A. Abacha, P. Ben, and . Zweigenbaum, MEANS: A medical question-answering system combining NLP techniques and semantic Web technologies, Information processing & management 51, vol.5, p.119, 2015.

, The question answering systems: A survey, p.38, 2012.

H. Azad, A. Kumar, and . Deepak, Query expansion techniques for information retrieval: a survey, Information Processing & Management, vol.56, p.40, 2019.

I. Beltagy, A. Cohan, and K. Lo, Scibert: Pretrained contextualized embeddings for scientific text, p.98, 2019.

B. Abacha, C. Asma, D. Shivade, and . Demner-fushman, Overview of the MEDIQA 2019 Shared Task on Textual Inference, Question Entailment and Question Answering, Proceedings of the 18th BioNLP Workshop and Shared Task, p.63, 2019.

J. Berant, A. Chou, R. Frostig, and P. Liang, Semantic parsing on freebase from question-answer pairs, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, p.29, 2013.

J. Bromley, I. Guyon, Y. Lecun, E. Säckinger, and R. Shah, Signature verification using a" siamese" time delay neural network, Advances in neural information processing systems, p.44, 1994.

D. Chen, J. Bolton, and C. Manning, A thorough examination of the cnn/daily mail reading comprehension task, p.47, 2016.

D. Chen, A. Fisch, J. Weston, and A. Bordes, Reading Wikipedia to Answer Open-Domain Questions, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol.1, pp.1870-1879, 2017.

E. Choi, D. Hewlett, and J. Uszkoreit, Coarse-to-fine question answering for long documents, Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics, vol.1, p.55, 2017.

, Proceedings of the Workshop on Machine Reading for Question Answering, p.64, 2018.

J. Chu-carroll, J. Fan, and . Boguraev, Finding needles in the haystack: Search and candidate generation, IBM Journal of Research and Development, vol.56, pp.6-7, 2012.

C. Clark and M. Gardner, Simple and Effective Multi-Paragraph Reading Comprehension, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol.1, p.58, 2018.

R. Collobert, J. Weston, and L. Bottou, Natural language processing (almost) from scratch, Journal of machine learning research, vol.12, issue.6, pp.2493-2537, 2011.

H. Cui, R. Sun, K. Li, M. Kan, and T. Chua, Question answering passage retrieval using dependency relations, Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval, p.42, 2005.

J. Daiber, M. Jakob, C. Hokamp, and P. N. Mendes, Improving efficiency and accuracy in multilingual entity extraction, Proceedings of the 9th International Conference on Semantic Systems. ACM (cit, vol.142, p.134, 2013.

J. Devlin, M. Chang, K. Lee, and K. Toutanova, Bert: Pretraining of deep bidirectional transformers for language understanding, 2018.

B. Dhingra, D. Danish, and D. Rajagopal, Simple and Effective Semi-Supervised Question Answering, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol.2, p.28, 2018.

B. Dhingra, H. Liu, R. Salakhutdinov, and W. W. Cohen, A Comparative Study of Word Embeddings for Reading Comprehension, p.139, 2017.

B. Dhingra, K. Mazaitis, and W. W. Cohen, Quasar: Datasets for question answering by search and reading, vol.55, p.47, 2017.

, Quasar: Datasets for Question Answering by Search and Reading, vol.87, 2017.

D. Dua, Y. Wang, and P. Dasigi, DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs, vol.28, pp.57-59, 2019.

M. Dunn, L. Sagun, and M. Higgins, Searchqa: A new q&a dataset augmented with context from a search engine, vol.55, p.29, 2017.

T. Elsken, J. H. Metzen, and F. Hutter, Neural architecture search: A survey, vol.8, 2018.

W. Fang, J. Zhang, D. Wang, Z. Chen, and M. Li, Entity Disambiguation by Knowledge and Text Jointly Embedding, Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, p.141, 2016.

B. Feng, B. Minwei, . Xiang, R. Michael, L. Glass et al., Applying deep learning to answer selection: A study and an open task, IEEE Workshop on Automatic Speech Recognition and Understanding, p.26, 2015.

A. Ferré, Représentations vectorielles et apprentissage automatique pour l'alignement d'entités textuelles et de concepts d'ontologie : application à la biologie, p.165, 2019.

