Elamur Research⌕
☰
home / papers / 2017 / SemEval-2017 Task 3: Community Question Answering

SemEval-2017 Task 3: Community Question Answering

Paper · 2017 · Preslav Nakov, Doris Hoogeveen, Lluís Màrquez et al.

Summary

This paper reports on the third edition of the SemEval shared task on Community Question Answering (CQA). The task targets web forums such as Qatar Living, where open posting produces long, noisy threads that are hard for users to read. The organizers reran the four 2016 subtasks: (A) ranking comments in a thread by relevance to its question, (B) reranking retrieved questions by similarity to a new question, (C) ranking comments from other threads as answers to a new question, and (D) an Arabic answer-reranking subtask built on medical forums. Training data came from the 2015 and 2016 editions, and new test sets were created. A new subtask E added large-scale, multi-domain duplicate question detection on StackExchange data (CQADupStack). Twenty-three teams took part. The top-performing approaches relied either on neural models built on distributed representations or on support vector machines using syntactic kernels, and they beat the baselines clearly on A–C. No team entered subtask E, which the authors attribute to its data volume. The released annotated datasets are a lasting resource for CQA research in English and Arabic.

Key points

  • 23 teams submitted 85 runs (36 primary, 49 contrastive) for subtasks A–D, compared with 18 teams and 95 runs in 2016.
  • The best official MAP scores were 88.43 (A), 47.22 (B), 15.46 (C) and 61.16 (D).
  • Subtask E asked systems to rerank 50 candidate questions per query using CQADupStack (StackExchange subforums), but it received no submissions.
  • Data covers English (Qatar Living) and Arabic (three medical forums), labeled through crowdsourcing. The test set for D was prepared with a slightly changed procedure.
  • Notable systems:
    • GW QA, best on D, used WTMF latent models trained partly on Arabic Gigaword, with MADAMIRA preprocessing.
    • bunji, second on C, combined decomposable-attention features in a CRF.
    • Talla did well on B with a random-forest pairwise-preference model of 2,000 estimators.

Interesting ideas

  • I1. Similarity triangle decomposition. The main problem (new question → external comment) is split into two easier pairwise problems: question–question and question–comment within a thread. Each can be modeled and evaluated separately and then combined, which suits any retrieval-then-answer pipeline.
  • I2. Modeling missing words for short texts. WTMF uses words absent from a short text as a signal of what the text is not about. This reduces sparsity and could help with short Ukrainian forum posts or product titles.
  • I3. "Plausibility" features. These check whether a comment actually tries to answer, rather than making a side remark or asking for clarification. Such cheap, task-specific cues are useful for filtering noisy user-generated content.
  • I4. Bilingual domain lexicon plus machine translation. UPC-USMBA translated Arabic data into English and used a lexicon of body parts, drugs and diseases in both languages. This lets a lower-resource language reuse English tools, a pattern that transfers to Ukrainian.
  • I5. Rerunning a shared task. Repeating a newly designed task with fresh test data while keeping old data for training gives participants a second, better-informed attempt and produces comparable results across years.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓The University of MelbourneMelbourne · Australia60 works · 21,199 citations🎓Hamad bin Khalifa UniversityDoha · Qatar71 works · 12,942 citations

📚 Shelves 5The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 worksInformation Systems · 523 works

🧭 Topics 2Research subjects and languages the work is about.Question answering · 242 worksSemitic languages · 1,484 works

Cite

Cite as Preslav Nakov, Doris Hoogeveen, Lluís Màrquez, Alessandro Moschitti, Hamdy Mubarak, Timothy Baldwin and Karin Verspoor. 2017. SemEval-2017 Task 3: Community Question Answering. Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/s17-2003

@inproceedings{nakov2017semeval,
  title = {{SemEval-2017 Task 3: Community Question Answering}},
  author = {Preslav Nakov, Doris Hoogeveen, Lluís Màrquez, Alessandro Moschitti, Hamdy Mubarak, Timothy Baldwin and Karin Verspoor},
  booktitle = {Proceedings of the 11th International Workshop on Semantic Evaluation (SemEval-2017)},
  year = {2017},
  doi = {10.18653/v1/s17-2003},
  url = {https://doi.org/10.18653/v1/s17-2003}
}

