Abstract
In this article, we propose a unified deep neural network framework for multilingual question answering (QA). The proposed network deals with the multilingual questions and answers snippets. The input to the network is a pair of factoid question and snippet in the multilingual environment (English and Hindi), and output is the relevant answer from the snippet. We begin by generating the snippet using a graph-based language-independent algorithm, which exploits the lexico-semantic similarity between the sentences. The soft alignment of the question words from the English and Hindi languages has been used to learn the shared representation of the question. The learned shared representation of question and attention-based snippet representation are passed as an input to the answer extraction layer of the network, which extracts the answer span from the snippet. Evaluation on a standard multilingual QA dataset shows the state-of-the-art performance with 39.44 Exact Match (EM) and 44.97 F1 values. Similarly, we achieve the performance of 50.11 Exact Match (EM) and 53.77 F1 values on Translated SQuAD dataset.
- Galen Andrew, Raman Arora, Jeff Bilmes, and Karen Livescu. 2013. Deep canonical correlation analysis. In Proceedings of the International Conference on Machine Learning. 1247--1255.Google Scholar
Digital Library
- Sarath Chandar A. P., Stanislas Lauly, Hugo Larochelle, Mitesh Khapra, Balaraman Ravindran, Vikas C. Raykar, and Amrita Saha. 2014. An autoencoder approach to learning bilingual word representations. In Proceedings of the Conference on Advances in Neural Information Processing Systems. 1853--1861.Google Scholar
- Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov. 2017. Enriching word vectors with subword information. Trans. Assoc. Comput. Ling. 5 (2017), 135--146. DOI:https://doi.org/10.1162/tacl_a_00051.Google Scholar
Cross Ref
- Antoine Bordes, Sumit Chopra, and Jason Weston. 2014. Question answering with subgraph embeddings. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP’14). Association for Computational Linguistics, 615--620. Retrieved from: http://www.aclweb.org/anthology/D14-1067.Google Scholar
Cross Ref
- Mitchell Bowden, Marian Olteanu, Pasin Suriyentrakorn, Thomas d’Silva, and Dan Moldovan. 2007. Multilingual question answering through intermediate translation: LCC’s PowerAnswer at QA@ CLEF 2007. In Proceedings of the Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 273--283.Google Scholar
- Junyoung Chung, Caglar Gulcehre, Kyunghyun Cho, and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. In Proceedings of the NIPS Workshop on Deep Learning.Google Scholar
- Arpita Das, Harish Yenala, Manoj Chinnakotla, and Manish Shrivastava. 2016. Together we stand: Siamese networks for similar question retrieval. In Proceedings of the 54th Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, 378--387. DOI:https://doi.org/10.18653/v1/P16-1036Google Scholar
Cross Ref
- Rajarshi Das, Shehzaad Dhuliawala, Manzil Zaheer, and Andrew McCallum. 2019. Multi-step retriever-reader interaction for scalable open-domain question answering. In Proceedings of the International Conference on Learning Representations. Retrieved from: https://openreview.net/forum?id=HkfPSh05K7.Google Scholar
- Asif Ekbal, Deepak Gupta, Surabhi Kumari, and Pushpak Bhattacharyya. 2018. MMQA: A multi-domain multi-lingual question-answering framework for English and Hindi. In Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC’18) (7-12). European Language Resources Association (ELRA).Google Scholar
- Pamela Forner, Anselmo Peñas, Eneko Agirre, Iñaki Alegria, Corina Forăscu, Nicolas Moreau, Petya Osenova, Prokopis Prokopidis, Paulo Rocha, Bogdan Sacaleanu et al. 2008. Overview of the CLEF 2008 multilingual question answering track. In Proceedings of the Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 262--295.Google Scholar