O. Ferret, B. Grau, and M. Hurault-plantet, Finding an answer based on the recognition of the question focus, p.39, 2001.
URL : https://hal.archives-ouvertes.fr/hal-02458025

D. Ferrucci, E. Brown, and J. Chu-carroll, Building Watson: An overview of the DeepQA project, p.55, 2010.

R. Gaizauskas, K. Humphreys, and ;. Documentaire, A combined IR/NLP approach to question answering against large text collections, Content-Based Multimedia Information Access, vol.2, p.41, 2000.

M. Gleize and B. Grau, A Unified Kernel Approach for Learning Typed Sentence Rewritings, Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, vol.1, p.42, 2015.
URL : https://hal.archives-ouvertes.fr/hal-02281919

, LIMSI-CNRS@ CLEF 2015: Tree Edit Beam Search for Multiple Choice Question Answering, p.46, 2015.

A. Grappy and B. Grau, Answer type validation in question answering systems, RIAO 2010, 9th International Conference, p.119, 2010.
URL : https://hal.archives-ouvertes.fr/hal-02282099

A. Grappy, B. Grau, and M. Falco, Selecting answers to questions from Web documents by a robust validation process, 2011.
URL : https://hal.archives-ouvertes.fr/hal-02282060

B. Grau and A. Ligozat, A Corpus for Hybrid Question Answering Systems, Companion Proceedings of the The Web Conference 2018. WWW '18, p.38, 2018.
URL : https://hal.archives-ouvertes.fr/hal-02284465

. Green, F. Bert, A. K. Wolf, C. Chomsky, and K. Laughery, Baseball: an automatic question-answerer, Papers presented at the May 9-11, p.37, 1961.

M. Habibi, L. Weber, M. Neves, D. L. Wiegandt, and U. Leser, Deep learning with word embeddings improves biomedical named entity recognition, Bioinformatics 33, vol.14, p.120, 2017.

. He, K. Hua, J. Gimpel, and . Lin, Multi-perspective sentence similarity modeling with convolutional neural networks, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, vol.46, p.44, 2015.

M. Heilman and N. Smith, Tree edit models for recognizing textual entailments, paraphrases, and answers to questions, Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, p.42, 2010.

K. Hermann, T. Moritz, E. Kocisky, and . Grefenstette, Teaching machines to read and comprehend, Advances in neural information processing systems, pp.1693-1701, 2015.

U. Hermjakob, Parsing and question classification for question answering, Proceedings of the ACL 2001 workshop on open-domain question answering, 2001.

L. Hirschman, M. Light, E. Breck, and J. Burger, Deep read: A reading comprehension system, Proceedings of the 37th annual meeting of the Association for Computational Linguistics on Computational Linguistics, p.46, 1999.

S. Hosein, D. Andor, and R. Mcdonald, Measuring Domain Portability and ErrorPropagation in Biomedical QA, vol.92, pp.63-65, 2019.

M. Hu, Y. Peng, and Z. Huang, Reinforced mnemonic reader for machine reading comprehension, p.49, 2017.

. Huang, C. Hsin-yuan, Y. Zhu, W. Shen, and . Chen, Fusionnet: Fusing via fully-aware attention with application to machine comprehension, vol.50, p.49, 2017.

R. Jia and P. Liang, Adversarial examples for evaluating reading comprehension systems, p.22, 2017.

M. Joshi, E. Choi, S. Daniel, L. Weld, and . Zettlemoyer, Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension, vol.87, 2017.

C. Jouis, C. Jouis, I. Biskri, J. Ganascia, and M. Roux, Next Generation Search Engines: Advanced Models for Information Retrieval, 2012.
URL : https://hal.archives-ouvertes.fr/hal-01262107

S. Kamath, B. Grau, and Y. Ma, A Study of Word Embeddings for Biomedical Question Answering, SIIM'17 (cit, p.112, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01704570

, A Study of Word Embeddings for Biomedical Question Answering, 4e édition du Symposium sur l'Ingénierie de l'Information Médicale, p.139, 2017.

, Predicting and Integrating Expected Answer Types into a Simple Recurrent Neural Network Model for Answer Sentence Selection, 20th International Conference on Computational Linguistics and Intelligent Text Processing, p.158, 2019.

Y. Kim, Convolutional Neural Networks for Sentence Classification, Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (cit, p.133, 2014.

T. Kobayashi and C. Shyu, Representing clinical questions by semantic type for better classification, AMIA Annual Symposium Proceedings, p.119, 2006.

B. Kolomiyets, M. Oleksandr, and . Moens, A survey on question answering technology from an information retrieval perspective, Information Sciences, vol.181, issue.24, p.119, 2011.

