Filters








419,730 Hits in 6.6 sec

Challenges in Generalization in Open Domain Question Answering [article]

Linqing Liu, Patrick Lewis, Sebastian Riedel, Pontus Stenetorp
2022 arXiv   pre-print
Recent work on Open Domain Question Answering has shown that there is a large discrepancy in model performance between novel test questions and those that largely overlap with training questions.  ...  However, it is unclear which aspects of novel questions make them challenging.  ...  Open-domain question answering (ODQA), which aims to answer factoid questions without any given context, is a task that has been receiving increasing attention in the community (Chen et al., 2017; Karpukhin  ... 
arXiv:2109.01156v3 fatcat:ijma4hbgxnc2pod6mmnpl7bxuq

Question Answering System, Approaches and Techniques: A Review

Ajitkumar M., Khillare S.A., C. Namrata
2016 International Journal of Computer Applications  
Question answering is a specialized area in the field of information retrieval Text Processing.  ...  Question Answering system has many application based on source of answering like extracting information from document, language learning, online examination etc.  ...  There are two types of question answering system i.e. open domain and closed domain.  ... 
doi:10.5120/ijca2016909587 fatcat:ru2papuclfcbdpyjzxnioptqu4

ConvAI3: Generating Clarifying Questions for Open-Domain Dialogue Systems (ClariQ) [article]

Mohammad Aliannejadi and Julia Kiseleva and Aleksandr Chuklin and Jeff Dalton and Mikhail Burtsev
2020 arXiv   pre-print
This document presents a detailed description of the challenge on clarifying questions for dialogue systems (ClariQ).  ...  Participants are asked to rank clarifying questions in an information-seeking conversations.  ...  Thanks to the crowd workers for their invaluable help in annotating ClariQ.  ... 
arXiv:2009.11352v1 fatcat:tm6joyjezndzjn7idtyx5fjxma

Improving Question Answering with External Knowledge [article]

Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu
2019 arXiv   pre-print
The first enriches the original subject-area reference corpus with relevant text snippets extracted from an open-domain resource (i.e., Wikipedia) that cover potentially ambiguous concepts in the question  ...  We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.  ...  First, we identify concepts in question and answer options and link these potentially ambiguous concepts to an open-domain resource that provides unstructured background information relevant to the concepts  ... 
arXiv:1902.00993v3 fatcat:xkbv6vcjhfesbghro7xcd4lnsu

Improving Subject-Area Question Answering with External Knowledge

Xiaoman Pan, Kai Sun, Dian Yu, Jianshu Chen, Heng Ji, Claire Cardie, Dong Yu
2019 Proceedings of the 2nd Workshop on Machine Reading for Question Answering  
The first enriches the original subject-area reference corpus with relevant text snippets extracted from an open-domain resource (i.e., Wikipedia) that cover potentially ambiguous concepts in the question  ...  We focus on multiple-choice question answering (QA) tasks in subject areas such as science, where we require both broad background knowledge and the facts from the given subject-area reference corpus.  ...  First, we identify concepts in question and answer options and link these potentially ambiguous concepts to an open-domain resource that provides unstructured background information relevant to the concepts  ... 
doi:10.18653/v1/d19-5804 dblp:conf/acl-mrqa/PanSYCJCY19 fatcat:uwgvrzhrfzgivaoyxd63dsig3q

Answering Open-Domain Questions of Varying Reasoning Steps from Text [article]

Peng Qi, Haejun Lee, Oghenetegiri "TG" Sido, Christopher D. Manning
2021 arXiv   pre-print
We develop a unified system to answer directly from text open-domain questions that may require a varying number of retrieval steps.  ...  Instead, we design a system that can answer open-domain questions on any text collection without prior knowledge of reasoning complexity.  ...  This research is funded in part by Samsung Electronics Co., Ltd. and in part by the SAIL-JD Research Initiative.  ... 
arXiv:2010.12527v4 fatcat:2qus2pngmfghxentwwx3stddfq

PathVQA: 30000+ Questions for Medical Visual Question Answering [article]

Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, Pengtao Xie
2020 arXiv   pre-print
Different from creating general-domain VQA datasets where the images are widely accessible and there are many crowdsourcing workers available and capable of generating question-answer pairs, developing  ...  We develop a semi-automated pipeline to extract pathology images and captions from textbooks and generate question-answer pairs from captions using natural language processing.  ...  Table 1 : 1 Comparison of VQA datasets Domain # images # QA pairs Answer type DAQUAR General 1,449 12,468 Open VQA General 204K 614K Open/MC VQA v2 General 204K 1.1M Open/MC COCO-QA General  ... 
arXiv:2003.10286v1 fatcat:xvi4axyezrcqvgdswynhjd5m64

Retrieval-guided Counterfactual Generation for QA [article]

Bhargavi Paranjape, Matthew Lamm, Ian Tenney
2022 arXiv   pre-print
Data augmentation with RGF counterfactuals improves performance on out-of-domain and challenging evaluation sets over and above existing methods, in both the reading comprehension and open-domain QA settings  ...  Using an open-domain QA framework and question generation model trained on original task data, we create counterfactuals that are fluent, semantically diverse, and automatically labeled.  ...  Open-domain Question Answering In this setting, only the question is provided as input.  ... 
arXiv:2110.07596v2 fatcat:upw2ly4dhjeehb4rndukmuupuy