- Jerome H. Friedman. 2001. Greedy function approximation: A gradient boosting machine. Ann. Stat. 29, 5 (2001), 1189--1232.Google Scholar
Cross Ref
- María Dolores García Santiago and María Dolores Olvera-Lobo. 2010. Automatic web translators as part of a multilingual question-answering (QA) system: Translation of questions. Transl. J. 14, 1 (2010).Google Scholar
- Danilo Giampiccolo, Pamela Forner, Jesús Herrera, Anselmo Peñas, Christelle Ayache, Corina Forascu, Valentin Jijkoun, Petya Osenova, Paulo Rocha, Bogdan Sacaleanu et al. 2007. Overview of the CLEF 2007 multilingual question answering track. In Proceedings of the Workshop of the Cross-Language Evaluation Forum for European Languages. Springer, 200--236.Google Scholar
- Deepak Gupta, Pabitra Lenka, Asif Ekbal, and Pushpak Bhattacharyya. 2018a. Uncovering code-mixed challenges: A framework for linguistically driven question generation and neural-based question answering. In Proceedings of the 22nd Conference on Computational Natural Language Learning. Association for Computational Linguistics, 119--130. DOI:https://doi.org/10.18653/v1/K18-1012Google Scholar
Cross Ref
- Deepak Gupta, Rajkumar Pujari, Asif Ekbal, Pushpak Bhattacharyya, Anutosh Maitra, Tom Jain, and Shubhashis Sengupta. 2018. Can taxonomy help? Improving semantic question matching using question taxonomy. In Proceedings of the 27th International Conference on Computational Linguistics. Association for Computational Linguistics, , 499--513. Retrieved from: https://www.aclweb.org/anthology/C18-1042.Google Scholar
- David R. Hardoon, Sandor Szedmak, and John Shawe-Taylor. 2004. Canonical correlation analysis: An overview with application to learning methods. Neural Comput. 16, 12 (2004), 2639--2664.Google Scholar
Digital Library
- Xiaodong He and David Golub. 2016. Character-level question answering with attention. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 1598--1607. Retrieved from: https://aclweb.org/anthology/D16-1166.Google Scholar
Cross Ref
- Minghao Hu, Yuxing Peng, Zhen Huang, Xipeng Qiu, Furu Wei, and Ming Zhou. 2018. Reinforced mnemonic reader for machine reading comprehension. In Proceedings of the 27th International Joint Conference on Artificial Intelligence (IJCAI’18). Retrieved from: http://www.ijcai.org/proceedings/2018/.Google Scholar
Digital Library
- Shafiq Joty, Preslav Nakov, Lluís Màrquez, and Israa Jaradat. 2017. Cross-language learning with adversarial neural networks. In Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL’17). 226--237.Google Scholar
Cross Ref
- Praveen Kumar, Shrikant Kashyap, Ankush Mittal, and Sumit Gupta. 2005. A Hindi question answering system for E-learning documents. In Proceedings of the 3rd International Conference on Intelligent Sensing and Information Processing (ICISIP’05). IEEE, 80--85.Google Scholar
Digital Library
- Xin Li and Dan Roth. 2002. Learning question classifiers. In Proceedings of the 19th International Conference on Computational Linguistics, (COLING’02). Association for Computational Linguistics, 1--7.Google Scholar
Digital Library
- Anutosh Maitra, Shubhashis Sengupta, Abhisek Mukhopadhyay, Deepak Gupta, Rajkumar Pujari, Pushpak Bhattacharya, Asif Ekbal, and Tom Geo Jain. 2018. Semantic question matching in data constrained environment. In Text, Speech, and Dialogue, Petr Sojka, Aleš Horák, Ivan Kopeček, and Karel Pala (Eds.). Springer International Publishing, Cham, 267--276.Google Scholar
- Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The Stanford CoreNLP natural language processing toolkit. In Proceedings of 52nd Meeting of the Association for Computational Linguistics: System Demonstrations. 55--60.Google Scholar
Cross Ref
- Bernardo Magnini Matteo, Matteo Negri, Roberto Prevete, and Hristo Tanev. 2001. Multilingual question/answering: The DIOGENE system. In Proceedings of the 10th Text Retrieval Conference.Google Scholar
- Donald Metzler and W. Bruce Croft. 2007. Linear feature-based models for information retrieval. Inf. Retr. 10, 3 (June 2007), 257--274. DOI:https://doi.org/10.1007/s10791-006-9019-zGoogle Scholar
