微信服务号

微信订阅号

2025年8月11日 5:24 星期一
首页 > 过刊浏览>2024年第35卷第1期 >236-265. DOI:10.13328/j.cnki.jos.006913
PDF HTML阅读 XML下载 导出引用 引用提醒
常识问答研究综述
作者:
作者简介:

范怡帆(1996-),女,博士生,CCF学生会员,主要研究领域为常识问答;邹博伟(1984-),男,博士,研究员,主要研究领域为自然语言处理,文本生成,自动问答;徐庆婷(1994-),女,博士生,CCF学生会员,主要研究领域为信息抽取;李志峰(1998-),男,硕士生,CCF学生会员,主要研究领域为深度学习,自然语言处理,常识问答.;洪宇(1978-),男,博士,教授,博士生导师,CCF专业会员,主要研究领域为信息抽取,篇章关系理解,多模态机器翻译,智能问答

通讯作者:

洪宇,E-mail:tianxianer@gmail.com

基金项目:

国家重点研发计划 (2020YFB1313601); 国家自然科学基金 (62076174, 61836007)


Survey on Commonsense Question Answering
Author:
  • 摘要
    • | |
  • 访问统计
    • |
  • 参考文献 [92]
    • |
  • 相似文献 [20]
    • | | |
  • 文章评论
    摘要:

    常识问答是一项重要的自然语言理解任务, 旨在利用常识知识对自然语言问句进行自动求解, 以得到准确答案. 常识问答在虚拟助手或社交聊天机器人等领域有着广泛的应用前景, 且其蕴涵了知识挖掘与表示、语言理解与计算、答案推理和生成等关键科学问题, 因而受到工业界和学术界的广泛关注. 首先介绍常识问答领域的主要数据集; 其次, 归纳不同常识知识源在构建方式、常识来源和表现形式上的区别; 同时, 重点分析并对比前沿常识问答模型, 以及融合常识知识的特色方法. 特别地, 根据不同问答任务场景中常识知识的共性和特性, 建立包含属性、语义、因果、语境、抽象和意图6大类的知识分类体系. 以此为支撑, 针对常识知识数据集建设, 感知知识融合和预训练语言模型的协作机制, 以及在此基础上的常识知识预分类技术, 进行前瞻性的研究, 并具体报告上述模型在跨数据集迁移场景下的性能变化, 及其在常识答案推理中的潜在贡献. 总体上, 包含对现有数据和前沿技术的回顾, 也包含面向跨数据知识体系建设、技术迁移与通用化的预研内容, 借以在汇报领域技术积累的前提下, 为其理论和技术的进一步发展提供参考意见.

    Abstract:

    Commonsense question answering is an essential natural language understanding task that aims to solve natural language questions automatically by using commonsense knowledge to obtain accurate answers. It has a broad application prospect in areas such as virtual assistants or social chatbots and contains crucial scientific issues such as knowledge mining and representation, language understanding and computation, and answer reasoning and generation. Therefore, it has received wide attention from industry and academia. This study first introduces the main datasets in commonsense question answering. Secondly, it summarizes the distinctions between different sources of commonsense knowledge in terms of construction methods, knowledge sources, and presentation forms. Meanwhile, the study focuses on the analysis and comparison of the state-of-the-art commonsense question answering models, as well as the characteristic methods fusing commonsense knowledge. Particularly, based on the commonalities and characteristics of commonsense knowledge in different question answering task scenarios, this study establishes a commonsense knowledge classification system containing attribute, semantic, causal, context, abstract, and intention. On this basis, it conducts prospective research on the construction of commonsense knowledge datasets, the collaboration mechanism of perceptual knowledge fusion and pre-trained language models, and corresponding commonsense knowledge pre-classification techniques. Furthermore, the study reports specifically on the performance changes in the above models under cross-dataset migration scenarios and their potential contributions in commonsense answer reasoning. On the whole, this study gives a comprehensive review of existing data and state-of-the-art technologies, as well as a pre-research for the construction of cross-data knowledge systems, technology migration, and generalization, so as to provide references for the further development of theories and technologies while reporting on the existing technologies in the field.