T. Kwiatkowski, J. Palomaki, and O. Rhinehart, Natural questions: a benchmark for question answering research, 2019.

T. Lai, T. Manh, S. Bui, and . Li, A review on deep learning techniques applied to answer selection, Proceedings of the 27th International Conference on Computational Linguistics, pp.2132-2144, 2018.

T. Lavergne, O. Cappé, and F. Yvon, Practical Very Large Scale CRFs, Proceedings the 48th Annual Meeting of the Association for Computational Linguistics (ACL), pp.504-513, 2010.

J. Lee, W. Yoon, and S. Kim, BioBERT: a pre-trained biomedical language representation model for biomedical text mining, vol.63, pp.96-99, 2019.

K. Lee, M. Chang, and K. Toutanova, Latent Retrieval for Weakly Supervised Open Domain Question Answering, 2019.

O. Levy, M. Seo, E. Choi, and L. Zettlemoyer, Zero-Shot Relation Extraction via Reading Comprehension, Proceedings of the 21st Conference on Computational Natural Language Learning, p.58, 2017.

P. Lewis, L. Denoyer, and S. Riedel, Unsupervised Question Answering by Cloze Translation, p.1, 2019.

X. Li and D. Roth, Learning question classifiers, Proceedings of the 19th international conference on Computational linguistics, vol.1, p.40, 2002.

Y. Lin, H. Ji, Z. Liu, and M. Sun, Denoising distantly supervised open-domain question answering, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol.1, pp.1736-1745, 2018.

Y. Liu, M. Ott, and N. Goyal, Roberta: A robustly optimized bert pretraining approach, p.97, 2019.

Z. Luo, M. Yetisgen-yildiz, and C. Weng, Dynamic categorization of clinical research eligibility criteria by hierarchical clustering, Journal of biomedical informatics, vol.44, p.119, 2011.

H. Madabushi, M. Tayyar, and . Lee, High accuracy rule-based question classification using question syntax and semantics, Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers (cit. on pp. 125, vol.127, pp.133-135, 2016.

T. Mikolov, . Chen, J. Corrado, and . Dean, Efficient estimation of word representations in vector space, vol.86, p.85, 2013.

T. Mikolov, E. Grave, P. Bojanowski, C. Puhrsch, and A. Joulin, Advances in Pre-Training Distributed Word Representations, Proceedings of the International Conference on Language Resources and Evaluation (LREC 2018) (cit, p.139, 2018.

T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, Distributed representations of words and phrases and their compositionality, Advances in neural information processing systems, pp.3111-3119, 2013.

G. A. Miller, WordNet: a lexical database for English, Communications of the ACM 38, vol.11, p.40, 1995.

D. Moldovan, S. Harabagiu, and M. Pasca, Lasso: A tool for surfing the answer net, 1999.

R. Moraes, J. F. Valiati, and W. Neto, Document-level sentiment classification: An empirical comparison between SVM and ANN, Expert Systems with Applications 40, vol.2, pp.621-633, 2013.

J. G. Moreno, R. Besançon, and R. Beaumont, Combining word and entity embeddings for entity linking, European Semantic Web Conference, p.141, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01626196

M. Neves and M. Kraus, BioMedLAT corpus: Annotation of the lexical answer type for biomedical questions, Proceedings of the Open Knowledge Base and Question Answering Workshop (OKBQA 2016), vol.165, p.121, 2016.

C. L. Paris, Towards more graceful interaction: a survey of question-answering programs, p.37, 1985.

A. Peñas, E. Hovy, and P. Forner, QA4MRE 2011-2013: Overview of question answering for machine reading evaluation, International Conference of the Cross-Language Evaluation Forum for European Languages, vol.46, p.20, 2013.

F. Peng, R. Weischedel, A. Licuanan, and J. Xu, Combining deep linguistics analysis and surface pattern learning: A hybrid approach to Chinese definitional question answering, Proceedings of the Conference on Human Language Technology and Empirical Methods in Natural Language Processing, p.42, 2005.

J. Pennington, R. Socher, and C. Manning, Glove: Global vectors for word representation, Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (cit. on pp. 70, vol.139, p.133, 2014.

M. E. Peters, W. Ammar, C. Bhagavatula, and R. Power, Semisupervised sequence tagging with bidirectional language models, vol.80, p.51, 2017.

M. Peters, M. Neumann, and M. Iyyer, Deep Contextualized Word Representations, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol.1, p.51, 2018.

, Deep Contextualized Word Representations, Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol.1, p.72, 2018.