Digital Library
- María-Dolores Olvera-Lobo and Juncal Gutiérrez-Artacho. 2011. Multilingual Question-Answering System in Biomedical Domain on the Web: An Evaluation. Springer Berlin, 83--88. DOI:https://doi.org/10.1007/978-3-642-23708-9_10Google Scholar
- Jahna Otterbacher, Gunes Erkan, and Dragomir R. Radev. 2009. Biased LexRank: Passage retrieval using random walks with question-based priors. Inform. Proc. Manag. 45, 1 (2009), 42--54.Google Scholar
Digital Library
- Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. BLEU: A method for automatic evaluation of machine translation. In Proceedings of the 40th Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 311--318.Google Scholar
- Pranav Rajpurkar, Jian Zhang, Konstantin Lopyrev, and Percy Liang. 2016. SQuAD: 100,000+ questions for machine comprehension of text. In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2383--2392. DOI:https://doi.org/10.18653/v1/D16-1264Google Scholar
Cross Ref
- Tim Rocktäschel, Edward Grefenstette, Karl Moritz Hermann, Tomas Kocisky, and Phil Blunsom. 2016. Reasoning about entailment with neural attention. In Proceedings of the International Conference on Learning Representations (ICLR’16).Google Scholar
- Shriya Sahu, Nandkishor Vasnik, and Devshri Roy. 2012. Prashnottar: A Hindi question answering system. Int. J. Comput. Sci. Inform. Technol. 4, 2 (2012), 149.Google Scholar
Cross Ref
- Satoshi Sekine and Ralph Grishman. 2003. Hindi-English cross-lingual question-answering system. ACM Tran. Asian Lang. Inform. Proc. 2, 3 (2003), 181--192.Google Scholar
Digital Library
- Minjoon Seo, Aniruddha Kembhavi, Ali Farhadi, and Hananneh Hajishirzi. 2017. Bidirectional attention flow for machine comprehension. In Proceedings of the International Conference on Learning Representations.Google Scholar
- Samuel L. Smith, David H. P. Turban, Steven Hamblin, and Nils Y. Hammerla. 2017. Offline bilingual word vectors, orthogonal transformations, and the inverted softmax. In Proceedings of the International Conference on Learning Representations.Google Scholar
- Daniil Sorokin and Iryna Gurevych. 2017. End-to-end representation learning for question answering with weak supervision. In Proceedings of the Semantic Web Evaluation Challenge. Springer, 70--83.Google Scholar
Cross Ref
- Shalini Stalin, Rajeev Pandey, and Raju Barskar. 2012. Web based application for Hindi question answering system. Int. J. Electron. Comput. Sci. Eng. 2, 1 (2012), 72--78.Google Scholar
- Sai Praneeth Suggu, Kushwanth Naga Goutham, Manoj K. Chinnakotla, and Manish Shrivastava. 2016. Hand in glove: Deep feature fusion network architectures for answer quality prediction in community question answering. In Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers. The COLING 2016 Organizing Committee, 1429--1440. Retrieved from: https://www.aclweb.org/anthology/C16-1135.Google Scholar
- Ilya Sutskever, Oriol Vinyals, and Quoc V. Le. 2014. Sequence to sequence learning with neural networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems 27, Z. Ghahramani, M. Welling, C. Cortes, N. D. Lawrence, and K. Q. Weinberger (Eds.). Curran Associates, Inc., 3104--3112. Retrieved from: http://papers.nips.cc/paper/5346-sequence-to-sequence-learning-with-neural-networks.pdf.Google Scholar
- Chuanqi Tan, Furu Wei, Nan Yang, Bowen Du, Weifeng Lv, and Ming Zhou. 2018. S-Net: From answer extraction to answer synthesis for machine reading comprehension. In Proceedings of the AAAI Conference on Artificial Intelligence (AAAI’18).Google Scholar
- Ming Tan, Cicero dos Santos, Bing Xiang, and Bowen Zhou. 2015. LSTM-based deep learning models for non-factoid answer selection. Retrieved from: arXiv preprint arXiv:1511.04108 (2015).Google Scholar
- Ferhan Ture and Oliver Jojic. 2017. No need to pay attention: Simple recurrent neural networks work! In Proceedings of the Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2866--2872. Retrieved from: https://www.aclweb.org/anthology/D17-1307.Google Scholar
