{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,15]],"date-time":"2026-08-15T20:34:29Z","timestamp":1786826069836,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589334.3645610","type":"proceedings-article","created":{"date-parts":[[2024,5,8]],"date-time":"2024-05-08T07:08:13Z","timestamp":1715152093000},"page":"2204-2215","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Causal Question Answering with Reinforcement Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0230-3995","authenticated-orcid":false,"given":"Lukas","family":"Bl\u00fcbaum","sequence":"first","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4525-6865","authenticated-orcid":false,"given":"Stefan","family":"Heindorf","sequence":"additional","affiliation":[{"name":"Paderborn University, Paderborn, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2022.09.029"},{"key":"e_1_3_2_2_3_1","volume-title":"Axel-Cyrille Ngonga Ngomo, Benno Stein, Pavel Braslavski, Matthias Hagen, and Martin Potthast.","author":"Bondarenko Alexander","year":"2022","unstructured":"Alexander Bondarenko, Magdalena Wolska, Stefan Heindorf, Lukas Bl\u00fc baum, Axel-Cyrille Ngonga Ngomo, Benno Stein, Pavel Braslavski, Matthias Hagen, and Martin Potthast. 2022. CausalQA: A Benchmark for Causal Question Answering. In COLING. International Committee on Computational Linguistics, 3296--3308."},{"key":"e_1_3_2_2_4_1","volume-title":"CEUR Workshop Proceedings","volume":"3005","author":"Dalal Dhairya","year":"2021","unstructured":"Dhairya Dalal. 2021. Knowledge augmented language models for causal question answering. CEUR Workshop Proceedings , Vol. 3005 (2021), 17--24."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"crossref","unstructured":"Dhairya Dalal Mihael Arcan and Paul Buitelaar. 2021. Enhancing Multiple-Choice Question Answering with Causal Knowledge. In DeeLIO@NAACL-HLT. ACL 70--80.","DOI":"10.18653\/v1\/2021.deelio-1.8"},{"key":"e_1_3_2_2_6_1","unstructured":"Rajarshi Das Shehzaad Dhuliawala Manzil Zaheer Luke Vilnis Ishan Durugkar Akshay Krishnamurthy Alex Smola and Andrew McCallum. 2018. Go for a Walk and Arrive at the Answer: Reasoning Over Paths in Knowledge Bases using Reinforcement Learning. In ICLR."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"crossref","unstructured":"Tim Dettmers Pasquale Minervini Pontus Stenetorp and Sebastian Riedel. 2018. Convolutional 2D Knowledge Graph Embeddings. In AAAI. 1811--1818.","DOI":"10.1609\/aaai.v32i1.11573"},{"key":"e_1_3_2_2_8_1","volume-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. ACL, 4171--4186.","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019a. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In NAACL-HLT. ACL, 4171--4186."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19--1423"},{"key":"e_1_3_2_2_10_1","volume-title":"Moldovan","author":"Girju Roxana","year":"2002","unstructured":"Roxana Girju and Dan I. Moldovan. 2002. Text Mining for Causal Relations. In FLAIRS. 360--364."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1175"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"Oktie Hassanzadeh Debarun Bhattacharjya Mark Feblowitz Kavitha Srinivas Michael Perrone Shirin Sohrabi and Michael Katz. 2019. Answering Binary Causal Questions Through Large-Scale Text Mining: An Evaluation Using Cause-Effect Pairs from Human Experts. In IJCAI. ijcai.org 5003--5009.","DOI":"10.24963\/ijcai.2019\/695"},{"key":"e_1_3_2_2_13_1","volume-title":"Axel-Cyrille Ngonga Ngomo, and Martin Potthast","author":"Heindorf Stefan","year":"2020","unstructured":"Stefan Heindorf, Yan Scholten, Henning Wachsmuth, Axel-Cyrille Ngonga Ngomo, and Martin Potthast. 2020. CauseNet: Towards a Causality Graph Extracted from the Web. In CIKM. ACM, 3023--3030."},{"key":"e_1_3_2_2_14_1","volume-title":"Zornitsa Kozareva, Preslav Nakov, Diarmuid \u00d3 S\u00e9 aghdha, Sebastian Pad\u00f3, Marco Pennacchiotti, Lorenza Romano, and Stan Szpakowicz.","author":"Hendrickx Iris","year":"2010","unstructured":"Iris Hendrickx, Su Nam Kim, Zornitsa Kozareva, Preslav Nakov, Diarmuid \u00d3 S\u00e9 aghdha, Sebastian Pad\u00f3, Marco Pennacchiotti, Lorenza Romano, and Stan Szpakowicz. 2010. SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations between Pairs of Nominals. In SemEval@ACL. ACL, 33--38."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_16_1","volume-title":"Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi.","author":"Hwang Jena D.","year":"2021","unstructured":"Jena D. Hwang, Chandra Bhagavatula, Ronan Le Bras, Jeff Da, Keisuke Sakaguchi, Antoine Bosselut, and Yejin Choi. 2021. (Comet-) Atomic 2020: On Symbolic and Neural Commonsense Knowledge Graphs. In AAAI. 6384--6392."