References

89 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Adam Berger, Rich Caruana, David Cohn, Dayne Freitag, and Vibhu Mittal. 2000. Bridging the lexical chasm: Statistical approaches to answer-finding. In Proceedings of the 23rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Athens, Greece, SIGIR ’00, pa… find
  2. Eneko Agirre, Carmen Banea, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre, Rada Mihalcea, German Rigau, and Janyce Wiebe. 2016. SemEval-2016 Task 1: Semantic textual similarity, monolingual and cross-lingual evaluation. In Proceedings of the Workshop on Semantic Evaluation. San Diego, California, USA…
  3. Daniele Bonadiman, Antonio Uva, and Alessandro Moschitti. 2017. Effective shared representations with multitask learning for community question answering. In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics. Valencia, Spain, pages 726–732. find
  4. Surya Agustian and Hiroya Takamura. 2017. UINSUSKA-TiTech at SemEval-2017 task 3: Exploiting word importance levels as similarity features for CQA. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 370–374. find
  5. Peter Brown, Vincent Della Pietra, Stephen Della Pietra, and Robert Mercer. 1993. The mathematics of statistical machine translation: Parameter estimation. Comput. Linguist. 19(2):263–311. find
  6. Nada Almarwani and Mona Diab. 2017. GW QA at SemEval-2017 task 3: Question answer re-ranking on Arabic fora. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 344–348. find
  7. Xin Cao, Gao Cong, Bin Cui, Christian Søndergaard Jensen, and Ce Zhang. 2009. The use of categorization information in language models for question retrieval. In Proceedings of the 18th ACM Conference on Information and Knowledge Management. Hong Kong, China, CIKM ’09, pages 265–274. find
  8. Giuseppe Attardi, Antonio Carta, Federico Errica, Andrea Madotto, and Ludovica Pannitto. 2017. FA3L at SemEval-2017 task 3: A three embeddings recurrent neural network for question answering. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pa… find
  9. Yunbo Cao, Huizhong Duan, Chin-Yew Lin, Yong Yu, and Hsiao-Wuen Hon. 2008. Recommending questions using the MDL-based tree cut model. In Proceedings of the International Conference on World Wide Web. Beijing, China, WWW ’08, pages 81–90. find
  10. Daniel Balchev, Yasen Kiprov, Ivan Koychev, and Preslav Nakov. 2016. PMI-cool at SemEval-2016 Task 3: Experiments with PMI and goodness polarity lexicons for community question answering. In Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego, California, USA, SemEval ’1… find
  11. Delphine Charlet and Geraldine Damnati. 2017. Sim-Bow at SemEval-2017 task 3: Soft-cosine semantic similarity between questions for community question answering. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 315–319. find
  12. Alberto Barrón-Cedeño, Simone Filice, Giovanni Da San Martino, Shafiq Joty, Lluı́s Màrquez, Preslav Nakov, and Alessandro Moschitti. 2015. Thread-level information for comment classification in community question answering. In Proceedings of the 53rd Annual Meeting of the Association for Computat… find
  13. Gordon V Cormack, Charles LA Clarke, and Stefan Buettcher. 2009. Reciprocal rank fusion outperforms condorcet and individual rank learning methods. In Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval. Boston, Massachusetts, USA, SIGIR ’0…
  14. Giovanni Da San Martino, Alberto Barrón Cedeño, Salvatore Romeo, Antonio Uva, and Alessandro Alberto Barrón-Cedeño, Giovanni Da San Martino, Shafiq Joty, Alessandro Moschitti, Fahad A. Al Moschitti. 2016. Learning to re-rank questions in community question answering using advanced features. In P… find
  15. Simone Filice, Giovanni Da San Martino, and Alessandro Moschitti. 2017. KeLP at SemEval-2017 task 3: Learning pairwise patterns in community question answering. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 327–334. find