- Kateryna Tymoshenko and Alessandro Moschitti. 2015. Assessing the impact of syntactic and semantic structures for answer passages reranking. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. ACM, 1451--1460.Google Scholar
Digital Library
- Oriol Vinyals, Meire Fortunato, and Navdeep Jaitly. 2015. Pointer networks. In Proceedings of the Conference on Advances in Neural Information Processing Systems 28, C. Cortes, N. D. Lawrence, D. D. Lee, M. Sugiyama, and R. Garnett (Eds.). Curran Associates, Inc., 2692--2700. Retrieved from: http://papers.nips.cc/paper/5866-pointer-networks.pdf.Google Scholar
- Shuohang Wang and Jing Jiang. 2017. Machine comprehension using match-LSTM and answer pointer. In Proceedings of the International Conference on Learning Representations (ICLR’17).Google Scholar
- Wenhui Wang, Nan Yang, Furu Wei, Baobao Chang, and Ming Zhou. 2017. Gated self-matching networks for reading comprehension and question answering. In Proceedings of the 55th Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Vol. 1. 189--198.Google Scholar
Cross Ref
- Qiang Wu, Christopher J. C. Burges, Krysta M. Svore, and Jianfeng Gao. 2010. Adapting boosting for information retrieval measures. Inform. Retr. 13, 3 (2010), 254--270.Google Scholar
Digital Library
- Liu Yang, Qingyao Ai, Jiafeng Guo, and W. Bruce Croft. 2016a. aNMM: Ranking short answer texts with attention-based neural matching model. In Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. ACM, 287--296.Google Scholar
- Liu Yang, Qingyao Ai, Damiano Spina, Ruey-Cheng Chen, Liang Pang, W. Bruce Croft, Jiafeng Guo, and Falk Scholer. 2016b. Beyond factoid QA: Effective methods for non-factoid answer sentence retrieval. In Proceedings of the European Conference on Information Retrieval. Springer, 115--128.Google Scholar
Cross Ref
- Dawei Yin, Yuening Hu, Jiliang Tang, Tim Daly, Mianwei Zhou, Hua Ouyang, Jianhui Chen, Changsung Kang, Hongbo Deng, Chikashi Nobata, Jean-Marc Langlois, and Yi Chang. 2016. Ranking relevance in Yahoo search. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’16). ACM, New York, NY, 323--332. DOI:https://doi.org/10.1145/2939672.2939677.Google Scholar
Digital Library
- Adams Wei Yu, David Dohan, Thang Luong, Rui Zhao, Kai Chen, and Quoc Le. 2018. QANet: Combining local convolution with global self-attention for reading comprehension. In Proceedings of the International Conference on Learning Representations (ICLR’18). Retrieved from: https://openreview.net/pdf?id=B14TlG-RW.Google Scholar
- Matthew D. Zeiler. 2012. ADADELTA: An adaptive learning rate method. Retrieved from: arXiv preprint arXiv:1212.5701 (2012).Google Scholar
Index Terms
A Deep Neural Network Framework for English Hindi Question Answering
Recommendations
Hindi-english cross-lingual question-answering system
We developed a cross-lingual, question-answering (CLQA) system for Hindi and English. It accepts questions in English, finds candidate answers in Hindi newspapers, and translates the answer candidates into English along with the context surrounding each ...
A Neural Framework for English-Hindi Cross-Lingual Natural Language Inference
Neural Information ProcessingAbstractRecognizing Textual Entailment (RTE) between two pieces of texts is a very crucial problem in Natural Language Processing (NLP), and it adds further challenges when involving two different languages, i.e. in cross-lingual scenario. The paucity of ...
Bilingual Question Answering Using CINDI_QA at [email protected] 2007
Advances in Multilingual and Multimodal Information RetrievalThis article presents the first participation of the CINDI group in the Multiple Language Question Answering Cross Language Evaluation Forum ([email protected]). We participated in a track using French as source language and English as target language. CINDI_QA ...






Comments