Filters








96,507 Hits in 5.1 sec

Recent Trends in Deep Learning Based Open-Domain Textual Question Answering Systems

Zhen Huang, Shiyi Xu, Minghao Hu, Xinyi Wang, Jinyan Qiu, Yongquan Fu, Yuncai Zhao, Yuxing Peng, Changjian Wang
2020 IEEE Access  
INDEX TERMS Open-domain textual question answering, deep learning, machine reading comprehension, information retrieval.  ...  Open-domain textual question answering (QA), which aims to answer questions from large data sources like Wikipedia or the web, has gained wide attention in recent years.  ...  . • SQuAD-open [37] is an open-domain textual question answering dataset based on SQuAD [13] .  ... 
doi:10.1109/access.2020.2988903 fatcat:po4euxfronf3pob52qc2wcgrre

R^3: Reinforced Reader-Ranker for Open-Domain Question Answering [article]

Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerald Tesauro, Bowen Zhou, Jing Jiang
2017 arXiv   pre-print
Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.  ...  an answer to the question.  ...  Then the Ranker and Reader are trained jointly using reinforcement learning to directly optimize the expectation of extracting the groundtruth answer from the retrieved passages.  ... 
arXiv:1709.00023v2 fatcat:t52l2rn2mrbfdinouv5vupof7q

Can Open Domain Question Answering Systems Answer Visual Knowledge Questions? [article]

Jiawen Zhang, Abhijit Mishra, Avinesh P.V.S, Siddharth Patwardhan, Sachin Agarwal
2022 arXiv   pre-print
Using these detected entities, the visual questions can be rewritten so as to be answerable by open domain QA systems.  ...  This allows for the reuse of existing text-based Open Domain Question Answering (QA) Systems for visual question answering.  ...  Using these detected entities, the visual questions can be rewritten so as to be answerable by open domain QA systems.  ... 
arXiv:2202.04306v1 fatcat:ycnfaljzkfcltggmwrzcbjdite

R3: Reinforced Ranker-Reader for Open-Domain Question Answering

Shuohang Wang, Mo Yu, Xiaoxiao Guo, Zhiguo Wang, Tim Klinger, Wei Zhang, Shiyu Chang, Gerry Tesauro, Bowen Zhou, Jing Jiang
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Second, we propose a novel method that jointly trains the Ranker along with an answer-extraction Reader model, based on reinforcement learning.  ...  an answer to the question.  ...  A successful open-domain QA system must be able to effectively retrieve and comprehend one or more knowledge sources to infer a correct answer.  ... 
doi:10.1609/aaai.v32i1.12053 fatcat:m7mrikgvxvg5rccfvn5qzhw3nq

Reinforcement Learning for Improved Low Resource Dialogue Generation

Ana V. González-Garduño
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
The aim is to create a unified approach to dialogue generation inspired by developments in both goal oriented and open ended dialogue systems.  ...  Learning methods for domain adaptation in goal oriented dialogue and 3) Introducing models that can adapt cross lingually.  ...  Currently, we are using this model to train on N number of domains and adapt this model to new domains for which we don't have turn level supervision using Reinforcement Learning.  ... 
doi:10.1609/aaai.v33i01.33019884 fatcat:2a6i6lx7hvav7gzf57vpgnoita

Advances in Natural Language Question Answering: A Review [article]

K.S.D. Ishwari, A.K.R.R.Aneeze, S.Sudheesan, H.J.D.A. Karunaratne, A. Nugaliyadde, Y. Mallawarrachchi
2019 arXiv   pre-print
This paper discusses the successes and challenges in question answering question answering systems and techniques that are used in these challenges.  ...  The dynamic nature of language has profited from the nonlinear learning in deep learning. This has created prominent success and a spike in work on question answering.  ...  Though these systems were successful initiatives to the Question Answering domain they were not without flaws.  ... 
arXiv:1904.05276v1 fatcat:kgnbpaey45fwrloyzj5dzfvile

Answer-guided and Semantic Coherent Question Generation in Open-domain Conversation

Weichao Wang, Shi Feng, Daling Wang, Yifei Zhang
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Generating intriguing question is a key step towards building human-like open-domain chatbots.  ...  First, the coherence score between generated question and answer is used as the reward function in a reinforcement learning framework, to encourage the cases that are consistent with the answer in semantic  ...  Acknowledgements The work was supported by the National Key R&D Program of China under grant 2018YF-B1004700, and National Natural Science Foundation of China (61872074, 61772122).  ... 
doi:10.18653/v1/d19-1511 dblp:conf/emnlp/WangFWZ19 fatcat:mmt6fxhcpngwne2dxmmc4lrsca