  16. Giovanni Da San Martino, Salvatore Romeo, Alberto Barrón-Cedeño, Shafiq Joty, Lluı́s Màrquez, Alessandro Moschitti, and Preslav Nakov. 2017. Cross-language question re-ranking. In Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval. Toky… find
  17. Byron Galbraith, Bhanu Pratap, and Daniel Shank. 2017. Talla at SemEval-2017 task 3: Identifying similar questions through paraphrase detection. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 375–379. find
  18. Jan Milan Deriu and Mark Cieliebak. 2017. SwissAlps at SemEval-2017 task 3: Attention-based convolutional neural network for community question answering. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 334–338. find
  19. Naman Goyal. 2017. LearningToQuestion at SemEval 2017 task 3: Ranking similar questions by learning to rank using rich features. In Proceedings of the International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 310–314. find
  20. Francisco Guzmán, Shafiq Joty, Lluı́s Màrquez, and Preslav Nakov. 2015. Pairwise neural machine translation evaluation. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing, Chi… find
  21. Cicero dos Santos, Luciano Barbosa, Dasha Bogdanova, and Bianca Zadrozny. 2015. Learning hybrid representations to retrieve semantically equivalent questions. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natu… find
  22. Francisco Guzmán, Lluı́s Màrquez, and Preslav Nakov. 2016a. Machine translation evaluation meets community question answering. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, ACL ’16, pages 460–466. find
  23. Huizhong Duan, Yunbo Cao, Chin-Yew Lin, and Yong Yu. 2008. Searching questions by identifying question topic and question focus. In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. Columbus, Ohio, USA, pages 156–164. find
  24. Francisco Guzmán, Preslav Nakov, and Lluı́s Màrquez. 2016b. MTE-NN at SemEval-2016 Task 3: Can machine translation evaluation help community question answering? In Proceedings of the International Workshop on Semantic Evaluation. San Diego, California, USA, SemEval ’16, pages 887–895. find
  25. Abdessamad Echihabi and Daniel Marcu. 2003. A noisy-channel approach to question answering. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics. Sapporo, Japan, ACL ’03, pages 16–23. find
  26. Yassine El Adlouni, Imane LAHBARI, Horacio Rodriguez, Mohammed Meknassi, Said Ouatik El Alaoui, and Noureddine Ennahnahi. 2017. UPC-USMBA at SemEval-2017 task 3: Combining multiple approaches for CQA for Arabic. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Can… find
  27. Michael Heilman and Noah A. Smith. 2010. Tree edit models for recognizing textual entailments, paraphrases, and answers to questions. In Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics. Los Angeles, California, US…
  28. Minwei Feng, Bing Xiang, Michael R. Glass, Lidan Wang, and Bowen Zhou. 2015. Applying deep learning to answer selection: a study and an open task. In Proceedings of the Workshop on Automatic Speech Recognition and Understanding. Scottsdale, Arizona, USA, ASRU ’15, pages 813–820. find
  29. Doris Hoogeveen, Yitong Li, Huizhi Liang, Bahar Salehi, Timothy Baldwin, and Long Duong. 2016a. UniMelb at SemEval-2016 Task 3: Identifying similar questions by combining a CNN with string similarity measures. In Proceedings of the International Workshop on Semantic Evaluation. San Diego, California… find
  30. Simone Filice, Danilo Croce, Alessandro Moschitti, and Roberto Basili. 2016. KeLP at SemEval-2016 Task 3: Learning semantic relations between questions and answers. In Proceedings of the Workshop on Semantic Evaluation. San Diego, California, USA, SemEval ’16, pages 1116–1123. find
