101,381 Hits in 5.1 sec

HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data [article]

Wenhu Chen, Hanwen Zha, Zhiyu Chen, Wenhan Xiong, Hong Wang, William Wang
2021 arXiv   pre-print
However, the hybrid model's score is still far behind human performance. Hence, HybridQA can serve as a challenging benchmark to study question answering with heterogeneous information.  ...  We test with three different models: 1) a table-only model. 2) text-only model. 3) a hybrid model that combines heterogeneous information to find the answer.  ...  Therefore, designing hybrid question answering systems would probably yield marginal benefits over the non-hybrid ones, which greatly hinders the research development in building hybrid question answering  ... 
arXiv:2004.07347v3 fatcat:h2mcly6aujfhhljzvud2w3e66a

Multi-Instance Training for Question Answering Across Table and Linked Text [article]

Vishwajeet Kumar, Saneem Chemmengath, Yash Gupta, Jaydeep Sen, Samarth Bharadwaj, Soumen Chakrabarti
2021 arXiv   pre-print
Often, a question is best answered by matching its parts to either table cell contents or unstructured text spans, and extracting answers from either source.  ...  Answering natural language questions using information from tables (TableQA) is of considerable recent interest.  ...  Our Approach We propose a row-grounded question answering system capable of multi-hop reasoning over hybrid context of table and text.  ... 
arXiv:2112.07337v1 fatcat:nqbhzovaqvg6pbvlvkwp3tmbti

VOGUE: Answer Verbalization through Multi-Task Learning [article]

Endri Kacupaj, Shyamnath Premnadh, Kuldeep Singh, Jens Lehmann, Maria Maleshkova
2021 arXiv   pre-print
The VOGUE framework attempts to generate a verbalized answer using a hybrid approach through a multi-task learning paradigm.  ...  Despite all the notable advancements, current KGQA systems only focus on answer generation techniques and not on answer verbalization.  ...  Suppose the QA system only responds with a number (e.g., 38) as an answer (similar to open-source KGQA systems), with no further explanation.  ... 
arXiv:2106.13316v2 fatcat:4nvt3gtje5dsfcqabhmms44vge

Discovering and Querying Hybrid Linked Data

Zareen Syed, Tim Finin, Muhammad Rahman, James Kukla, Jeehye Yun
2015 Extended Semantic Web Conference  
We describe limitations of our approach and also discuss cases where our system can complement other structured data querying systems by retrieving additional answers not available in structured sources  ...  We describe our approach to developing a natural language query interface for a hybrid knowledge base Wikitology, and present that as a case study for accessing hybrid information sources with structured  ...  We find our system in line with the new hybrid question answering track.  ... 
dblp:conf/esws/SyedFRKY15 fatcat:ignvnuh7rnbrvijpcgod65pg3u

ADAPT Centre Cone Team at IJCNLP-2017 Task 5: A Similarity-Based Logistic Regression Approach to Multi-choice Question Answering in an Examinations Shared Task

Daria Dzendzik, Alberto Poncelas, Carl Vogel, Qun Liu
2017 International Joint Conference on Natural Language Processing  
The system is based on a logistic regression over the string similarities between question, answer, and additional text.  ...  We describe the work of a team from the ADAPT Centre in Ireland in addressing automatic answer selection for the Multichoice Question Answering in Examinations shared task.  ...  Introduction This paper describes the participation of the ADAPT Centre team in the Multi-choice Question Answering in Examinations Shared Task 2017. 1 This is a typical question answering task that aims  ... 
dblp:conf/ijcnlp/DzendzikPVL17 fatcat:2g7diew32jaejnxrcim5t3gnay

From Talk to Action with Accountability: Monitoring the Public Discussion of Policy Makers with Deep Neural Networks and Topic Modelling [article]

Vili Hätönen, Fiona Melzer
2021 arXiv   pre-print
MuSTAS uses novel multi-source hybrid latent Dirichlet allocation to model topics from a variety of documents.  ...  In response, we propose a multi-source topic aggregation system (MuSTAS) which processes policy makers speech and rhetoric from several publicly available sources into an easily digestible topic summary  ...  Empirical Evaluation -Modelling the Topics of Finnish Politicians We will demonstrate the functionality of multi-source hybrid LDA as part of MuSTAS by implementing the system in the Finnish context.  ... 
arXiv:2010.08346v3 fatcat:jjp57w726rdanin4a73k32r24u

TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance [article]

Fengbin Zhu, Wenqiang Lei, Youcheng Huang, Chao Wang, Shuo Zhang, Jiancheng Lv, Fuli Feng, Tat-Seng Chua
2021 arXiv   pre-print
However, Question Answering (QA) over such hybrid data is largely neglected in existing research.  ...  Hybrid data combining both tabular and textual content (e.g., financial reports) are quite pervasive in the real world.  ...  We show the basic statistics of each split in Table 1 , and the question distribution regarding answer source and answer type in Table 2 .  ... 
arXiv:2105.07624v2 fatcat:sakevdvefvbbzhwx4ng7nyyjkq

