Filters








180 Hits in 5.4 sec

Joint question clustering and relevance prediction for open domain non-factoid question answering

Snigdha Chaturvedi, Vittorio Castelli, Radu Florian, Ramesh M. Nallapati, Hema Raghavan
2014 Proceedings of the 23rd international conference on World wide web - WWW '14  
Answer Type taxonomies currently exist for factoid-style questions, but not for open-domain questions.  ...  learn question-clusters and cluster-specific relevance models.  ...  Salim Roukos for his valuable suggestions and for providing the necessary resources for developing labeled data for relevance as well as for answer-types.  ... 
doi:10.1145/2566486.2567999 dblp:conf/www/ChaturvediCFNR14 fatcat:ehmzr6g6ujatjplzirf65uumga

Neural Domain Adaptation for Biomedical Question Answering [article]

Georg Wiese, Dirk Weissenborn, Mariana Neves
2017 arXiv   pre-print
For example, the BioASQ dataset for biomedical QA comprises less then 900 factoid (single answer) and list (multiple answers) QA instances.  ...  Despite this fact, our systems achieve state-of-the-art results on factoid questions and competitive results on list questions.  ...  Acknowledgments This research was supported by the German Federal Ministry of Education and Research (BMBF) through Software Campus project GeNIE (01IS12050).  ... 
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)  
For example, the BioASQ dataset for biomedical QA comprises less then 900 factoid (single answer) and list (multiple answers) QA instances.  ...  Despite this fact, our systems achieve state-of-the-art results on factoid questions and competitive results on list questions.  ...  Acknowledgments This research was supported by the German Federal Ministry of Education and Research (BMBF) through Software Campus project GeNIE (01IS12050).  ... 
doi:10.18653/v1/k17-1029 dblp:conf/conll/WieseWN17 fatcat:aig6evwimfczlfxokaytvwnnrq

Overview of BioASQ 2020: The Eighth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering [chapter]

Anastasios Nentidis, Anastasia Krithara, Konstantinos Bougiatiotis, Martin Krallinger, Carlos Rodriguez-Penagos, Marta Villegas, Georgios Paliouras
2020 Lecture Notes in Computer Science  
BioASQ is a series of challenges aiming at the promotion of systems and methodologies for large-scale biomedical semantic indexing and question answering.  ...  tasks are organized yearly since 2012, where different teams develop systems that compete on the same demanding benchmark datasets that represent the real information needs of experts in the biomedical domain  ...  to develop systems for all the stages of question answering in the biomedical domain.  ... 
doi:10.1007/978-3-030-58219-7_16 fatcat:wekghiprdzc53ejvwxdvn5d2xq

Combining evidence with a probabilistic framework for answer ranking and answer merging in question answering

Jeongwoo Ko, Luo Si, Eric Nyberg
2010 Information Processing & Management  
The hypotheses of the paper are that (1) the framework effectively combines multiple evidence for identifying answer relevance and their correlation in answer ranking, (2) the framework supports answer  ...  merging on answer candidates returned by multiple extraction techniques, (3) the framework can support list questions as well as factoid questions, (4) the framework can be easily applied to a different  ...  Acknowledgments This work was supported in part by ARDA/DTO Advanced Question Answering for Intelligence (AQUAINT) program award number NBCHC040164.  ... 
doi:10.1016/j.ipm.2009.11.004 fatcat:fr5zrh3fdzecva5rvm3nfjgj3e

MultiCQA: Zero-Shot Transfer of Self-Supervised Text Matching Models on a Massive Scale [article]

Andreas Rücklé, Jonas Pfeiffer, Iryna Gurevych
2020 arXiv   pre-print
We investigate the model performances on nine benchmarks of answer selection and question similarity tasks, and show that all 140 models transfer surprisingly well, where the large majority of models substantially  ...  We study the zero-shot transfer capabilities of text matching models on a massive scale, by self-supervised training on 140 source domains from community question answering forums in English.  ...  Acknowledgements This work was supported by the German Federal Ministry of Education and Research (BMBF) and the Hessen State Ministry for Higher Education, Research and the Arts within their joint support  ... 
arXiv:2010.00980v1 fatcat:lggd7px4j5cotj4nkfx4a6raqi

An overview of the BIOASQ large-scale biomedical semantic indexing and question answering competition

George Tsatsaronis, Georgios Balikas, Prodromos Malakasiotis, Ioannis Partalas, Matthias Zschunke, Michael R Alvers, Dirk Weissenborn, Anastasia Krithara, Sergios Petridis, Dimitris Polychronopoulos, Yannis Almirantis, John Pavlopoulos (+10 others)
2015 BMC Bioinformatics  
F-measure for exact answers to yes/no, factoid, and list questions in Phase B; ROUGE for ideal answers.  ...  The official measure for the "exact" answers of factoid questions was the mean reciprocal rank (MRR), which is often used to evaluate factoid questions in question answering challenges; consult, for example  ...  The output of the system for each of the tasks is compared with the "gold" answers, e.g., MESH concepts, relevant documents, snippets, triples, and ideal answer to the input question.  ... 
doi:10.1186/s12859-015-0564-6 pmid:25925131 pmcid:PMC4450488 fatcat:u5enfjjos5gv5k3wkjxxa5ebry

