Методы структурно-ориентированного извлечения фрагментов веб-таблиц для вопросно-ответных систем: научно-аналитический обзор
(Стр. 107-130)
Подробнее об авторах
Али Диб Халед
аспирант
Московский государственный технический университет имени Н.Э. Баумана
г. Москва, Российская Федерация Гапанюк Юрий Евгеньевич кандидат технический наук, доцент; доцент; Московский государственный технический университет имени Н.Э. Баумана; г. Москва, Российская Федерация Афанасьев Геннадий Иванович кандидат технический наук, доцент; доцент; Московский государственный технический университет имени Н.Э. Баумана; г. Москва, Российская Федерация
Московский государственный технический университет имени Н.Э. Баумана
г. Москва, Российская Федерация Гапанюк Юрий Евгеньевич кандидат технический наук, доцент; доцент; Московский государственный технический университет имени Н.Э. Баумана; г. Москва, Российская Федерация Афанасьев Геннадий Иванович кандидат технический наук, доцент; доцент; Московский государственный технический университет имени Н.Э. Баумана; г. Москва, Российская Федерация
Нажимая на кнопку купить вы соглашаетесь с условиями договора оферты
Аннотация:
Веб-таблицы являются важным источником структурированных данных для вопросно-ответных систем, однако методы их извлечения существенно различаются по единице поиска, способу моделирования структуры и механизму сопоставления запроса с табличным представлением. Целью статьи является систематизация методологических направлений структурно-ориентированного извлечения фрагментов веб-таблиц и выявление ограничений, мотивирующих применение многовекторных и поздне-взаимодействующих схем. Исследование выполнено в формате научно-аналитического обзора. Поиск проводился в Scopus, OpenAlex, eLIBRARY/RSCI и с использованием анализа цитирований; из 767 выявленных записей после удаления дубликатов, скрининга и полнотекстовой оценки в итоговый синтез включены 42 исследования. В работе предложен единый формальный каркас для сопоставления методов извлечения, построена таксономия подходов, проанализированы гранулярность извлечения, типы векторного взаимодействия, механизмы агрегации релевантности, структурные сигналы и вычислительные ограничения. Показано, что доминируют плотные и структурно-ориентированные методы уровня целых таблиц, тогда как масштабируемое извлечение строк, ячеек, подтаблиц и мультитабличных свидетельств остается недостаточно разработанным направлением. Сделан вывод о необходимости дальнейшей разработки многовекторных методов, сохраняющих локальную структуру таблиц при приемлемой вычислительной сложности.
Образец цитирования:
ОБРАЗЕЦ ЦИТИРОВАНИЯ: Али Диб Халед, Гапанюк Ю.Е., Афанасьев Г.И. Методы структурно-ориентированного извлечения фрагментов веб-таблиц для вопросно-ответных систем: научно-аналитический обзор // Computational Nanotechnology. 2026. Т. 13. № 2. С. 107-130. DOI: 10.33693/2313-223X-2026-13-2-107-130. EDN: YYPVDQ
Список литературы:
Agarwal R., Singhal H., Chen P.B. et al. REaR: Retrieve, expand and refine for effective multitable retrieval. arXiv preprint. 2025. arXiv:2511.00805.
Bodensohn J.-M., Binnig C. Rethinking table retrieval from data lakes. In: Proceedings of the 7th International Workshop on Exploiting Artificial Intelligence Techniques for Data Management (aiDM@SIGMOD 2024). 2024. Art. 2. Pp. 2:1–2:5. DOI: 10.1145/3663742.3663972.
Boutaleb A., Amann B., Angarita R., Naacke H. Exploring multi-table retrieval through iterative search. arXiv preprint. 2025. arXiv:2511.13418.
Chen N., Shou L., Gong M. et al. Bridge the gap between language models and tabular understanding. arXiv preprint. 2023. arXiv:2302.09302.