  31. Doris Hoogeveen, Karin Verspoor, and Timothy Baldwin. 2016b. CQADupStack: Gold or silver? In Proceedings of the SIGIR 2016 Workshop on Web Question Answering Beyond Factoids. Pisa, Italy, WebQA ’16. find
  32. Shuguang Li and Suresh Manandhar. 2011. Improving question recommendation by exploiting information need. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. Portland, Oregon, USA, ACL ’11, pages 1425–1434. find
  33. Doris Hoogeveen, Karin M. Verspoor, and Timothy Baldwin. 2015. CQADupStack: A benchmark data set for community question-answering research. In Proceedings of the 20th Australasian Document Computing Symposium. Parramatta, NSW, Australia, ADCS ’15, pages 3:1–3:8. find
  34. Fei Liu, Alistair Moffat, Timothy Baldwin, and Xiuzhen Zhang. 2016. Quit while ahead: Evaluating truncated rankings. In Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval. Pisa, Italy, SIGIR ’16, pages 953–956. find
  35. Enamul Hoque, Shafiq Joty, Lluı́s Màrquez, Alberto Barrón-Cedeño, Giovanni Da San Martino, Alessandro Moschitti, Preslav Nakov, Salvatore Romeo, and Giuseppe Carenini. 2016. An interactive system for exploring community question answering forums. In Proceedings of the 26th International Conferenc… find
  36. Todor Mihaylov, Daniel Balchev, Yasen Kiprov, Ivan Koychev, and Preslav Nakov. 2017a. Large-scale goodness polarity lexicons for community question answering. In Proceedings of the 40th International Conference on Research and Development in Information Retrieval. Tokyo, Japan, SIGIR ’17. find
  37. Yongshuai Hou, Cong Tan, Xiaolong Wang, Yaoyun Zhang, Jun Xu, and Qingcai Chen. 2015. HITSZ-ICRC: Exploiting classification approach for answer selection in community question answering. In Proceedings of the 9th International Workshop on Semantic Evaluation. Denver, Colorado, USA, SemEval ’15, page… find
  38. Todor Mihaylov, Georgi Georgiev, and Preslav Nakov. 2015a. Finding opinion manipulation trolls in news community forums. In Proceedings of the Nineteenth Conference on Computational Natural Language Learning. Beijing, China, CoNLL ’15, pages 310–314. find
  39. Jiwoon Jeon, W. Bruce Croft, and Joon Ho Lee. 2005. Finding similar questions in large question and answer archives. In Proceedings of the 14th ACM International Conference on Information and Knowledge Management. Bremen, Germany, CIKM ’05, pages 84–90. find
  40. Todor Mihaylov, Ivan Koychev, Georgi Georgiev, and Preslav Nakov. 2015b. Exposing paid opinion manipulation trolls. In Proceedings of the International Conference Recent Advances in Natural Language Processing. Hissar, Bulgaria, RANLP’15, pages 443–450. find
  41. Shafiq Joty, Alberto Barrón-Cedeño, Giovanni Da San Martino, Simone Filice, Lluı́s Màrquez, Alessandro Moschitti, and Preslav Nakov. 2015. Global thread-level inference for comment classification in community question answering. In Proceedings of the 2015 Conference on Empirical Methods in Natura… find
  42. Todor Mihaylov, Tsvetomila Mihaylova, Preslav Nakov, Lluı́s Màrquez, Georgi Georgiev, and Ivan Koychev. 2017b. The dark side of news community forums: Opinion manipulation trolls. Internet Research . find
  43. Shafiq Joty, Lluı́s Màrquez, and Preslav Nakov. 2016. Joint learning with global inference for comment classification in community question answering. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. S… find
  44. Todor Mihaylov and Preslav Nakov. 2016a. Hunting for troll comments in news community forums. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany, ACL ’16, pages 399–405. find
  45. Yuta Koreeda, Takuya Hashito, Yoshiki Niwa, Misa Sato, Toshihiko Yanase, Kenzo Kurotsuchi, and Kohsuke Yanai. 2017. bunji at SemEval-2017 task 3: Combination of neural similarity features and comment plausibility features. In Proceedings of the International Workshop on Semantic Evaluation. Vancouve… find
