Evaluation","slug":"coherence-evaluation","description_markdown":"Evaluating the overall coherence of text as measured by its readability and flow through ideas.","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":28,"papers_with_code":15,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-accuracy","slug":"coherence-evaluation-on-gcdc-rst-accuracy","dataset":"GCDC + RST - Accuracy","dataset_url":"/dataset/gcdc","rows_in_archive":4,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"MTL with Transformer","paper_title":"Transformer Models for Text Coherence Assessment","paper_url":"/paper/transformer-models-for-text-coherence","paper_date":"2021-09-05","arxiv_id":"2109.02176","code_links":[{"title":"LiamMaclean216/Pytorch-Transfomer","url":"https://github.com/LiamMaclean216/Pytorch-Transfomer"},{"title":"tushar117/Transformer-Models-for-Text-Coherence-Assessment","url":"https://github.com/tushar117/Transformer-Models-for-Text-Coherence-Assessment"}],"syntology":null}},{"leaderboard":"/sota/coherence-evaluation-on-gcdc-rst-f1","slug":"coherence-evaluation-on-gcdc-rst-f1","dataset":"GCDC + RST - F1","dataset_url":"/dataset/gcdc","rows_in_archive":3,"metrics":["Average F1"],"first_row_in_archive_order":{"model":"RST-Ensemble","paper_title":"Neural RST-based Evaluation of Discourse Coherence","paper_url":"/paper/neural-rst-based-evaluation-of-discourse","paper_date":"2020-09-30","arxiv_id":"2009.14463","code_links":[{"title":"grig-guz/coherence-rst","url":"https://github.com/grig-guz/coherence-rst"}],"syntology":null}}],"datasets":[{"url":"/dataset/gcdc","name":"GCDC","full_name":"Grammarly Corpus of Discourse Coherence","num_papers_in_archive":13}],"subtasks":[],"parent_tasks":[{"url":"/task/text-classification","name":"Text Classification"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":15,"of":15,"tagged_in_all":28,"items":[{"url":"/paper/transformer-models-for-text-coherence","title":"Transformer Models for Text Coherence Assessment","date":"2021-09-05","arxiv_id":"2109.02176","repositories_listed":2,"syntology":null},{"url":"/paper/ecoh-turn-level-coherence-evaluation-for","title":"ECoh: Turn-level Coherence Evaluation for Multilingual Dialogues","date":"2024-07-16","arxiv_id":"2407.11660","repositories_listed":1,"syntology":null},{"url":"/paper/couda-coherence-evaluation-via-unified-data","title":"CoUDA: Coherence Evaluation via Unified Data Augmentation","date":"2024-03-31","arxiv_id":"2404.00681","repositories_listed":1,"syntology":null},{"url":"/paper/unlocking-structure-measuring-introducing-pdd","title":"Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence","date":"2024-02-15","arxiv_id":"2402.10175","repositories_listed":1,"syntology":null},{"url":"/paper/the-problem-of-coherence-in-natural-language","title":"The Problem of Coherence in Natural Language Explanations of Recommendations","date":"2023-12-18","arxiv_id":"2312.11356","repositories_listed":1,"syntology":null},{"url":"/paper/open-domain-text-evaluation-via-meta","title":"Open-Domain Text Evaluation via Contrastive Distribution Methods","date":"2023-06-20","arxiv_id":"2306.11879","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/transform-contrast-and-tell-coherent-entity","title":"Transform, Contrast and Tell: Coherent Entity-Aware Multi-Image Captioning","date":"2023-02-04","arxiv_id":"2302.02124","repositories_listed":1,"syntology":null},{"url":"/paper/gispy-a-tool-for-measuring-gist-inference","title":"GisPy: A Tool for Measuring Gist Inference Score in Text","date":"2022-05-25","arxiv_id":"2205.12484","repositories_listed":1,"syntology":null},{"url":"/paper/snac-coherence-error-detection-for-narrative","title":"SNaC: Coherence Error Detection for Narrative Summarization","date":"2022-05-19","arxiv_id":"2205.09641","repositories_listed":1,"syntology":null},{"url":"/paper/deam-dialogue-coherence-evaluation-using-amr","title":"DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations","date":"2022-03-18","arxiv_id":"2203.09711","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/a-neural-graph-based-local-coherence-model","title":"A Neural Graph-based Local Coherence Model","date":"2021-11-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/towards-quantifiable-dialogue-coherence","title":"Towards Quantifiable Dialogue Coherence Evaluation","date":"2021-06-01","arxiv_id":"2106.00507","repositories_listed":1,"syntology":null},{"url":"/paper/is-incoherence-surprising-targeted-evaluation","title":"Is Incoherence Surprising? Targeted Evaluation of Coherence Prediction from Language Models","date":"2021-05-07","arxiv_id":"2105.03495","repositories_listed":1,"syntology":null},{"url":"/paper/neural-rst-based-evaluation-of-discourse","title":"Neural RST-based Evaluation of Discourse Coherence","date":"2020-09-30","arxiv_id":"2009.14463","repositories_listed":1,"syntology":null},{"url":"/paper/discourse-coherence-in-the-wild-a-dataset","title":"Discourse Coherence in the Wild: A Dataset, Evaluation and Methods","date":"2018-05-14","arxiv_id":"1805.04993","repositories_listed":1,"syntology":null}],"syntology_records":2,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}