{"url":"/task/question-similarity","name":"Question Similarity","slug":"question-similarity","description_markdown":"This is the problem of detecting duplicate questions in forums, which is an important step towards automating the process of answering new questions","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":62,"papers_with_code":17,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/question-similarity-on-q2q-arabic-benchmark","slug":"question-similarity-on-q2q-arabic-benchmark","dataset":"Q2Q Arabic Benchmark","dataset_url":null,"rows_in_archive":3,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"Ensemble multilingual BERT model","paper_title":"The Inception Team at NSURL-2019 Task 8: Semantic Question Similarity in Arabic","paper_url":"/paper/the-inception-team-at-nsurl-2019-task-8","paper_date":"2020-04-24","arxiv_id":"2004.11964","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/lcqmc","name":"LCQMC","full_name":"Large-scale Chinese Question Matching Corpus","num_papers_in_archive":6}],"subtasks":[{"url":"/task/medical-question-pair-similarity-computation","name":"Medical question pair similarity computation"}],"parent_tasks":[],"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":17,"of":17,"tagged_in_all":62,"items":[{"url":"/paper/deep-learning-models-for-multilingual-hate","title":"Deep Learning Models for Multilingual Hate Speech Detection","date":"2020-04-14","arxiv_id":"2004.06465","repositories_listed":3,"syntology":null},{"url":"/paper/a-question-entailment-approach-to-question","title":"A Question-Entailment Approach to Question Answering","date":"2019-01-23","arxiv_id":"1901.08079","repositories_listed":3,"syntology":null},{"url":"/paper/kcluster-an-llm-based-clustering-approach-to","title":"KCluster: An LLM-based Clustering Approach to Knowledge Component Discovery","date":"2025-05-09","arxiv_id":"2505.06469","repositories_listed":1,"syntology":null},{"url":"/paper/personalized-llm-for-generating-customized","title":"Personalized LLM for Generating Customized Responses to the Same Query from Different Users","date":"2024-12-16","arxiv_id":"2412.11736","repositories_listed":1,"syntology":null},{"url":"/paper/dagkt-difficulty-and-attempts-boosted-graph","title":"DAGKT: Difficulty and Attempts Boosted Graph-based Knowledge Tracing","date":"2022-10-18","arxiv_id":"2210.15470","repositories_listed":1,"syntology":null},{"url":"/paper/linguistic-knowledge-in-data-augmentation-for","title":"Linguistic Knowledge in Data Augmentation for Natural Language Processing: An Example on Chinese Question Matching","date":"2021-11-29","arxiv_id":"2111.14709","repositories_listed":1,"syntology":null},{"url":"/paper/new-students-on-sesame-street-what-order","title":"General Cross-Architecture Distillation of Pretrained Language Models into Matrix Embeddings","date":"2021-09-17","arxiv_id":"2109.08449","repositories_listed":1,"syntology":null},{"url":"/paper/multicqa-zero-shot-transfer-of-self","title":"MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale","date":"2020-10-02","arxiv_id":"2010.00980","repositories_listed":1,"syntology":null},{"url":"/paper/tha3aroon-at-nsurl-2019-task-8-semantic","title":"Tha3aroon at NSURL-2019 Task 8: Semantic Question Similarity in Arabic","date":"2019-12-28","arxiv_id":"1912.12514","repositories_listed":1,"syntology":null},{"url":"/paper/semeval-2017-task-3-community-question-1","title":"SemEval-2017 Task 3: Community Question Answering","date":"2019-12-02","arxiv_id":"1912.00730","repositories_listed":1,"syntology":null},{"url":"/paper/question-similarity-in-community-question","title":"Question Similarity in Community Question Answering: A Systematic Exploration of Preprocessing Methods and Models","date":"2019-09-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/faq-retrieval-using-query-question-similarity","title":"FAQ Retrieval using Query-Question Similarity and BERT-Based Query-Answer Relevance","date":"2019-05-08","arxiv_id":"1905.02851","repositories_listed":1,"syntology":null},{"url":"/paper/adversarial-domain-adaptation-for-duplicate","title":"Adversarial Domain Adaptation for Duplicate Question Detection","date":"2018-09-07","arxiv_id":"1809.02255","repositories_listed":1,"syntology":null},{"url":"/paper/injecting-relational-structural","title":"Injecting Relational Structural Representation in Neural Networks for Question Similarity","date":"2018-06-20","arxiv_id":"1806.08009","repositories_listed":1,"syntology":null},{"url":"/paper/learning-semantic-textual-similarity-from","title":"Learning Semantic Textual Similarity from Conversations","date":"2018-04-20","arxiv_id":"1804.07754","repositories_listed":1,"syntology":{"n":17,"n_ran":0,"n_unverified":17,"n_pointer_only":0}},{"url":"/paper/iit-uhh-at-semeval-2017-task-3-exploring","title":"IIT-UHH at SemEval-2017 Task 3: Exploring Multiple Features for Community Question Answering and Implicit Dialogue Identification","date":"2017-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/swissalps-at-semeval-2017-task-3-attention","title":"SwissAlps at SemEval-2017 Task 3: Attention-based Convolutional Neural Network for Community Question Answering","date":"2017-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}