Chen P.B., Zhang Y., Roth D. Is table retrieval a solved problem? Exploring join-aware multi-table retrieval. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Vol. 1: Long Papers. 2024. Pp. 2687–2699. DOI: 10.18653/v1/2024.acl-long.148.
Chen S., Yubo Liu, Jie Wu, Mengshu Hou. Retrieval augmented via execution guidance in open-domain table QA. In: Proceedings of the 5th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI). 2022. Art. 2. Pp. 1–6. DOI: 10.1145/3579654.3579656.
Chen S.-A., Miculicich L., Eisenschlos J.M. et al. TableRAG: million-token table understanding with language models. In: Advances in Neural Information Processing Systems 37 (NeurIPS 2024). 2024. Pp. 74899–74921. DOI: 10.52202/079017-2382.
Chen Z., Zhang S., Davison B.D. WTR: a test collection for web table retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021. Pp. 2514–2520. DOI: 10.1145/3404835.3463260.
Dantart A., Kóvacs-Navarro M. Topo-RAG: Topology-aware retrieval for hybrid text-table documents. arXiv preprint. 2026. arXiv:2601.10215.
Dong H., Cheng Z., He X. et al. Table pre-training: a survey on model architectures, pre-training objectives, and downstream tasks. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. 2022. Pp. 5426–5435. DOI: 10.24963/ijcai.2022/761.
Guan C., Huang M., Zhang P. MFORT-QA: Multi-hop few-shot open rich table question answering. In: Proceedings of the 10th International Conference on Computing and Artificial Intelligence (ICCAI 2024). 2024. Pp. 434–442. DOI: 10.1145/3669754.3669822.
Jin N., Li D., Chen J. et al. Enhancing open-domain table question answering via syntax- and structure-aware dense retrieval. In: Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Vol. 2: Short Papers. 2023. Pp. 157–165.
Johnson J., Douze M., Jégou H. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data. 2021. Vol. 7. No. 3. Pp. 535–547. DOI: 10.1109/TBDATA.2019.2921572.
Karki B., Hu F., Haridas N. et al. Question answering via web extracted tables and pipelined models. arXiv preprint. 2019. arXiv:1903.07113.
Khattab O., Zaharia M. ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020. Pp. 39–48. DOI: 10.1145/3397271.3401075.
Khodabakhsh M., Bagheri E. Qualitative measures for ad hoc table retrieval. Information Sciences. 2022. Vol. 607. Pp. 1–26. DOI: 10.1016/j.ins.2022.05.080.
Kim K., Kim M., Lee H. et al. THoRR: Complex table retrieval and refinement for RAG. In: Proceedings of the Workshop Information Retrieval’s Role in RAG Systems (IR-RAG 2024). CEUR Workshop Proceedings, 2024. Vol. 3784. Pp. 50–55.
Kojima A. Sub-table rescorer for table question answering. In: Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024. Pp. 15422–15427.
Kopliku A., Pinel-Sauvagnat K., Boughanem M. Attribute retrieval from relational web tables. In: String Processing and Information Retrieval (SPIRE 2011). Berlin; Heidelberg: Springer, 2011. Lecture Notes in Computer Science. Vol. 7024. Pp. 117–128. DOI: 10.1007/978-3-642-24583-1_12.
Li D., Bi K., Guo J., Cheng X. Bridging queries and tables through entities in open-domain table retrieval. In: Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025). 2025. Pp. 1540–1550. DOI: 10.1145/3746252.3761002.
Li X., Xue T. HTR-GEN: A structure-aware framework for hierarchical table retrieval and generation. In: Proceedings of the 5th International Conference on Computer Systems (ICCS). 2025. DOI: 10.1109/ICCS67844.2025.11292378.
Liang H.-P., Chang C.-W., Fan Y.-C. Improving table retrieval with question generation from partial tables. In: Proceedings of the 4th Table Representation Learning Workshop. Vienna: Association for Computational Linguistics, 2025. Pp. 217–228. DOI: 10.18653/v1/2025.trl-1.19.