Questions and Answers: Theoretical and Applied Perspectives

Raffaella Bernardi, Bonnie Webber
2007 Journal of Applied Logic  
They present their approach for domain-restricted question answering from structured knowledge sources and multilingual data (QUETAL).  ...  The distinctive characteristics of this system are its hybrid architecture integrating high-quality NLP tools, the focus on linguistic analysis of questions, and its use of ontologies to interface between  ...  s COGEX system.) The great diversity of candidate answers that can be relevant to a questioner is exploited in an original way in the paper by Dalmas and Webber.  ... 
doi:10.1016/j.jal.2005.12.008 fatcat:rak2bsvqize5jgvhgavvxclxo4

Answering Questions from Multiple Documents - the Role of Multi-Document Summarization

Pinaki Bhaskar
2013 Recent Advances in Natural Language Processing  
Ongoing research work on Question Answering using multi-document summarization has been described. It has two main sub modules, document retrieval and Multi-document Summarization.  ...  The system is tested on data set of INEX QA track from 2011 to 2013 and best readability score was achieved.  ...  Acknowledgments We acknowledge the support of the DeitY, MCIT, Govt. of India funded project "Development of Cross Lingual Information Access (CLIA) System Phase II".  ... 
dblp:conf/ranlp/Bhaskar13 fatcat:mjw255widrfkxct2diozlxro2y

A Multi-Strategy and Multi-Source Approach to Question Answering

Jennifer Chu-Carroll, John M. Prager, Christopher A. Welty, Krzysztof Czuba, David A. Ferrucci
2002 Text Retrieval Conference  
This work was supported in part by the Advanced Research and Development Activity (ARDA)'s Advanced Question Answering for Intelligence (AQUAINT) Program under contract number MDA904-01-C-0988.  ...  Acknowledgments We would like to thank Abe Ittycheriah and Salim Roukos for making available their system and results for experimental purposes, Stefano Bertolo for his help with Cyc integration, and Ruchi  ...  Run "IBMPQ" exploits the multi-source aspect of PIQUANT with the knowledge-based answering agent.  ... 
dblp:conf/trec/Chu-CarrollPWCF02 fatcat:3cygrsqpzngh5dbsqvnjuyixlm

Answering Numerical Reasoning Questions in Table-Text Hybrid Contents with Graph-based Encoder and Tree-based Decoder [article]

Fangyu Lei, Shizhu He, Xiang Li, Jun Zhao, Kang Liu
2022 arXiv   pre-print
It models the numerical question answering over table-text hybrid contents as an expression tree generation task.  ...  In the real-world question answering scenarios, hybrid form combining both tabular and textual contents has attracted more and more attention, among which numerical reasoning problem is one of the most  ...  QA systems use various types of knowledge to answer natural language questions.  ... 
arXiv:2209.07692v1 fatcat:l45wohrosbbnjgvmfuuxn25qau

Question Answering over Curated and Open Web Sources [article]

Rishiraj Saha Roy, Avishek Anand
2020 arXiv   pre-print
We partition research contributions by the underlying source from where answers are retrieved: curated knowledge graphs, unstructured text, or hybrid corpora.  ...  Other key dimensions are covered within each sub-topic: like the complexity of questions addressed, and degrees of explainability and interactivity introduced in the systems.  ...  Some methods for hybrid QA start with KGs as a source for candidate answers and use text corpora like Wikipedia or ClueWeb as additional evidence [26, 71, 72, 75, 85, 88] , or start with answer sentences  ... 
arXiv:2004.11980v3 fatcat:bavyc2xlrbazrphxhhgzzeitrq

Question Answering Survey: Directions, Challenges, Datasets, Evaluation Matrices [article]

Hariom A. Pandya, Brijesh S. Bhatt
2021 arXiv   pre-print
Such systems are designed to cater the most prominent answer from this giant knowledge source to the user query using natural language understanding (NLU) and thus eminently depends on the Question-answering  ...  This digitization leads to the need for automated answering system to extract fruitful information from redundant and transitional knowledge sources.  ...  Hybrid Question Answering Answering the hybrid question like: Which is the second largest planet in the solar system? involves many natural language challenges [109] .  ... 
arXiv:2112.03572v1 fatcat:c6ena24xondevec54u7f524p3m

Reasoning over Hybrid Chain for Table-and-Text Open Domain QA [article]

Wanjun Zhong, Junjie Huang, Qian Liu, Ming Zhou, Jiahai Wang, Jian Yin, Nan Duan
2022 arXiv   pre-print
CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.  ...  We evaluate our system on OTT-QA, a large-scale table-and-text open-domain question answering benchmark, and our system achieves the state-of-the-art performance.  ...  Our synthesized pre-training corpus includes higher ratio of 3-hop questions, which enhance the multi-hop reasoning ability of the system.  ... 
arXiv:2201.05880v1 fatcat:2l3on3glcfglhima65xzdmswwu

Obj2Sub: Unsupervised Conversion of Objective to Subjective Questions [article]

Aarish Chhabra, Nandini Bansal, Venktesh V, Mukesh Mohania, Deep Dwivedi
2022 arXiv   pre-print
mandating a detailed answer.  ...  Hence, in this paper, we propose a novel hybrid unsupervised approach leveraging rule-based methods and pre-trained dense retrievers for the novel task of automatically converting the objective questions  ...  Upon receiving the inputs (Q and A), our system automatically classifies Q into one of the 3 broad categories of objective questions based on what class it represents: • Multi-option Dependent (∼ 7%) The  ... 
arXiv:2206.11848v1 fatcat:32nnals5mbhjvdbqm5t34hm3cy
« Previous Showing results 1 — 15 out of 101,381 results