    参考文献
    [1] Pujara J, Miao H, Getoor L, Cohen W. Knowledge graph identification. In: Proc. of the 12th Int’l Semantic Web Conf. Sydney: Springer, 2013. 542–557.
    [2] 王鑫, 邹磊, 王朝坤, 彭鹏, 冯志勇. 知识图谱数据管理研究综述. 软件学报, 2019, 30(7): 2139–2174. http://www.jos.org.cn/1000-9825/5841.htm
    Wang X, Zou L, Wang CK, Peng P, Feng ZY. Research on knowledge graph data management: A survey. Ruan Jian Xue Bao/Journal of Software, 2019, 30(7): 2139–2174 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/5841.htm
    [3] Holland PW. Statistics and causal inference. Journal of the American statistical Association, 1986, 81(396): 945–960. [doi: 10.1080/01621459.1986.10478354]
    [4] Settles B, Craven M. An analysis of active learning strategies for sequence labeling tasks. In: Proc. of the 2008 Conf. on Empirical Methods in Natural Language Processing. Honolulu: Association for Computational Linguistics, 2008. 1070–1079.
    [5] Liu H, Singh P. ConceptNet-A practical commonsense reasoning tool-kit. BT Technology Journal, 2004, 22(4): 211–226. [doi: 10.1023/B:BTTJ.0000047600.45421.6d]
    [6] Zaremba W, Sutskever I, Vinyals O. Recurrent neural network regularization. arXiv:1409.2329, 2015.
    [7] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735–1780. [doi: 10.1162/neco.1997.9.8.1735]
    [8] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate. In: Proc. of the 3rd Int’l Conf. on Learning Representations. San Diego, 2015. 1–15.
    [9] Devlin J, Chang M W, Lee K, Toutanova K. BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers). Minneapolis: Association for Computational Linguistics, 2019. 4171–4186.
    [10] Liu Z, Lin W, Shi Y, Zhao J. A robustly optimized BERT pre-training approach with post-training. In: Proc. of the 20th Chinese National Conf. on Computational Linguistics. Huhhot: Chinese Information Processing Society of China, 2021. 1218–1227.
    [11] Lewis M, Liu YH, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L. BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In: Proc. of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, 2020. 7871–7880.
    [12] Brown TB, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, Neelakantan A, Shyam P, Sastry G, Askell A, Agarwal S, Herbert-Voss A, Krueger G, Henighan T, Child R, Ramesh A, Ziegler DM, Wu J, Winter C, Hesse C, Chen M, Sigler E, Litwin M, Gray S, Chess B, Clark J, Berner C, McCandlish S, Radford A, Sutskever I, Amodei D. Language models are few-shot learners. In: Proc. of the 34th Int’l Conf. on Neural Information Processing Systems. Vancouver: Curran Associates Inc., 2020. 1877–1901.
    [13] Raffel C, Shazeer N, Roberts A, Lee K, Narang S, Matena M, Zhou YQ, Li W, Liu PJ. Exploring the limits of transfer learning with a unified text-to-text transformer. The Journal of Machine Learning Research, 2020, 21(1): 5485–5551.
    [14] Yang Y, Kang S. Common sense-based reasoning using external knowledge for question answering. IEEE Access, 2020, 8: 227185–227192. [doi: 10.1109/ACCESS.2020.3045762]
    [15] Lim J, Oh D, Jang Y, Yang K, Lim H. I know what you asked: Graph path learning using AMR for commonsense reasoning. In: Proc. of the 28th Int’l Conf. on Computational Linguistics. Barcelona: International Committee on Computational Linguistics, 2020. 2459–2471.
    [16] Ma KX, Francis J, Lu QY, Nyberg E, Oltramari A. Towards generalizable neuro-symbolic systems for commonsense question answering. In: Proc. of the 1st Workshop on Commonsense Inference in Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 22–32.