A. Petrova, Y. Ma, and G. Tsatsaronis, Formalizing biomedical concepts from textual definitions, J. Biomedical Semantics, vol.6, p.119, 2015.

H. Poon, J. Christensen, and P. Domingos, Machine reading at the university of washington, Proceedings of the NAACL HLT 2010 First International Workshop on Formalisms and Methodology for Learning by Reading. Association for Computational Linguistics, p.46, 2010.

. Punyakanok, D. Vasin, W. Roth, and . Yih, Natural language inference via dependency tree mapping: An application to question answering, p.42, 2004.

D. Radev, W. Fan, H. Qi, H. Wu, and A. Grewal, Probabilistic question answering on the web, Proceedings of the 11th international conference on World Wide Web. ACM, p.39, 2002.

A. Radford and K. Narasimhan, Improving language understanding by generative pre-training, Tim Salimans, and Ilya Sutskever, p.51, 2018.

P. Rajpurkar, R. Jia, and P. Liang, Know What You Don't Know: Unanswerable Questions for SQuAD, vol.28, 2018.

P. Rajpurkar, J. Zhang, K. Lopyrev, and P. Liang, SQuAD: 100,000+ Questions for Machine Comprehension of Text, Proceedings of the, 2016.

, Conference on Empirical Methods in Natural Language Processing, pp.2383-2392

J. Rao, H. He, and J. Lin, Noise-Contrastive Estimation for Answer Selection with Deep Neural Networks, Proceedings of the 25th ACM International on Conference on Information and Knowledge Management. CIKM '16, 2016.

D. Ravichandran and E. Hovy, Learning surface text patterns for a question answering system, Proceedings of the 40th annual meeting on association for computational linguistics, p.42, 2002.

E. Riloff and M. Thelen, Workshop: Reading Comprehension Tests as Evaluation for Computer-Based Language Understanding Systems (cit, ANLP-NAACL, p.46, 2000.

O. Russakovsky, J. Deng, and H. Su, ImageNet Large Scale Visual Recognition Challenge, International Journal of Computer Vision, vol.115, p.80, 2015.

V. Sanh, L. Debut, J. Chaumond, and T. Wolf, DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter, p.97, 2019.

C. Santos, M. Dos, B. Tan, B. Xiang, and . Zhou, Attentive pooling networks, p.45, 2016.

F. Schulze, R. Schüler, and T. Draeger, Hpi question answering system in bioasq, Proceedings of the Fourth BioASQ workshop, p.62, 2016.

. Bibliography,

M. Seo, A. Kembhavi, A. Farhadi, and H. Hajishirzi, Bidirectional attention flow for machine comprehension, 2016.

A. Severyn and A. Moschitti, Automatic feature engineering for answer selection and extraction, Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp.458-467, 2013.

, Learning to rank short text pairs with convolutional deep neural networks, Proceedings of the 38th international ACM SIGIR conference on research and development in information retrieval, p.44, 2015.

Y. Shen, P. Huang, J. Gao, and W. Chen, Reasonet: Learning to stop reading in machine comprehension, Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, p.49, 2017.

E. Sherkat and E. E. Milios, Vector embedding of wikipedia concepts and entities, International Conference on Applications of Natural Language to Information Systems, p.139, 2017.

. Shih, M. Cheng-wei, T. Day, and . Tsai, ASQA: Academia sinica question answering system for NTCIR-5 CLQA, p.42, 2005.

A. Singh, Entity based q&a retrieval, Proceedings of the 2012 Joint conference on empirical methods in natural language processing and computational natural language learning, p.54, 2012.

R. Socher, J. Bauer, and C. D. Manning, Parsing with compositional vector grammars, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, vol.1, pp.455-465, 2013.

P. Stenetorp, S. Pyysalo, and G. Topi?, BRAT: a web-based tool for NLP-assisted text annotation, Proceedings of the Demonstrations at the 13th Conference of the European Chapter of the Association for Computational Linguistics, p.108, 2012.

S. Stoyanchev, Y. C. Song, and W. Lahti, Exact phrases in information retrieval for question answering, Coling 2008: Proceedings of the 2nd workshop on Information Retrieval for Question Answering, p.41, 2008.

A. Talmor and J. Berant, MultiQA: An Empirical Investigation of Generalization and Transfer in Reading Comprehension, Proceedings of the 57th Conference of the Association for Computational Linguistics, pp.4911-4921, 2019.

M. Tan, B. Cicero-dos-santos, B. Xiang, and . Zhou, Lstm-based deep learning models for non-factoid answer selection, p.45, 2015.