Liang X., Hu R., Liu Y., Zhu K. Open-domain question answering over tables with large language models. In: Advanced Intelligent Computing Technology and Applications. Singapore: Springer, 2024. Pp. 347–358. DOI: 10.1007/978-981-97-5615-5_28.
Limaye G., Sarawagi S., Chakrabarti S. Annotating and searching web tables using entities, types and relationships. In: Proceedings of the VLDB Endowment. 2010. Vol. 3. No. 1–2. Pp. 1338–1347. DOI: 10.14778/1920841.1921005.
Lin W., Blloshmi R., Byrne B. et al. LI-RAGE: Late interaction retrieval augmented generation with explicit signals for open-domain table question answering. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Vol. 2: Short Papers. 2023. Pp. 1557–1566. DOI: 10.18653/v1/2023.acl-short.133.
Luo F., Lan H., Luo H. et al. Decomposition-driven multi-table retrieval and reasoning for numerical question answering. arXiv preprint. 2026. arXiv:2603.07950.
Ni W. Lightweight table retrieval via vector matching for table question answering. In: Proceedings of the 22nd International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). 2025. DOI: 10.1109/ICCWAMTIP68645.2025.11352653.
Pan F., Canim M., Glass M. et al. CLTR: An end-to-end, transformer-based system for cell-level table retrieval and table question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations. 2021. Pp. 202–209. DOI: 10.18653/v1/2021.acl-demo.24.
Pan F., Canim M., Glass M. et al. T-RAG: End-to-end table question answering via retrieval-augmented generation. arXiv preprint. 2022. arXiv:2203.16714.
Pilaluisa J., Tomás D., Navarro-Colorado B., Mazón J.-N. Contextual word embeddings for tabular data search and integration. Neural Computing and Applications. 2023. Vol. 35. No. 13. Pp. 9319–9333. DOI: 10.1007/s00521-022-08066-8.
Shen Y., Ye L., Xie Z. A table semantic retrieval method using self-supervised pre-training querying transformer and text-attributed graphs. In: Advanced Intelligent Computing Technology and Applications (ICIC 2025). Singapore: Springer, 2025. Pp. 3–14. DOI: 10.1007/978-981-96-9986-5_1.
Shraga R., Roitman H., Feigenblat G., Canim M. Web table retrieval using multimodal deep learning. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020. Pp. 1399–1408. DOI: 10.1145/3397271.3401120.
Sun C., Cao B., Li T. et al. FGTR: fine-grained multi-table retrieval via hierarchical LLM reasoning. arXiv preprint. 2026. arXiv:2603.12702.
Tchuitcheu W.C., Lu T., Dooms A. Towards platonic representation for table reasoning: A foundation for permutation-invariant retrieval. arXiv preprint. 2026. arXiv:2604.12133.
Trabelsi M., Chen Z., Zhang S. et al. StruBERT: Structure-aware BERT for table search and matching. In: Proceedings of the ACM Web Conference 2022. 2022. 10 p. DOI: 10.1145/3485447.3511972.
Vaswani A., Shazeer N., Parmar N. et al. Attention is all you need. Advances in Neural Information Processing Systems. 2017. Vol. 30. Pp. 5998–6008. DOI: 10.48550/arXiv.1706.03762.
Wang H., Liu A., Wang J. et al. Context retrieval for web tables. In: Proceedings of the International Conference on The Theory of Information Retrieval (ICTIR 2015). 2015. Pp. 251–260. DOI: 10.1145/2808194.2809453.
Wang Z., Dong H., Jia R. et al. TUTA: Tree-based transformers for generally structured table pre-training. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021. Pp. 1780–1790. DOI: 10.1145/3447548.3467434.
Wang Z., Jiang Z., Nyberg E., Neubig G. Table retrieval may not necessitate table-specific model design. In: Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI). 2022. Pp. 36–46. DOI: 10.18653/v1/2022.suki-1.5.
Wu J., Yang L., Li D. et al. MMQA: Evaluating LLMs with multi-table multi-hop complex questions. In: Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025). 2025.