    [17] 李志峰, 邹博伟, 李烨秋, 金志凌, 洪宇. 基于多知识源融合的级联式常识问答方法. 山西大学学报(自然科学版), 2022, 45(2): 264–273. [doi: 10.13451/j.sxu.ns.2021099]
    Li ZF, Zou BW, Li YQ, Jin ZL, Hong Y. Cascading commonsense question answering method base on multi-source knowledge fusion. Journal of Shanxi University (Natural Science Edition), 2022, 45(2): 264–273 (in Chinese with English abstract). [doi: 10.13451/j.sxu.ns.2021099]
    [18] Wang RZ, Tang DY, Duan N, Wei ZY, Huang XJ, Ji JS, Cao GH, Jiang DX, Zhou M. K-adapter: Infusing knowledge into pre-trained models with adapters. In: Proc. of the 2021 Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Association for Computational Linguistics, 2021. 1405–1418.
    [19] Wang PF, Peng NY, Ilievski F, Szekely P, Ren X. Connecting the dots: A knowledgeable path generator for commonsense question answering. In: Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 2020. 4129–4140.
    [20] Talmor A, Herzig J, Lourie N, Berant J. CommonsenseQA: A question answering challenge targeting commonsense knowledge. In: Proc. of the 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol. 1 (Long and Short Papers). Minneapolis: Association for Computational Linguistics, 2019. 4149–4158.
    [21] Mihaylov T, Clark P, Khot T, Sabharwal A. Can a suit of armor conduct electricity? A new dataset for open book question answering. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: Association for Computational Linguistics, 2018. 2381–2391.
    [22] Clark P, Cowhey I, Etzioni O, Khot T, Sabharwal A, Schoenick C, Tafjord O. Think you have solved question answering? Try ARC, the AI2 reasoning challenge. arXiv:180305457, 2018.
    [23] Sap M, Rashkin H, Chen D, Le Bras R, Choi Y. Social IQa: Commonsense reasoning about social interactions. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 4463–4473.
    [24] Huang LF, Le Bras R, Bhagavatula C, Choi Y. Cosmos QA: Machine reading comprehension with contextual commonsense reasoning. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 2391–2401.
    [25] Ostermann S, Modi A, Roth M, Thater S, Pinkal M. MCScript: A novel dataset for assessing machine comprehension using script knowledge. In: Proc. of the 11th Int’l Conf. on Language Resources and Evaluation. Miyazaki: European Language Resources Association (ELRA), 2018. 3567–3574.
    [26] Ostermann S, Roth M, Pinkal M. MCScript2.0: A machine comprehension corpus focused on script events and participants. In: Proc. of the 8th Joint Conf. on Lexical and Computational Semantics. Minneapolis: Association for Computational Linguistics, 2019. 103–117.
    [27] Zhang S, Liu XD, Liu JJ, Gao JF, Duh K, van Durme B. ReCoRD: Bridging the gap between human and machine commonsense reading comprehension. arXiv:181012885, 2018.
    [28] Boratko M, Li X, O’Gorman T, Das R, Le D, McCallum A. ProtoQA: A question answering dataset for prototypical common-sense reasoning. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2020. 1122–1136.
    [29] Rahman A, Ng V. Resolving complex cases of definite pronouns: The Winograd schema challenge. In: Proc. of the 2012 Joint Conf. on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Jeju Island: Association for Computational Linguistics, 2012. 777–789.
    [30] Emami A, De La Cruz N, Trischler A, Suleman K, Cheung JCK. A knowledge hunting framework for common sense reasoning. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: Association for Computational Linguistics, 2018. 1949–1958.