},{"key":"e_1_3_2_2_17_1","volume-title":"CSKG: The CommonSense Knowledge Graph. In ESWC","author":"Ilievski Filip","year":"2021","unstructured":"Filip Ilievski, Pedro A. Szekely, and Bin Zhang. 2021. CSKG: The CommonSense Knowledge Graph. In ESWC, Vol. 12731. Springer, 680--696."},{"key":"e_1_3_2_2_18_1","volume-title":"Rishiraj Saha Roy, and Gerhard Weikum","author":"Kaiser Magdalena","year":"2021","unstructured":"Magdalena Kaiser, Rishiraj Saha Roy, and Gerhard Weikum. 2021. Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs. In SIGIR. ACM, 459--469."},{"key":"e_1_3_2_2_19_1","volume-title":"Watters","author":"Kayesh Humayun","year":"2020","unstructured":"Humayun Kayesh, Md. Saiful Islam, Junhu Wang, Shikha Anirban, A. S. M. Kayes, and Paul A. Watters. 2020. Answering Binary Causal Questions: A Transfer Learning Based Approach. In IJCNN. IEEE, 1--9."},{"key":"e_1_3_2_2_20_1","volume-title":"UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training. CoRR","author":"Khashabi Daniel","year":"2022","unstructured":"Daniel Khashabi, Yeganeh Kordi, and Hannaneh Hajishirzi. 2022. UnifiedQA-v2: Stronger Generalization via Broader Cross-Format Training. CoRR , Vol. abs\/2202.12359 (2022)."},{"key":"e_1_3_2_2_21_1","volume-title":"EMNLP (Findings) (Findings of ACL","author":"Khashabi Daniel","unstructured":"Daniel Khashabi, Sewon Min, Tushar Khot, Ashish Sabharwal, Oyvind Tafjord, Peter Clark, and Hannaneh Hajishirzi. 2020. UnifiedQA: Crossing Format Boundaries With a Single QA System. In EMNLP (Findings) (Findings of ACL, Vol. EMNLP 2020). ACL, 1896--1907."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"Zhongyang Li Xiao Ding Ting Liu J. Edward Hu and Benjamin Van Durme. 2020. Guided Generation of Cause and Effect. In IJCAI. ijcai.org 3629--3636.","DOI":"10.24963\/ijcai.2020\/502"},{"key":"e_1_3_2_2_23_1","unstructured":"Xi Victoria Lin Richard Socher and Caiming Xiong. 2018. Multi-Hop Knowledge Graph Reasoning with Reward Shaping. In EMNLP. ACL 3243--3253."},{"key":"e_1_3_2_2_24_1","volume-title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR , Vol. abs\/1907.11692 (2019). showeprint[arXiv]1907.11692 http:\/\/arxiv.org\/abs\/1907.11692"},{"key":"e_1_3_2_2_25_1","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. In ICLR (Poster). OpenReview.net."},{"key":"e_1_3_2_2_26_1","volume-title":"Steven Bethard, and David McClosky.","author":"Manning Christopher D.","year":"2014","unstructured":"Christopher D. Manning, Mihai Surdeanu, John Bauer, Jenny Rose Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP Natural Language Processing Toolkit. In ACL (System Demonstrations). ACL, 55--60."},{"key":"e_1_3_2_2_27_1","volume-title":"Asynchronous Methods for Deep Reinforcement Learning. In ICML (JMLR Workshop and Conference Proceedings","volume":"1937","author":"Mnih Volodymyr","year":"2016","unstructured":"Volodymyr Mnih, Adri\u00e0 Puigdom\u00e8 nech Badia, Mehdi Mirza, Alex Graves, Timothy P. Lillicrap, Tim Harley, David Silver, and Koray Kavukcuoglu. 2016. Asynchronous Methods for Deep Reinforcement Learning. In ICML (JMLR Workshop and Conference Proceedings, Vol. 48). JMLR.org, 1928--1937."},{"key":"e_1_3_2_2_28_1","volume-title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In CoCo@NIPS (CEUR Workshop Proceedings","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A Human Generated MAchine Reading COmprehension Dataset. In CoCo@NIPS (CEUR Workshop Proceedings, Vol. 1773). CEUR-WS.org."},{"key":"e_1_3_2_2_29_1","unstructured":"OpenAI. 2023. GPT-4 Technical Report. CoRR Vol. abs\/2303.08774 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2303.08774 showeprint[arXiv]2303.08774"},{"key":"e_1_3_2_2_30_1","volume-title":"ICML (JMLR Workshop and Conference Proceedings","volume":"1318","author":"Pascanu Razvan","year":"2013","unstructured":"Razvan Pascanu, Tom\u00e1 s Mikolov, and Yoshua Bengio. 2013. On the difficulty of training recurrent neural networks. In ICML (JMLR Workshop and Conference Proceedings, Vol. 28). JMLR.org, 1310--1318."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"e_1_3_2_2_32_1","volume-title":"Manning","author":"Pennington Jeffrey","year":"2014","unstructured":"Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. Glove: Global Vectors for Word Representation. In EMNLP. ACL, 1532--1543."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"crossref","unstructured":"Yunqi Qiu Yuanzhuo Wang Xiaolong Jin and Kun Zhang. 