  46. Todor Mihaylov and Preslav Nakov. 2016b. SemanticZ at SemEval-2016 Task 3: Ranking relevant answers in community question answering using semantic similarity based on fine-tuned word embeddings. In Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego, California, USA, Sem… find
  47. Tao Lei, Hrishikesh Joshi, Regina Barzilay, Tommi S. Jaakkola, Kateryna Tymoshenko, Alessandro Moschitti, and Lluı́s Màrquez. 2016. Semi-supervised question retrieval with gated convolutions. In Proceedings of the 15th Annual Conference of the North American Chapter of the Association for Computati… find
  48. Tsvetomila Mihaylova, Pepa Gencheva, Martin Boyanov, Ivana Yovcheva, Todor Mihaylov, Momchil Hardalov, Yasen Kiprov, Daniel Balchev, Ivan Koychev, Preslav Nakov, Ivelina Nikolova, and Galia Angelova. 2016. SUper Team at SemEval-2016 Task 3: Building a feature-rich system for community question answe… find
  49. Mitra Mohtarami, Yonatan Belinkov, Wei-Ning Hsu, Yu Zhang, Tao Lei, Kfir Bar, Scott Cyphers, and Jim Glass. 2016. SLS at SemEval-2016 Task 3: Neural-based approaches for ranking in community question answering. In Proceedings of the International Workshop on Semantic Evaluation. San Diego, Californi… find
  50. Le Qi, Yu Zhang, and Ting Liu. 2017. SCIR-QA at SemEval-2017 task 3: CNN model based on similar and dissimilar information between keywords for question similarity. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 305–309. find
  51. Alessandro Moschitti, Lluı́s Márquez, Preslav Nakov, Eugene Agichtein, Charles Clarke, and Idan Szpektor. 2016. find
  52. SIGIR 2016 workshop WebQA II: Web question answering beyond factoids. In Proceedings of the 39th International Conference on Research and Development in Information Retrieval. ACM, Pisa, Italy, SIGIR ’16, pages 1251–1252. find
  53. Mohammed R. H. Qwaider, Abed Alhakim Freihat, and Fausto Giunchiglia. 2017. TrentoTeam at SemEval-2017 task 3: An application of Grice Maxims principles in ranking community question answers. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pa… find
  54. Preslav Nakov, Lluı́s Màrquez, and Francisco Guzmán. 2016a. It takes three to tango: Triangulation approach to answer ranking in community question answering. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas, USA, pages 1586–1597. find
  55. Stefan Riezler, Alexander Vasserman, Ioannis Tsochantaridis, Vibhu Mittal, and Yi Liu. 2007. Statistical machine translation for query expansion in answer retrieval. In Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics. Prague, Czech Republic, ACL ’07, pages 464–…
  56. Preslav Nakov, Lluı́s Màrquez, Walid Magdy, Alessandro Moschitti, Jim Glass, and Bilal Randeree. 2015. SemEval-2015 task 3: Answer selection in community question answering. In Proceedings of the International Workshop on Semantic Evaluation. Denver, Colorado, USA, SemEval ’15, pages 269–281. find
  57. Miguel J. Rodrigues and Francisco M Couto. 2017. MoRS at SemEval-2017 task 3: Easy to use SVM in ranking tasks. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 288–292. find
  58. Preslav Nakov, Lluı́s Màrquez, Alessandro Moschitti, Walid Magdy, Hamdy Mubarak, abed Alhakim Freihat, Jim Glass, and Bilal Randeree. 2016b. SemEval-2016 task 3: Community question answering. In Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego, California, USA, SemEv…
  59. Salvatore Romeo, Giovanni Da San Martino, Alberto Barrón-Cedeño, Alessandro Moschitti, Yonatan Belinkov, Wei-Ning Hsu, Yu Zhang, Mitra Mohtarami, and James Glass. 2016. Neural attention for learning to rank questions in community question answering. In Proceedings of the 26th International Confere… find