    [31] Cai Z, Tu LF, Gimpel K. Pay attention to the ending: Strong neural baselines for the ROC story cloze task. In: Proc. of the 55th Annual Meeting of the Association for Computational Linguistics (Vol. 2: Short Papers). Vancouver: Association for Computational Linguistics, 2017. 616–622.
    [32] Shwartz V, West P, Le Bras R, Bhagavatula C, Choi Y. Unsupervised commonsense question answering with self-talk. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2020. 4615–4629.
    [33] Sun Y, Wang SH, Feng SK, Ding SY, Pang C, Shang JY, Liu JX, Chen XY, Zhao YB, Lu YX, Liu WX, Wu ZH, Gong WB, Liang JZ, Shang ZZ, Sun P, Liu W, Ouyang X, Yu DH, Tian H, Wu H, Wang HF. ERNIE 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation. arXiv:2107.02137, 2021.
    [34] Ma KX, Ilievski F, Francis J, Bisk Y, Nyberg E, Oltramari A. Knowledge-driven data construction for zero-shot evaluation in commonsense question answering. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(15): 13507–13515. [doi: 10.1609/aaai.v35i15.17593]
    [35] Lin BY, Chen XY, Chen JM, Ren X. KagNet: Knowledge-aware graph networks for commonsense reasoning. In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 2829–2839.
    [36] Lv SW, Guo DY, Xu JJ, Tang DY, Duan N, Gong M, Shou LJ, Jiang DX, Cao GH, Hu SL. Graph-based reasoning over heterogeneous external knowledge for commonsense question answering. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(5): 8449–8456. [doi: 10.1609/aaai.v34i05.6364]
    [37] Li YQ, Zou BW, Li ZF, Aw AT, Hong Y, Zhu QM. Winnowing knowledge for multi-choice question answering. In: Proc. of the 2021 Findings of the Association for Computational Linguistics. Punta Cana: Association for Computational Linguistics, 2021. 1157–1165.
    [38] Roemmele M, Bejan CA, Gordon AS. Choice of plausible alternatives: An evaluation of commonsense causal reasoning. In: Proc. of the 2011 AAAI Spring Symp. Stanford: AAAI, 2011. 90–95.
    [39] Levesque HJ, Davis E, Morgenstern L. The winograd schema challenge. In: Proc. of the 13th Int’l Conf. on the Principles of Knowledge Representation and Reasoning. Rome: Institute of Electrical and Electronics Engineers, 2012. 552–561.
    [40] Sharma A, Vo NH, Aditya S. Baral C. Towards addressing the winograd schema challenge: Building and using a semantic parser and a knowledge hunting module. In: Proc. of the 24th Int’l Joint Conf. on Artificial Intelligence. Buenos Aires: AAAI, 2015. 1319–1325.
    [41] Mostafazadeh N, Chambers N, He XD, Parikh D, Batra D, Vanderwende L, Kohli P, Allen J. A corpus and cloze evaluation for deeper understanding of commonsense stories. In: Proc. of the 2016 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. San Diego: Association for Computational Linguistics, 2016. 839–849.
    [42] Zellers R, Bisk Y, Schwartz R, Choi Y. SWAG: A large-scale adversarial dataset for grounded commonsense inference. In: Proc. of the 2018 Conf. on Empirical Methods in Natural Language Processing. Brussels: Association for Computational Linguistics, 2018. 93–104.
    [43] Han K, Xiao A, Wu EH, Guo JY, Xu CJ, Wang YH. Transformer in Transformer. In: Proc. of the 35th Conf. on Neural Information Processing Systems. Sydney, 2021. 15908–15919.
    [44] Improving language understanding by generative pre-training. 2018. https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf
    [45] Yang ZL, Dai ZH, Yang YM, Carbonell J, Salakhutdinov R, Le QV. XLNet: Generalized autoregressive pretraining for language understanding. In: Proc. of the 33rd Int’l Conf. on Neural Information Processing Systems. Vancouver, 2019. 5753–5763.
    [46] Sap M, Le Bras R, Allaway, E, Bhagavatula C, Lourie N, Rashkin H, Roof B, Smith NA, Choi Y. Atomic: An atlas of machine commonsense for if-then reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 3027–3035. [doi: 10.1609/aaai.v33i01.33013027]
    [47] Fellbaum C. WordNet: An Electronic Lexical Database. Cambridge: MIT Press, 1998. 21–120.
    [48] Krishna R, Zhu YK, Groth O, Johnson J, Hata K, Kravitz J, Chen S, Kalantidis Y, Li LJ, Shamma DA, Bernstein MS, Fei-Fei L. Visual genome: Connecting language and vision using crowdsourced dense image annotations. International Journal of Computer Vision, 2017, 123(1): 32–73. [doi: 10.1007/s11263-016-0981-7]
    [49] Vrandečić D, Krötzsch M. Wikidata: A free collaborative knowledge base. Communications of the ACM, 2014, 57(10): 78–85. [doi: 10.1145/2629489]
    [50] Singh P, Lin T, Mueller ET, Lim G, Perkins T, Zhu WL. Open mind common sense: Knowledge acquisition from the general public. In: Proc. of the 2002 OTM Confederated Int’l Conf. Berlin: Springer, 2002. 1223–1237.
    [51] Burton K, Java A, Soboroff I. The ICWSM 2009 Spinn3r dataset. In: Proc. of the 3rd Annual Conf. on Weblogs and Social Media. San Jose: AAAI, 2009.
    [52] Modi A, Anikina T, Ostermann S, Pinkal M. InScript: Narrative texts annotated with script information. In: Proc. of the 10th Int’l Conf. on Language Resources and Evaluation. 2016. 3485–3493.
    [53] Cambria E, Song YQ, Wang HX, Hussain A. Isanette: A common and common sense knowledge base for opinion mining. In: Proc. of the 11th IEEE Int’l Conf. on Data Mining Workshops. Vancouver: IEEE, 2011. 315–322.
    [54] Ilievski F, Oltramari A, Ma KX, Zhang B, McGuinness DL, Szekely P. Dimensions of commonsense knowledge. Knowledge-Based Systems, 2021, 229: 107347. [doi: 10.1016/j.knosys.2021.107347]
    [55] Lenat DB, Guha RV, Pittman K, Pratt D, Shepherd M. Cyc: Toward programs with common sense. Communications of the ACM, 1990, 33(8): 30–49. [doi: 10.1145/79173.79176]
    [56] Mostafazadeh N, Kalyanpur A, Moon L, Buchanan D, Berkowitz L, Biran O, Chu-Carroll J. GLUCOSE: Generalized and contextualized story explanations. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2020. 4569–4586.
    [57] Tandon N, De Melo G, Weikum G. WebChild 2.0: Fine-grained commonsense knowledge distillation. In: Proc. of the 2017 ACL, System Demonstrations. Vancouver: Association for Computational Linguistics, 2017. 115–120.
    [58] Romero J, Razniewski S, Pal K, Pan JZ, Sakhadeo A, Weikum G. Commonsense properties from query logs and question answering forums. In: Proc. of the 28th ACM Int’l Conf. on Information and Knowledge Management. Beijing: ACM, 2019. 1411–1420.
    [59] Cambria E, Li Y, Xing FZ, Poria S, Kwok K. SenticNet 6: Ensemble application of symbolic and subsymbolic AI for sentiment analysis. In: Proc. of the 29th ACM Int’l Conf. on Information & Knowledge Management. Ireland: ACM, 2020. 105–114.
    [60] Bhakthavatsalam S, Richardson K, Tandon N, Clark P. Do dogs have whiskers? A new knowledge base of haspart relations. arXiv:2006.07510, 2020.
    [61] Wu WT, Li HS, Wang HX, Zhu KQ. Probase: A probabilistic taxonomy for text understanding. In: Proc. of the 2012 ACM SIGMOD Int’l Conf. on Management of Data. Scottsdale: ACM, 2012. 481–492.