Yao X., Zhang Z., Hu X. et al. COTER: Conditional optimal transport meets table retrieval. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining (WSDM 2024). 2024. Pp. 911–919. DOI: 10.1145/3616855.3635796.
Yao Y., Lyu X. Multi-agent enhanced retrieval-augmented generation for open-domain table question answering. In: Proceedings of the 18th International Conference on Advanced Computer Theory and Engineering (ICACTE). 2025. Pp. 357–363. DOI: 10.1109/ICACTE66284.2025.11412132.
Zhang S., Balog K. Web table extraction, retrieval, and augmentation: A survey. ACM Transactions on Intelligent Systems and Technology. 2020. Vol. 11. No. 2. Art. 13. Pp. 1–35. DOI: 10.1145/3372117.
Zhang X., Wang D., Dou L. et al. MURRE: Multi-hop table retrieval with removal for open-domain text-to-SQL. In: Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025). 2025. Pp. 5789–5806.
Zhang Y., Chen P.B., Ives Z.G. Searching data lakes for nested and joined data. In: Proceedings of the VLDB Endowment. 2024. Vol. 17. No. 11. Pp. 3346–3359. DOI: 10.14778/3681954.3682005.
Bodensohn J.-M., Binnig C. Rethinking table retrieval from data lakes. In: Proceedings of the 7th International Workshop on Exploiting Artificial Intelligence Techniques for Data Management (aiDM@SIGMOD 2024). 2024. Art. 2. Pp. 2:1–2:5. DOI: 10.1145/3663742.3663972.
Boutaleb A., Amann B., Angarita R., Naacke H. Exploring multi-table retrieval through iterative search. arXiv preprint. 2025. arXiv:2511.13418.
Chen N., Shou L., Gong M. et al. Bridge the gap between language models and tabular understanding. arXiv preprint. 2023. arXiv:2302.09302.
Chen P.B., Zhang Y., Roth D. Is table retrieval a solved problem? Exploring join-aware multi-table retrieval. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Vol. 1: Long Papers. 2024. Pp. 2687–2699. DOI: 10.18653/v1/2024.acl-long.148.
Chen S., Yubo Liu, Jie Wu, Mengshu Hou. Retrieval augmented via execution guidance in open-domain table QA. In: Proceedings of the 5th International Conference on Algorithms, Computing and Artificial Intelligence (ACAI). 2022. Art. 2. Pp. 1–6. DOI: 10.1145/3579654.3579656.
Chen S.-A., Miculicich L., Eisenschlos J.M. et al. TableRAG: million-token table understanding with language models. In: Advances in Neural Information Processing Systems 37 (NeurIPS 2024). 2024. Pp. 74899–74921. DOI: 10.52202/079017-2382.
Chen Z., Zhang S., Davison B.D. WTR: a test collection for web table retrieval. In: Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. 2021. Pp. 2514–2520. DOI: 10.1145/3404835.3463260.
Dantart A., Kóvacs-Navarro M. Topo-RAG: Topology-aware retrieval for hybrid text-table documents. arXiv preprint. 2026. arXiv:2601.10215.
Dong H., Cheng Z., He X. et al. Table pre-training: a survey on model architectures, pre-training objectives, and downstream tasks. In: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. 2022. Pp. 5426–5435. DOI: 10.24963/ijcai.2022/761.
Guan C., Huang M., Zhang P. MFORT-QA: Multi-hop few-shot open rich table question answering. In: Proceedings of the 10th International Conference on Computing and Artificial Intelligence (ICCAI 2024). 2024. Pp. 434–442. DOI: 10.1145/3669754.3669822.
Jin N., Li D., Chen J. et al. Enhancing open-domain table question answering via syntax- and structure-aware dense retrieval. In: Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics. Vol. 2: Short Papers. 2023. Pp. 157–165.
Johnson J., Douze M., Jégou H. Billion-scale similarity search with GPUs. IEEE Transactions on Big Data. 2021. Vol. 7. No. 3. Pp. 535–547. DOI: 10.1109/TBDATA.2019.2921572.