  60. Titas Nandi, Chris Biemann, Seid Muhie Yimam, Deepak Gupta, Sarah Kohail, Asif Ekbal, and Pushpak Bhattacharyya. 2017. IIT-UHH at SemEval-2017 task 3: Exploring multiple features for community question answering and implicit dialogue identification. In Proceedings of the 11th International Workshop… find
  61. Aliaksei Severyn and Alessandro Moschitti. 2015. Learning to rank short text pairs with convolutional deep neural networks. In Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Santiago, Chile, SIGIR ’15, pages 373–382. find
  62. Massimo Nicosia, Simone Filice, Alberto Barrón-Cedeño, Iman Saleh, Hamdy Mubarak, Wei Gao, Preslav Nakov, Giovanni Da San Martino, Alessandro Moschitti, Kareem Darwish, Lluı́s Màrquez, Shafiq Joty, and Walid Magdy. 2015. QCRI: Answer selection for community question answering -experiments for Ara… find
  63. Radu Soricut and Eric Brill. 2006. Automatic question answering using the web: Beyond the factoid. Inf. Retr. 9(2):191–206. find
  64. Mihai Surdeanu, Massimiliano Ciaramita, and Hugo Zaragoza. 2011. Learning to rank answers to non-factoid questions from web collections. Comput. Linguist. 37(2):351–383. find
  65. Ankur Parikh, Oscar Täckström, Dipanjan Das, and Jakob Uszkoreit. 2016. A decomposable attention model for natural language inference. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas, USA, EMNLP ’16, pages 2249–2255.
  66. Ming Tan, Bing Xiang, and Bowen Zhou. 2015. Lstm-based deep learning models for non-factoid answer selection. arXiv preprint arXiv:1511.04108 . find
  67. Marwan Torki, Maram Hasanain, and Tamer Elsayed. 2017. QU-BIGIR at SemEval-2017 task 3: Using similarity features for Arabic community question Jeffrey Pennington, Richard Socher, and Christopher Manning. 2014. Glove: Global vectors for word Yu Wu, WenZheng Feng, Wei Wu, Ming Zhou, and Zhoujun Li. 2… find
  68. Quan Hung Tran, Vu Tran, Tu Vu, Minh Nguyen, and Son Bao Pham. 2015. JAIST: Combining multiple features for answer selection in community question answering. In Proceedings of the 9th International Workshop on Semantic Evaluation. Denver, Colorado, USA, SemEval ’15, pages 215–219. find
  69. Yunfang Wu and Minghua Zhang. 2016. ICL00 at SemEval-2016 Task 3: Translation-based method for CQA system. In Proceedings of the Workshop on Semantic Evaluation. San Diego, California, USA, SemEval ’16, pages 857–860. find
  70. Kateryna Tymoshenko, Daniele Bonadiman, and Alessandro Moschitti. 2016. Learning to rank non-factoid answers: Comment selection in web forums. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. Indianapolis, Indiana, USA, CIKM ’16, pages 2049–2052. find
  71. Yufei Xie, Maoquan Wang, Jing Ma, Jian Jiang, and Zhao Lu. 2017. EICA team at SemEval-2017 task 3: Semantic and metadata-based features for Community Question Answering. In Proceedings of the International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 293–299. find
  72. Filip S̆aina, Toni Kukurin, Lukrecija Puljić, Mladen Karan, and Jan S̆najder. 2017. TakeLab-QA at SemEval-2017 task 3: Classification experiments for answer retrieval in community QA. In Proceedings of the Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 339–343. find
  73. Xuchen Yao, Benjamin Van Durme, Chris Callison-Burch, and Peter Clark. 2013. Answer extraction as sequence tagging with tree edit distance. In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics. NAACL-HLT ’13, pages 858–867. find
  74. Di Wang and Eric Nyberg. 2015. A long short-term memory model for answer sentence selection in question answering. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Beijing, China, ACL… find
  75. Kai Zhang, Wei Wu, Haocheng Wu, Zhoujun Li, and Ming Zhou. 2014. Question retrieval with high quality answers in community question answering. In Proceedings of the 23rd ACM International Conference on Information and Knowledge Management. Shanghai, China, CIKM ’14, pages 371–380. find