Learning strategies for story comprehension

Eugene Grois, David C. Wilkins
2005 Proceedings of the 22nd international conference on Machine learning - ICML '05  
This paper describes the use of machine learning to improve the performance of natural language question answering systems.  ...  We compare our approach to three prior non-learning systems, and evaluate the conditions under which learning is effective.  ...  Acknowledgements We gratefully acknowledge the helpful feedback provided by Dan Roth. This research was supported, in part, by ONR MURI grant N00014-00-1-0660.  ... 
doi:10.1145/1102351.1102384 dblp:conf/icml/GroisW05 fatcat:bfp5funvdvgtzc46ok52c5jhli

SSL-QA: Analysis of Semi-Supervised Learning for QuestionAnswering

Parth Patel, Jignesh Prajapati
2017 IOSR Journal of Computer Engineering  
Open domain natural language question answering (QA) is a process of automatically finding answers to questions searching collections of text files.  ...  In this paper we analyse different intensive researches in semi-supervised learning for question-answering.  ...  from standard transfer learning of a question answering model trained on a large, span-level supervision.  ... 
doi:10.9790/0661-1903051415 fatcat:iv2qx3pejjf7fkt5rsewld7dky

Training a Ranking Function for Open-Domain Question Answering

Phu Mon Htut, Samuel Bowman, Kyunghyun Cho
2018 Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop  
However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question.  ...  Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.  ...  Acknowledgments PMH is funded as an AdeptMind Scholar. This project has benefited from financial support to SB by Google, Tencent Holdings, and Samsung Research.  ... 
doi:10.18653/v1/n18-4017 dblp:conf/naacl/HtutBC18 fatcat:ch5rnw7stjahvheaysebrl7kn4

Open-Domain Neural Conversational Agents: The Step Towards Artificial General Intelligence

Sasa Arsovski, Sze Hui, Adrian David
2018 International Journal of Advanced Computer Science and Applications  
In order to create a conversational agent which is able to pass the Turing Test, numerous research efforts are focused on open-domain dialogue system.  ...  This paper will present latest research in domain of Neural Network reasoning and logical association, sentiment analysis and real-time learning approaches applied to open domain neural conversational  ...  Authors in [30] simultaneously train the model by alternating input data between question answering (QA) and question generation (QG), both in the same model.  ... 
doi:10.14569/ijacsa.2018.090654 fatcat:gs5reut56ze2nbykzoorbq3aou

Training a Ranking Function for Open-Domain Question Answering [article]

Phu Mon Htut, Samuel R. Bowman, Kyunghyun Cho
2018 arXiv   pre-print
However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question.  ...  Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.  ...  Acknowledgments PMH is funded as an AdeptMind Scholar. This project has benefited from financial support to SB by Google, Tencent Holdings, and Samsung Research.  ... 
arXiv:1804.04264v1 fatcat:net73xus5be6hm2ukgpizrtpfu

Recent advances in conversational NLP : Towards the standardization of Chatbot building [article]

Maali Mnasri
2019 arXiv   pre-print
Finally, we present an opinion piece suggesting to orientate the research towards the standardization of dialogue systems building.  ...  In this paper, we try to provide an overview to the current state of the art of dialogue systems, their categories and the different approaches to build them.  ...  To train a dialogue system with reinforcement learning, the chatbot is put in use by the end users to become increasingly efficient throughout the conversations.  ... 
arXiv:1903.09025v1 fatcat:cocknrgvdvguvjykorzmeu5zse

Dialog as a Vehicle for Lifelong Learning [article]

Aishwarya Padmakumar, Raymond J. Mooney
2020 arXiv   pre-print
Dialog systems research has primarily been focused around two main types of applications - task-oriented dialog systems that learn to use clarification to aid in understanding a goal, and open-ended dialog  ...  However, dialog interactions can also be used to obtain various types of knowledge that can be used to improve an underlying language understanding system, or other machine learning systems that the dialog  ...  for an open vocabulary of objects.  ... 
arXiv:2006.14767v1 fatcat:dozixourvfha5ljs3y3hk4yaaq

Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering [article]

Gautier Izacard, Edouard Grave
2021 arXiv   pre-print
Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge.  ...  We obtain state-of-the-art results on the Natural Questions and TriviaQA open benchmarks.  ...  Passage retrieval is an important step in open domain question answering, and is an active area of research to improve QA systems.  ... 
arXiv:2007.01282v2 fatcat:r7ycylnttvc43pm5gwltoggqbu
« Previous Showing results 1 — 15 out of 96,507 results