Karki B., Hu F., Haridas N. et al. Question answering via web extracted tables and pipelined models. arXiv preprint. 2019. arXiv:1903.07113.
Khattab O., Zaharia M. ColBERT: efficient and effective passage search via contextualized late interaction over BERT. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020. Pp. 39–48. DOI: 10.1145/3397271.3401075.
Khodabakhsh M., Bagheri E. Qualitative measures for ad hoc table retrieval. Information Sciences. 2022. Vol. 607. Pp. 1–26. DOI: 10.1016/j.ins.2022.05.080.
Kim K., Kim M., Lee H. et al. THoRR: Complex table retrieval and refinement for RAG. In: Proceedings of the Workshop Information Retrieval’s Role in RAG Systems (IR-RAG 2024). CEUR Workshop Proceedings, 2024. Vol. 3784. Pp. 50–55.
Kojima A. Sub-table rescorer for table question answering. In: Proceedings of the Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024). 2024. Pp. 15422–15427.
Kopliku A., Pinel-Sauvagnat K., Boughanem M. Attribute retrieval from relational web tables. In: String Processing and Information Retrieval (SPIRE 2011). Berlin; Heidelberg: Springer, 2011. Lecture Notes in Computer Science. Vol. 7024. Pp. 117–128. DOI: 10.1007/978-3-642-24583-1_12.
Li D., Bi K., Guo J., Cheng X. Bridging queries and tables through entities in open-domain table retrieval. In: Proceedings of the 34th ACM International Conference on Information and Knowledge Management (CIKM 2025). 2025. Pp. 1540–1550. DOI: 10.1145/3746252.3761002.
Li X., Xue T. HTR-GEN: A structure-aware framework for hierarchical table retrieval and generation. In: Proceedings of the 5th International Conference on Computer Systems (ICCS). 2025. DOI: 10.1109/ICCS67844.2025.11292378.
Liang H.-P., Chang C.-W., Fan Y.-C. Improving table retrieval with question generation from partial tables. In: Proceedings of the 4th Table Representation Learning Workshop. Vienna: Association for Computational Linguistics, 2025. Pp. 217–228. DOI: 10.18653/v1/2025.trl-1.19.
Liang X., Hu R., Liu Y., Zhu K. Open-domain question answering over tables with large language models. In: Advanced Intelligent Computing Technology and Applications. Singapore: Springer, 2024. Pp. 347–358. DOI: 10.1007/978-981-97-5615-5_28.
Limaye G., Sarawagi S., Chakrabarti S. Annotating and searching web tables using entities, types and relationships. In: Proceedings of the VLDB Endowment. 2010. Vol. 3. No. 1–2. Pp. 1338–1347. DOI: 10.14778/1920841.1921005.
Lin W., Blloshmi R., Byrne B. et al. LI-RAGE: Late interaction retrieval augmented generation with explicit signals for open-domain table question answering. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Vol. 2: Short Papers. 2023. Pp. 1557–1566. DOI: 10.18653/v1/2023.acl-short.133.
Luo F., Lan H., Luo H. et al. Decomposition-driven multi-table retrieval and reasoning for numerical question answering. arXiv preprint. 2026. arXiv:2603.07950.
Ni W. Lightweight table retrieval via vector matching for table question answering. In: Proceedings of the 22nd International Computer Conference on Wavelet Active Media Technology and Information Processing (ICCWAMTIP). 2025. DOI: 10.1109/ICCWAMTIP68645.2025.11352653.
Pan F., Canim M., Glass M. et al. CLTR: An end-to-end, transformer-based system for cell-level table retrieval and table question answering. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations. 2021. Pp. 202–209. DOI: 10.18653/v1/2021.acl-demo.24.
Pan F., Canim M., Glass M. et al. T-RAG: End-to-end table question answering via retrieval-augmented generation. arXiv preprint. 2022. arXiv:2203.16714.