    [62] Cambria E, Song YQ, Wang HX, Howard N. Semantic multidimensional scaling for open-domain sentiment analysis. IEEE Intelligent Systems, 2014, 29(2): 44–51. [doi: 10.1109/MIS.2012.118]
    [63] Tanon TP, Weikum G, Suchanek F. YAGO 4: A reason-able knowledge base. In: Proc. of the 17th Int’l Conf. on the Semantic Web. Heraklion: Springer, 2020. 583–596.
    [64] Guha RV, Brickley D, Macbeth S. Schema. org: Evolution of structured data on the web. Communications of the ACM, 2016, 59(2): 44–51. [doi: 10.1145/2844544]
    [65] Gangemi A, Guarino N, Masolo C, Oltramari A, Schneider L. Sweetening ontologies with DOLCE. In: Knowledge Engineering and Knowledge Management: Ontologies and the Semantic Web. Berlin: Springer, 2002. 166–181.
    [66] Niles I, Pease A. Towards a standard upper ontology. In: Proc. of the 2001 Int’l Conf. on Formal Ontology in Information Systems. Ogunquit: ACM, 2001. 2–9.
    [67] Bennett JS. ROGET: A knowledge-based system for acquiring the conceptual structure of a diagnostic expert system. Journal of Automated Reasoning, 1985, 1(1): 49–74. [doi: 10.1007/BF00244289]
    [68] Baker CF, Fillmore CJ, Lowe JB. The berkeley framenet project. In: Proc. of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th Int’l Conf. on Computational Linguistics. Montreal: ACM, 1998. 86–90.
    [69] Dodge EK, Hong J, Stickles E. MetaNet: Deep semantic automatic metaphor analysis. In: Proc. of the 3rd Workshop on Metaphor in NLP. Denver: Association for Computational Linguistics, 2015. 40–49.
    [70] Schuler KK. VerbNet: A Broad-coverage, Comprehensive Verb Lexicon. Philadelphia: University of Pennsylvania, 2005.
    [71] Bhakthavatsalam S, Anastasiades C, Clark P. GenericsKB: A knowledge base of generic statements. arXiv:200500660, 2020.
    [72] Radford A, Wu J, Child R, Luan D, Amodei D, Sutskever I. Language models are unsupervised multitask learners. OpenAI blog, 2019, 1(8): 9. (查阅所有网上资料, 请确认标黄部分信息)
    [73] Bosselut A, Rashkin H, Sap M, Malaviya C, Celikyilmaz A, Choi Y. COMET: Commonsense transformers for automatic knowledge graph construction. In: Proc. of the 57th Annual Meeting of the Association for Computational Linguistics. Florence: Association for Computational Linguistics, 2019. 4762–4779.
    [74] Xu YH, Zhu CG, Xu RC, Liu Y, Zeng M, Huang XD. Fusing context into knowledge graph for commonsense question answering. In: Proc. of the 2021 Findings of the Association for Computational Linguistics. Association for Computational Linguistics, 2021. 1201–1207.
    [75] Feng YL, Chen XY, Lin BY, Wang PF, Yan J, Ren X. Scalable multi-hop relational reasoning for knowledge-aware question answering. In: Proc. of the 2020 Conf. on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2020. 1295–1309.
    [76] Yasunaga M, Ren HY, Bosselut A, Liang P, Leskovec J. QA-GNN: Reasoning with language models and knowledge graphs for question answering. In: Proc. of the 2021 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Association for Computational Linguistics, 2021. 535–546.
    [77] Sun YQ, Shi Q, Qi L, Zhang Y. JointLK: Joint reasoning with language models and knowledge graphs for commonsense question answering. In: Proc. of the 2022 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Seattle: Association for Computational Linguistics, 2021. 5049–5060.
    [78] Wang JX, Li XY, Tan Z, Zhao X, Xiao WD. Relation-aware bidirectional path reasoning for commonsense question answering. In: Proc. of the 25th Conf. on Computational Natural Language Learning. Association for Computational Linguistics, 2021. 445–453.