T. Madabushi, M. Harish, J. Lee, and . Barnden, Integrating Question Classification and Deep Learning for improved Answer Selection, Proceedings of the 27th International Conference on Computational Linguistics, vol.46, pp.132-136, 2018.

G. Tsatsaronis, G. Balikas, and P. Malakasiotis, An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition, BMC Bioinformatics, vol.16, issue.1, p.138, 2015.
URL : https://hal.archives-ouvertes.fr/hal-01156600

K. Tymoshenko and A. Moschitti, Cross-Pair Text Representations for Answer Sentence Selection, Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, p.136, 2018.

A. Vaswani, N. Shazeer, and N. Parmar, Attention is all you need, Advances in neural information processing systems, pp.5998-6008, 2017.

O. Vinyals, M. Fortunato, and N. Jaitly, Pointer networks, Advances in Neural Information Processing Systems, p.49, 2015.

E. M. Voorhees, The TREC question answering track, Natural Language Engineering, p.29, 2001.

, The evaluation of question answering systems: Lessons learned from the TREC QA track, Question Answering: Strategy and Resources Workshop Program, p.60, 2002.

M. Wang and C. D. Manning, Probabilistic tree-edit models with structured latent variables for textual entailment and question answering, Proceedings of the 23rd International Conference on Computational Linguistics, p.42, 2010.

M. Wang, N. A. Smith, and T. Mitamura, What is the Jeopardy model? A quasi-synchronous grammar for QA, Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp.22-32, 2007.

S. Wang and J. Jiang, Machine comprehension using match-lstm and answer pointer, p.49, 2016.

S. Wang, M. Yu, and X. Guo, R 3: Reinforced ranker-reader for open-domain question answering, Thirty-Second AAAI Conference on Artificial Intelligence, vol.55, p.29, 2018.

S. Wang, M. Yu, and J. Jiang, Evidence aggregation for answer reranking in open-domain question answering, p.55, 2017.

D. Weissenborn, G. Wiese, and L. Seiffe, Making neural qa as simple as possible but not simpler, Proceedings of the 21st Conference on Computational Natural Language Learning, vol.119, p.49, 2017.

G. Wiese, D. Weissenborn, and M. Neves, Neural Domain Adaptation for Biomedical Question Answering, Proceedings of the 21st Conference on Computational Natural Language Learning, pp.281-289, 2017.

, Neural Domain Adaptation for Biomedical Question Answering, Proceedings of the 21st Conference on Computational Natural Language Learning, pp.281-289, 2017.

. Bibliography,

G. Wiese, D. Weissenborn, and M. Neves, Neural Question Answering at BioASQ 5B, vol.111, pp.113-115, 2017.

T. Wolf, L. Debut, and V. Sanh, Transformers: State-of-the-art Natural Language Processing, p.73, 2019.

W. A. Woods, Progress in natural language understanding: an application to lunar geology, Proceedings of the, p.37, 1973.

C. Xiong, V. Zhong, and R. Socher, Dynamic coattention networks for question answering, p.49, 2016.

I. Yamada, H. Shindo, H. Takeda, and Y. Takefuji, Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation, Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning, 2016.

G. Berlin, , p.141

Y. Yang, W. Yih, and C. Meek, Wikiqa: A challenge dataset for open-domain question answering, Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp.2013-2018, 2015.

Z. Yang, Z. Dai, and Y. Yang, XLNet: Generalized Autoregressive Pretraining for Language Understanding, p.97, 2019.

Z. Yang, P. Qi, and S. Zhang, Hotpotqa: A dataset for diverse, explainable multi-hop question answering, 2018.

Z. Yang, Y. Zhou, and E. Nyberg, Learning to answer biomedical questions: Oaqa at bioasq 4b, Proceedings of the Fourth BioASQ workshop, pp.23-37, 2016.

X. Yao, B. Van-durme, C. Callison-burch, and P. Clark, Answer Extraction as Sequence Tagging with Tree Edit Distance, Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol.158, p.157, 2013.

, Answer extraction as sequence tagging with tree edit distance, Proceedings of the 2013 conference of the North American chapter of the association for computational linguistics: human language technologies, p.42, 2013.

W. Yih, M. Chang, C. Meek, and A. Pastusiak, Question answering using enhanced lexical semantic models, Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, vol.1, p.42, 2013.

W. Yin, H. Schütze, B. Xiang, and B. Zhou, Abcnn: Attentionbased convolutional neural network for modeling sentence pairs, Transactions of the Association for Computational Linguistics, vol.4, p.44, 2016.