Data Augmentation for Biomedical Factoid Question Answering [article]

Dimitris Pappas and Prodromos Malakasiotis and Ion Androutsopoulos
2022 arXiv   pre-print
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult.  ...  One of the simplest da methods, word2vec-based word substitution, performed best and is recommended. We release our artificial training instances and code.  ...  We suspect that the biomedical experts of bioasq create questions whose answers cannot be found in large numbers of documents (unlike common questions in open-domain qa datasets), and the few relevant  ... 
arXiv:2204.04711v1 fatcat:ewv6dinzsjdrbl55sj2njmngqu

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  
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.  ...  INDEX TERMS Open-domain textual question answering, deep learning, machine reading comprehension, information retrieval.  ...  Following the above categories, open-domain textual QA can be defined as: (1) unstructured data sources on text, (2) factoid questions or keyword/phrase as inputs,(3)extractive-based answer, (4) open-domain  ... 
doi:10.1109/access.2020.2988903 fatcat:po4euxfronf3pob52qc2wcgrre

Dense Passage Retrieval for Open-Domain Question Answering [article]

Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis, Ledell Wu, Sergey Edunov, Danqi Chen, Wen-tau Yih
2020 arXiv   pre-print
Open-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method.  ...  When evaluated on a wide range of open-domain QA datasets, our dense retriever outperforms a strong Lucene-BM25 system largely by 9%-19% absolute in terms of top-20 passage retrieval accuracy, and helps  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments and suggestions.  ... 
arXiv:2004.04906v3 fatcat:yff6ror4xbbjxjcoaaczsdzhqi

Pruning the Index Contents for Memory Efficient Open-Domain QA [article]

Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz
2021 arXiv   pre-print
This work presents a simple approach for pruning the contents of a massive index such that the open-domain QA system altogether with index, OS, and library components fits into 6GiB docker image while  ...  retaining only 8% of original index contents and losing only 3% EM accuracy.  ...  The computation used the infrastructure supported by the Czech Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project "IT4Innovations  ... 
arXiv:2102.10697v2 fatcat:rbkfghoainb37asci2etnhyzse

In search of the Why

Suzan Verberne
2011 SIGIR Forum  
of the open domain why-questions.  ...  At the same time there has been a development away from domain-specific to open-domain questions.  ...  After her graduation, Suzan worked as a linguistic engineer and project manager for Polderland Language and Speech Technology.  ... 
doi:10.1145/1924475.1924501 fatcat:fjnlh6htjfg5bas5rjdxd5wx44

Knowledge Efficient Deep Learning for Natural Language Processing [article]

Hai Wang
2020 arXiv   pre-print
Annotation is time-consuming and expensive to produce at scale.  ...  This thesis focuses on adapting such classical methods to modern deep learning models and algorithms.  ...  Additionally, to have a head-to-head comparison with existing sentence selectors designed for factoid question answering, we also evaluate our approach on two open-domain question answering datasets  ... 
arXiv:2008.12878v1 fatcat:vhcxrhydyfcsnh3iu5t3g5goky

NeuralQA: A Usable Library for Question Answering (Contextual Query Expansion + BERT) on Large Datasets [article]

Victor Dibia
2020 arXiv   pre-print
Existing tools for Question Answering (QA) have challenges that limit their use in practice.  ...  Code and documentation for NeuralQA is available as open source on Github (https://github.com/victordibia/neuralqaGithub).  ...  Acknowledgments The author thanks Melanie Beck, Andrew Reed, Chris Wallace, Grant Custer, Danielle Thorpe and other members of the Cloudera Fast Forward team for their valuable feedback.  ... 
arXiv:2007.15211v2 fatcat:q5wnqc6awzdw7nsxoyl4ehlb4u

Answering Science Exam Questions Using Query Rewriting with Background Knowledge [article]

Ryan Musa, Xiaoyan Wang, Achille Fokoue, Nicholas Mattei, Maria Chang, Pavan Kapanipathi, Bassem Makni, Kartik Talamadupula, Michael Witbrock
2019 arXiv   pre-print
Open-domain question answering (QA) is an important problem in AI and NLP that is emerging as a bellwether for progress on the generalizability of AI methods and techniques.  ...  Much of the progress in open-domain QA systems has been realized through advances in information retrieval methods and corpus construction.  ...  In this section, we look at the most relevant prior work in improving open-domain question answering.  ... 
arXiv:1809.05726v2 fatcat:27muyx5t7vcexh5gyrwinsibre
« Previous Showing results 1 — 15 out of 180 results