Pilaluisa J., Tomás D., Navarro-Colorado B., Mazón J.-N. Contextual word embeddings for tabular data search and integration. Neural Computing and Applications. 2023. Vol. 35. No. 13. Pp. 9319–9333. DOI: 10.1007/s00521-022-08066-8.
Shen Y., Ye L., Xie Z. A table semantic retrieval method using self-supervised pre-training querying transformer and text-attributed graphs. In: Advanced Intelligent Computing Technology and Applications (ICIC 2025). Singapore: Springer, 2025. Pp. 3–14. DOI: 10.1007/978-981-96-9986-5_1.
Shraga R., Roitman H., Feigenblat G., Canim M. Web table retrieval using multimodal deep learning. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. 2020. Pp. 1399–1408. DOI: 10.1145/3397271.3401120.
Sun C., Cao B., Li T. et al. FGTR: fine-grained multi-table retrieval via hierarchical LLM reasoning. arXiv preprint. 2026. arXiv:2603.12702.
Tchuitcheu W.C., Lu T., Dooms A. Towards platonic representation for table reasoning: A foundation for permutation-invariant retrieval. arXiv preprint. 2026. arXiv:2604.12133.
Trabelsi M., Chen Z., Zhang S. et al. StruBERT: Structure-aware BERT for table search and matching. In: Proceedings of the ACM Web Conference 2022. 2022. 10 p. DOI: 10.1145/3485447.3511972.
Vaswani A., Shazeer N., Parmar N. et al. Attention is all you need. Advances in Neural Information Processing Systems. 2017. Vol. 30. Pp. 5998–6008. DOI: 10.48550/arXiv.1706.03762.
Wang H., Liu A., Wang J. et al. Context retrieval for web tables. In: Proceedings of the International Conference on The Theory of Information Retrieval (ICTIR 2015). 2015. Pp. 251–260. DOI: 10.1145/2808194.2809453.
Wang Z., Dong H., Jia R. et al. TUTA: Tree-based transformers for generally structured table pre-training. In: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021. Pp. 1780–1790. DOI: 10.1145/3447548.3467434.
Wang Z., Jiang Z., Nyberg E., Neubig G. Table retrieval may not necessitate table-specific model design. In: Proceedings of the Workshop on Structured and Unstructured Knowledge Integration (SUKI). 2022. Pp. 36–46. DOI: 10.18653/v1/2022.suki-1.5.
Wu J., Yang L., Li D. et al. MMQA: Evaluating LLMs with multi-table multi-hop complex questions. In: Proceedings of the Thirteenth International Conference on Learning Representations (ICLR 2025). 2025.
Yao X., Zhang Z., Hu X. et al. COTER: Conditional optimal transport meets table retrieval. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining (WSDM 2024). 2024. Pp. 911–919. DOI: 10.1145/3616855.3635796.
Yao Y., Lyu X. Multi-agent enhanced retrieval-augmented generation for open-domain table question answering. In: Proceedings of the 18th International Conference on Advanced Computer Theory and Engineering (ICACTE). 2025. Pp. 357–363. DOI: 10.1109/ICACTE66284.2025.11412132.
Zhang S., Balog K. Web table extraction, retrieval, and augmentation: A survey. ACM Transactions on Intelligent Systems and Technology. 2020. Vol. 11. No. 2. Art. 13. Pp. 1–35. DOI: 10.1145/3372117.
Zhang X., Wang D., Dou L. et al. MURRE: Multi-hop table retrieval with removal for open-domain text-to-SQL. In: Proceedings of the 31st International Conference on Computational Linguistics (COLING 2025). 2025. Pp. 5789–5806.
Zhang Y., Chen P.B., Ives Z.G. Searching data lakes for nested and joined data. In: Proceedings of the VLDB Endowment. 2024. Vol. 17. No. 11. Pp. 3346–3359. DOI: 10.14778/3681954.3682005.
Ключевые слова:
веб-таблицы, вопросно-ответные системы, извлечение информации, структурированные фрагменты, многовекторное представление, позднее взаимодействие.