W. Yoon, J. Lee, D. Kim, M. Jeong, and J. Kang, Pretrained Language Model for Biomedical Question Answering, 2019.

A. Yu, D. Wei, M. Dohan, and . Luong, Qanet: Combining local convolution with global self-attention for reading comprehension, vol.72, p.50, 2018.

L. Yu, K. M. Hermann, P. Blunsom, and S. Pulman, Deep learning for answer sentence selection, p.44, 2014.

D. Zhang and W. Sun-lee, Question classification using support vector machines, Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval. ACM, p.40, 2003.

, 3 1.2 Deep learning QA pipeline (only the modules highlighted in red are used, p.5

. .. .-;-zhilin-yang and . Qi, A traditional IR or NLP based question answering pipeline

, Question Answering pipeline as defined by, p.38, 2012.

. Moldovan, 1999) (left) and (Li and Roth, 2002) (right), Hierarchical question types taxonomy by

. Lai, An overview of deep learning methods applied for Answer Sentence Selection presented by, 2018.

. Huang, Summary of several models using an attention mechanism for Reading Comprehension. Figure by, p.50, 2017.

B. Comparing and . Devlin, , p.51, 2018.

. Devlin, Overall process of pre-training and fine tuning BERT for different NLP tasks by, 2018.

, Overall DeepQA architecture of the IBM Watson QA system, p.56

. Dua, 2019) with different types of reasoning required for the QA in DROP dataset, Table presented by

F. Chen, DRQA model by, p.69, 2017.

. Detailed, . .. Drqa, and . Devlin, 70 4.3 BERT model modified for several NLP tasks by, p.72, 2018.

Y. Lin, Left) and BIDAF model by (Seo et al., 2016) (Right), OpenQA model by, 2017.

. .. , Right: PSPR -Paragraph Selector and Paragraph Reader model (Open QA task), p.89

, BERT model training process from Language modelling task to BIOASQ QA task

. Lai, 27 2.3 BIOASQ datasets used in all our experiments along with their splits. The numbers represent number of questions. It is a small scale expert annotated QA dataset, Answer Sentence Selection Datasets. #Questions -Number of questions. #QA Pairs -Number of Question-Answer pairs. Statistics presented by, 2015.

. .. , 81 4.2 Results reporting the importance of Pre-Training and Fine-Tuning a model, top 5) and MRR is the Mean Reciprocal Rank for the correct answer in Top-5 answers. No-Pre is for No-Pretraining on open domain, No-Fine is for No-Finetuning on biomedical domain and Pre+Fine is for Pretraining and Finetuning on open domain and biomedical domain

, Accuracy (top 5) on 4B test with different Embeddings: |V|= vocab

). .. Chen and . Fisch, 2019) who average the best scores from each batch (possibly from multiple different models). Results from BIOASQ 4b, 5b and 6b test sets. 7b test set cannot be evaluated yet due to lack of gold standard answers, Comparision of Word2vec models on 4B Test set (Testset, 2017.

, 132 5.10 Statistics of datasets with plain and EAT annotated questions. '#' refers to "Number of, Three methods for replacing entities along with an example from TrecQA dataset, vol.135

W. Trecqa and S. Datasets, 136 5.12 Results reported on TrecQA, SQUAD-Sent and WikiQA datasets using RNN-Similarity model trained only on EAT annotated questions, p.137

, Number of questions with at least one entity as answer, SQUAD dataset140

, Average number of entities in the SQUAD dataset paragraphs, p.140

, Number of questions in SQUAD dataset official vs pre-processed, p.143

, Whole SQUAD dataset system performance with dev set of 10570 questions. EW-EMB is the entity+word embeddings, p.143

, Entity QA system performance on pre-processed SQUAD dev set of 2705 questions. The same EW-Emb space does not perform well when used on only word (W) representations, Glove performs the best on only words (W) representations with comparable results on Fast text models, p.143

, Experiments on QUASAR-T dataset using different algorithms with best hyper parameters with all features Single, Collective and Semantic features from above. The best K value was found to be 3 on this dataset, p.150

, 151 5.20 Experiments on Feature ablation and importance of features. Computing decrease in performance when certain features are removed from the input, Experiments on choosing K value for Top-K predictions using Adaboost algorithm with all features mentioned above on QUASAR-T dataset, p.153

, 153 5.23 Results on SQUAD variant dev datasets in Open Domain Question Answering and Reading Comprehension settings, p.155

, Results on using TrecQA dataset for OpenQA task