  76. Sheng Zhang, Jiajun Cheng, Hui Wang, Xin Zhang, Pei Li, and Zhaoyun Ding. 2017. FuRongWang at SemEval-2017 task 3: Deep neural networks for selecting relevant answers in community question answering. In Proceedings of the 11th International Workshop on Semantic Evaluation. Vancouver, Canada, SemEval… find
  77. Kai Wang, Zhaoyan Ming, and Tat-Seng Chua. 2009. A syntactic tree matching approach to finding similar questions in community-based QA services. In Proceedings of the 32nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Boston, Massachusetts, USA, SI-GIR ’09,… find
  78. Guangyou Zhou, Li Cai, Jun Zhao, and Kang Liu. 2011. Phrase-based translation model for question retrieval in community question answer archives. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. Portland, Oregon, USA, ACL ’11, pages 653–662. find
  79. Mengqiu Wang and Christopher D. Manning. 2010. Probabilistic tree-edit models with structured latent variables for textual entailment and question answering. In Proceedings of the 23rd International Conference on Computational Linguistics. Beijing, China, COLING ’10, pages 1164–1172. find
  80. Xiaoqiang Zhou, Baotian Hu, Qingcai Chen, Buzhou Tang, and Xiaolong Wang. 2015a. Answer sequence learning with neural networks for answer selection in community question answering. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Jo… find
  81. Mengqiu Wang, Noah A. Smith, and Teruko Mitamura. 2007. What is the Jeopardy model? A quasi-synchronous grammar for QA. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Prague, Czech Republic, EMNLP-CoNLL ’07…
  82. Xiaoqiang Zhou, Baotian Hu, Jiaxin Lin, Yang Xiang, and Xiaolong Wang. 2015b. ICRC-HIT: A deep learning based comment sequence labeling system for answer selection challenge. In Proceedings of the 11th International Workshop on Semantic Evaluation. Denver, Colorado, USA, SemEval ’15, pages 210–214. find
  83. Guoshun Wu, Yixuan Sheng adn Man Lan, and Yuanbin Wu. 2017a. ECNU at SemEval-2017 task 3: Using traditional and deep learning methods to address community question answering task. In Proceedings of the Workshop on Semantic Evaluation. Vancouver, Canada, SemEval ’17, pages 365–369. find
  84. Team ID Team Affiliation Beihang-MSRA Beihang University, Beijing, China; Microsoft Research, Beijing, China (Wu et al., 2017b) bunji Hitachi Ltd., Japan (Koreeda et al., 2017) ECNU East China Normal University, P.R. China; Shanghai Key Laboratory of Multidimensional Information Processing, P.R. find
  85. China (Wu et al., 2017a) EICA East China Normal University, Shanghai, P.R.China (Xie et al., 2017) FuRongWang National University of Defense Technology, P.R. find
  86. China (Zhang et al., 2017) FA3L University of Pisa, Italy (Attardi et al., 2017) The George Washington University, D.C. find
  87. USA GW QA (Almarwani and Diab, 2017) IIT-UHH Indian Institute of Technology Patna, India; University of Hamburg, Germany (Nandi et al., 2017) KeLP University of Roma, Tor Vergata, Italy; Qatar Computing Research Institute, HBKU, Qatar (Filice et al., 2017) MoRS Universidade de Lisboa, Portugal (Rodr… find
  88. China (Qi et al., 2017) SimBow Orange Labs, France (Charlet and Damnati, 2017) SnowMan Harbin Institute of Technology, P.R. China [no paper submitted] SwissAlps Zurich University of Applied Sciences, Switzerland (Deriu and Cieliebak, 2017) TakeLab-QA University of Zagreb, Croatia (S̆aina et al., 201… find
  89. Submission KeLP-primary Beihang-MSRA-primary Beihang-MSRA-contrastive2 Beihang-MSRA-contrastive1 IIT-UHH-primary ECNU-contrastive1 ECNU-primary EICA-contrastive2 bunji-primary EICA-primary EICA-contrastive1 IIT-UHH-contrastive1 SwissAlps-primary SwissAlps-contrastive1 bunji-contrastive1 IIT-UHH-cont… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/nakov-2017-semeval-2017-task-3-community/