Question Answering Systems: A Review on Present Developments, Challenges and Trends

Lorena Kodra, Elinda Kajo
2017 International Journal of Advanced Computer Science and Applications  
trends of the research being done in the area of question answering.  ...  Question Answering Systems (QAS) are becoming a model for the future of web search. In this paper we present a study of the latest research in this area.  ...  The greatest part of the systems we studied is open domain with a ratio of 117 open domain to 12 closed domain QAS, translating to a percentage of 90.6% open domain to 9.4% closed domain. of QAS: 1) System  ... 
doi:10.14569/ijacsa.2017.080931 fatcat:mehxnmfnm5g63nup6r7mmafq44

Addressing Issues of Cross-Linguality in Open-Retrieval Question Answering Systems For Emergent Domains [article]

Alon Albalak, Sharon Levy, William Yang Wang
2022 arXiv   pre-print
Open-retrieval question answering systems are generally trained and tested on large datasets in well-established domains.  ...  In this paper, we demonstrate a cross-lingual open-retrieval question answering system for the emergent domain of COVID-19.  ...  We presented methods for generating cross-lingual data in an emergent domain, COVID-19.  ... 
arXiv:2201.11153v1 fatcat:ion7747l4vb6nmkwnk3hsul76e

Incorporating External Knowledge to Answer Open-Domain Visual Questions with Dynamic Memory Networks [article]

Guohao Li, Hang Su, Wenwu Zhu
2017 arXiv   pre-print
Extensive experiments demonstrate that our model not only achieves the state-of-the-art performance in the visual question answering task, but can also answer open-domain questions effectively by leveraging  ...  Most of the current algorithms are incapable of answering open-domain questions that require to perform reasoning beyond the image contents.  ...  Answer Open-Domain Visual Questions In this section, we elaborate on the details and formulations of our proposed model for answering open-domain visual questions.  ... 
arXiv:1712.00733v1 fatcat:tqfh5otaqrgl7jq6l6bjmenvm4

Towards a Visual Turing Challenge [article]

Mateusz Malinowski, Mario Fritz
2015 arXiv   pre-print
This trend has allowed the community to progress towards more challenging and open tasks and refueled the hope at achieving the old AI dream of building machines that could pass a turing test in open domains  ...  We exemplify some of the solutions on a recently presented dataset of question-answering task based on real-world indoor images that establishes a visual turing challenge.  ...  In this paper we argue for a Visual Turing Test -an open domain task of question-answering based on real-world images that resemblances the famous Turing Test [28, 29] and deviates from other attempts  ... 
arXiv:1410.8027v3 fatcat:wyk3qnz7mzbm5f4s5dclpymm6y

Answering Any-hop Open-domain Questions with Iterative Document Reranking [article]

Ping Nie, Yuyu Zhang, Arun Ramamurthy, Le Song
2021 arXiv   pre-print
To address these challenges, we propose a unified QA framework to answer any-hop open-domain questions, which iteratively retrieves, reranks and filters documents, and adaptively determines when to stop  ...  Existing approaches for open-domain question answering (QA) are typically designed for questions that require either single-hop or multi-hop reasoning, which make strong assumptions of the complexity of  ...  To address the challenges above, we introduce a unified QA framework for answering any-hop open-domain questions named Iterative Document Reranking (IDR).  ... 
arXiv:2009.07465v5 fatcat:m3hosnzbwvdx3k3g7x7tlm5zhi

Neural Domain Adaptation for Biomedical Question Answering [article]

Georg Wiese, Dirk Weissenborn, Mariana Neves
2017 arXiv   pre-print
However, these systems have not yet been applied to QA in more specific domains, such as biomedicine, because datasets are generally too small to train a DL system from scratch.  ...  In this work, we adapt a neural QA system trained on a large open-domain dataset (SQuAD, source) to a biomedical dataset (BioASQ, target) by employing various transfer learning techniques.  ...  For candidate answer generation, OAQA employs different strategies for general factoid/list questions, choice questions and quantity questions.  ... 
arXiv:1706.03610v2 fatcat:terefio4trhidlwmleusdzow3y

Neural Domain Adaptation for Biomedical Question Answering

Georg Wiese, Dirk Weissenborn, Mariana Neves
2017 Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)  
However, these systems have not yet been applied to QA in more specific domains, such as biomedicine, because datasets are generally too small to train a DL system from scratch.  ...  In this work, we adapt a neural QA system trained on a large open-domain dataset (SQuAD, source) to a biomedical dataset (BioASQ, target) by employing various transfer learning techniques.  ...  For candidate answer generation, OAQA employs different strategies for general factoid/list questions, choice questions and quantity questions.  ... 
doi:10.18653/v1/k17-1029 dblp:conf/conll/WieseWN17 fatcat:aig6evwimfczlfxokaytvwnnrq
« Previous Showing results 1 — 15 out of 419,730 results