    [79] Yan J, Raman M, Chan A, Zhang TY, Rossi R, Zhao HD, Kim S, Lipka N, Ren X. Learning contextualized knowledge structures for commonsense reasoning. In: Proc. of the 2021 Findings of the Association for Computational Linguistics (ACL-IJCNLP 2021). Association for Computational Linguistics, 2021. 4038–4051.
    [80] Ye ZX, Chen Q, Wang W, Ling ZH. Align, mask and select: A simple method for incorporating commonsense knowledge into language representation models. arXiv:1908.06725, 2020.
    [81] Niu YL, Huang F, Liang JM, Chen WK, Zhu XY, Huang ML. A semantic-based method for unsupervised commonsense question answering. In: Proc. of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th Int’l Joint Conf. on Natural Language Processing (Vol. 1: Long Papers). Association for Computational Linguistics, 2021. 3037–3049.
    [82] Lourie N, Le Bras R, Bhagavatula C, Choi Y. Unicorn on rainbow: A universal commonsense reasoning model on a new multitask benchmark. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(15): 13480–13488. [doi: 10.1609/aaai.v35i15.17590]
    [83] Khashabi D, Min S, Khot T, Sabharwal A, Tafjord O, Clark P, Hajishirzi H. UNIFIEDQA: Crossing format boundaries with a single QA system. In: Proc. of the 2020 Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 2020. 1896–1907.
    [84] Clark K, Luong MT, Le QV, Manning CD. ELECTRA: Pre-training text encoders as discriminators rather than generators. arXiv:2003.10555, 2020.
    [85] Ilievski F, Szekely P, Zhang B. CSKG: The commonsense knowledge graph. In: Proc. of the 18th Int’l Conf. on the Semantic Web. Springer, 2021. 680–696.
    [86] Kavumba P, Inoue N, Heinzerling B, Heinzerling B, Singh K, Reisert P, Inui K. When choosing plausible alternatives, clever hans can be clever. In: Proc. of the 1st Workshop on Commonsense Inference in Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 33–42.
    [87] Da J, Kasai J. Cracking the contextual commonsense code: Understanding commonsense reasoning aptitude of deep contextual representations. In: Proc. of the 1st Workshop on Commonsense Inference in Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 1–12.
    [88] Petroni F, Rocktäschel T, Riedel S, Lewis P, Bakhtin A, Wu YX, Miller A. Language models as knowledge bases? In: Proc. of the 2019 Conf. on Empirical Methods in Natural Language Processing and the 9th Int’l Joint Conf. on Natural Language Processing. Hong Kong: Association for Computational Linguistics, 2019. 2463–2473.
    [89] Poerner N, Waltinger U, Schütze H. E-BERT: Efficient-yet-effective entity embeddings for BERT. In: Proc. of the 2020 Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics, 2020. 803–818.
    [90] Li DW, Li YR, Zhang JY, Li K, Wei C, Cui JW, Wang B. C3KG: A Chinese commonsense conversation knowledge graph. In: Proc. of the 2022 Findings of the Association for Computational Linguistics: ACL 2022. Dublin: Association for Computational Linguistics, 2022. 1369–1383.
    引证文献
    网友评论
    网友评论
    分享到微博
    发 布
引用本文

范怡帆,邹博伟,徐庆婷,李志峰,洪宇.常识问答研究综述.软件学报,2024,35(1):236-265

复制
分享
文章指标
  • 点击次数:1098
  • 下载次数: 4353
  • HTML阅读次数: 3116
  • 引用次数: 0
历史
  • 收稿日期:2022-10-18
  • 最后修改日期:2022-12-29
  • 在线发布日期: 2023-08-09
  • 出版日期: 2024-01-06
文章二维码
友情链接:中国科学院软件研究所中国计算机学会中国科学院国家自然科学基金委员会CCF数字图书馆Int'l J of Softw Info计算机系统应用
您是第20525171位访问者
版权所有：中国科学院软件研究所 京ICP备05046678号-3
地址：北京市海淀区中关村南四街4号,邮政编码：100190
电话：010-62562563 传真：010-62562533 Email：jos@iscas.ac.cn
技术支持：北京勤云科技发展有限公司

京公网安备 11040202500063号