2020. Stepwise Reasoning for Multi-Relation Question Answering over Knowledge Graph with Weak Supervision. In WSDM. ACM 474--482.","DOI":"10.1145\/3336191.3371812"},{"key":"e_1_3_2_2_34_1","article-title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J. Liu. 2020. Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer. J. Mach. Learn. Res. , Vol. 21 (2020), 140:1--140:67.","journal-title":"J. Mach. Learn. Res."},{"key":"e_1_3_2_2_35_1","volume-title":"Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi.","author":"Sap Maarten","year":"2019","unstructured":"Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi. 2019. ATOMIC: An Atlas of Machine Commonsense for If-Then Reasoning. In AAAI. 3027--3035."},{"key":"e_1_3_2_2_36_1","unstructured":"John Schulman Philipp Moritz Sergey Levine Michael I. Jordan and Pieter Abbeel. 2016. High-Dimensional Continuous Control Using Generalized Advantage Estimation. In ICLR (Poster)."},{"key":"e_1_3_2_2_37_1","volume-title":"Proximal Policy Optimization Algorithms. CoRR","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. CoRR , Vol. abs\/1707.06347 (2017)."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"crossref","unstructured":"Rebecca Sharp Mihai Surdeanu Peter Jansen Peter Clark and Michael Hammond. 2016. Creating Causal Embeddings for Question Answering with Minimal Supervision. In EMNLP. ACL 138--148.","DOI":"10.18653\/v1\/D16-1014"},{"key":"e_1_3_2_2_39_1","unstructured":"Yelong Shen Jianshu Chen Po-Sen Huang Yuqing Guo and Jianfeng Gao. 2018. M-Walk: Learning to Walk over Graphs using Monte Carlo Tree Search. In NeurIPS. 6787--6798."},{"key":"e_1_3_2_2_40_1","volume-title":"Mastering the game of Go with deep neural networks and tree search. Nat","author":"Silver David","year":"2016","unstructured":"David Silver, Aja Huang, Chris J. Maddison, Arthur Guez, Laurent Sifre, George van den Driessche, Julian Schrittwieser, Ioannis Antonoglou, Vedavyas Panneershelvam, Marc Lanctot, Sander Dieleman, Dominik Grewe, John Nham, Nal Kalchbrenner, Ilya Sutskever, Timothy P. Lillicrap, Madeleine Leach, Koray Kavukcuoglu, Thore Graepel, and Demis Hassabis. 2016. Mastering the game of Go with deep neural networks and tree search. Nat. , Vol. 529, 7587 (2016), 484--489."},{"key":"e_1_3_2_2_41_1","volume-title":"Science","volume":"362","author":"Silver David","year":"2018","unstructured":"David Silver, Thomas Hubert, Julian Schrittwieser, Ioannis Antonoglou, Matthew Lai, Arthur Guez, Marc Lanctot, Laurent Sifre, Dharshan Kumaran, Thore Graepel, et al. 2018. A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play. Science, Vol. 362, 6419 (2018), 1140--1144."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"crossref","unstructured":"Robyn Speer Joshua Chin and Catherine Havasi. 2017. ConceptNet 5.5: An Open Multilingual Graph of General Knowledge. In AAAI. 4444--4451.","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_2_43_1","volume-title":"Barto","author":"Sutton Richard S.","year":"1998","unstructured":"Richard S. Sutton and Andrew G. Barto. 1998. Reinforcement learning - an introduction."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1075\/cvs.5"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"crossref","unstructured":"Guojia Wan and Bo Du. 2021. GaussianPath: A Bayesian Multi-Hop Reasoning Framework for Knowledge Graph Reasoning. In AAAI. 4393--4401.","DOI":"10.1609\/aaai.v35i5.16565"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2212.03533"},{"key":"e_1_3_2_2_47_1","volume-title":"Ximing Lu, Sean Welleck, and Yejin Choi.","author":"West Peter","year":"2022","unstructured":"Peter West, Chandra Bhagavatula, Jack Hessel, Jena D. Hwang, Liwei Jiang, Ronan Le Bras, Ximing Lu, Sean Welleck, and Yejin Choi. 2022. Symbolic Knowledge Distillation: from General Language Models to Commonsense Models. In NAACL-HLT. ACL, 4602--4625."},{"key":"e_1_3_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"crossref","unstructured":"Wenhan Xiong Thien Hoang and William Yang Wang. 2017. DeepPath: A Reinforcement Learning Method for Knowledge Graph Reasoning. In EMNLP. ACL 564--573. io","DOI":"10.18653\/v1\/D17-1060"}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645610","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589334.3645610","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:32:53Z","timestamp":1755822773000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589334.3645610"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":49,"alternative-id":["10.1145\/3589334.3645610","10.1145\/3589334"],"URL":"https:\/\/doi.org\/10.1145\/3589334.3645610","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}