Filters








62,475 Hits in 7.2 sec

CAiRE-COVID: A Question Answering and Query-focused Multi-Document Summarization System for COVID-19 Scholarly Information Management [article]

Dan Su, Yan Xu, Tiezheng Yu, Farhad Bin Siddique, Elham J. Barezi, Pascale Fung
2020 arXiv   pre-print
We present CAiRE-COVID, a real-time question answering (QA) and multi-document summarization system, which won one of the 10 tasks in the Kaggle COVID-19 Open Research Dataset Challenge, judged by medical  ...  We also propose query-focused abstractive and extractive multi-document summarization methods, to provide more relevant information related to the question.  ...  Query-focused Multi-document Summarization In order to generate query-focused summarizatioin for COVID-19 questions, we propose to incorporate answer relevance with the help of a QA model into the summarization  ... 
arXiv:2005.03975v3 fatcat:r3nf673dcbef5b2mnatxthvy4y

WSL-DS: Weakly Supervised Learning with Distant Supervision for Query Focused Multi-Document Abstractive Summarization [article]

Md Tahmid Rahman Laskar, Enamul Hoque, Jimmy Xiangji Huang
2020 arXiv   pre-print
In the Query Focused Multi-Document Summarization (QF-MDS) task, a set of documents and a query are given where the goal is to generate a summary from these documents based on the given query.  ...  in a document set from the multi-document gold reference summaries.  ...  We acknowledge Compute Canada for providing us the computing resources.  ... 
arXiv:2011.01421v1 fatcat:fth4hcqwonafpcdptgrp3kwm6e

A survey on sentimental cluster based opinion summarization in question answering community

Ankur Goswami
2019 International Journal of Advanced Technology and Engineering Exploration  
Rautray and Balabantaray [27], 2018 Multi document summarization using Cuckoo search approach (MDSCSA) Uses Cuckoo search meta-heuristic algorithm to summarize the document.  ...  , learning model designed to measure the answerability of questions to a product review.  ... 
doi:10.19101/ijatee.2019.650016 fatcat:zxuraar6azfctfhhzrnjqoro3a

More Than Reading Comprehension: A Survey on Datasets and Metrics of Textual Question Answering [article]

Yang Bai, Daisy Zhe Wang
2022 arXiv   pre-print
Textual Question Answering (QA) aims to provide precise answers to user's questions in natural language using unstructured data.  ...  In this paper, we survey 47 recent textual QA benchmark datasets and propose a new taxonomy from an application point of view. In addition, We summarize 8 evaluation metrics of textual QA tasks.  ...  A human-written answer was then created by summarizing the top 5 documents retrieved for each question.  ... 
arXiv:2109.12264v2 fatcat:sesgmfxagzdjji37cj3oin7yma

AQuaMuSe: Automatically Generating Datasets for Query-Based Multi-Document Summarization [article]

Sayali Kulkarni, Sheide Chammas, Wan Zhu, Fei Sha, Eugene Ie
2020 arXiv   pre-print
We propose a scalable approach called AQuaMuSe to automatically mine qMDS examples from question answering datasets and large document corpora.  ...  Query-based multi-document summarization (qMDS) addresses this pervasive need, but the research is severely limited due to lack of training and evaluation datasets as existing single-document and multi-document  ...  These long-form answers address user questions with content that are focused and coherent.  ... 
arXiv:2010.12694v1 fatcat:v6cgex7ttfhxzkiz2hl2d6ijxm

Design Challenges for a Multi-Perspective Search Engine [article]

Sihao Chen and Siyi Liu and Xander Uyttendaele and Yi Zhang and William Bruno and Dan Roth
2021 arXiv   pre-print
Many users turn to document retrieval systems (e.g. search engines) to seek answers to controversial questions.  ...  Naturally, identifying such responses within a document is a natural language understanding task.  ...  This work was supported in part by a Focused Award from Google, and a gift from Tencent.  ... 
arXiv:2112.08357v1 fatcat:a2eufs3rlbckpk56ydrt3kx2zm

Satisfying information needs with multi-document summaries

Sanda Harabagiu, Andrew Hickl, Finley Lacatusu
2007 Information Processing & Management  
Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the  ...  summarization strategies.  ...  engines: (1) a question-focused summarization (QFS) system and (2) a multi-document summarization system.  ... 
doi:10.1016/j.ipm.2007.01.004 fatcat:uujzhptylfci3i4kdjknvn7bpa

Biomedical Question Answering: A Survey of Approaches and Challenges [article]

Qiao Jin, Zheng Yuan, Guangzhi Xiong, Qianlan Yu, Huaiyuan Ying, Chuanqi Tan, Mosha Chen, Songfang Huang, Xiaozhong Liu, Sheng Yu
2021 arXiv   pre-print
Automatic Question Answering (QA) has been successfully applied in various domains such as search engines and chatbots.  ...  Despite the developments, BQA systems are still immature and rarely used in real-life settings.  ...  BioSquash [175] is adapted from the general domain summarizer Squash [114] and is focused on QA-oriented summarization of biomedical documents. Terol et al.  ... 
arXiv:2102.05281v2 fatcat:gngt6kffszbzbc3donik55dd64

DUC in context

Paul Over, Hoa Dang, Donna Harman
2007 Information Processing & Management  
The themes are extrinsic and intrinsic evaluation, evaluation procedures and methods, generic versus focused summaries, single-and multi-document summaries, length and compression issues, extracts versus  ...  Recent years have seen increased interest in text summarization with emphasis on evaluation of prototype systems.  ...  of multi-document question-focused summaries.  ... 
doi:10.1016/j.ipm.2007.01.019 fatcat:ycjd3eebvzd5lemkt277fpsjma

Text Summarization using QA Corpus for User Interaction Model QA System

Karpagam K., College of Engineering & Technology, Pollachi, Saradha A., Manikandan K., Madusudanan K., Institute of Road Transport and Technology, Erode, Vellore Institute of Technology, Vellore, College of Engineering & Technology, Pollachi
2020 International Journal of Education and Management Engineering  
Document summarization is capable of generating user query relevant, precise summaries from the original document for user needs.  ...  Answer datasets. The large QA corpus has been dynamically clustered with semantic features paves a way for efficient document's retrieval.  ...  Multi-similar questions with answer are used to build QA pair corpus to reduce response time for candidate summaries withdrawal.  ... 
doi:10.5815/ijeme.2020.03.04 fatcat:wokhamjdo5fwvhf5ojtmovntxy

A question-answering system for aircraft pilots' documentation [article]

Alexandre Arnold and Gérard Dupont and Félix Furger and Catherine Kobus and François Lancelot
2020 arXiv   pre-print
This paper presents a question answering (QA) system that would help aircraft pilots access information in this documentation by naturally interacting with the system and asking questions in natural language  ...  After describing each module of the dialog system, we present a multi-task based approach for the QA module which enables performance improvement on a Flight Crew Operating Manual (FCOM) dataset.  ...  There are a number of obvious improvements we might consider; a first obvious one is to get more in-domain data, that will allow us to further fine-tune the QA engine on in-domain data.  ... 
arXiv:2011.13284v1 fatcat:crozzhefbzdfnertq3tafguc3u

RxWhyQA: a clinical question-answering dataset with the challenge of multi-answer questions [article]

Sungrim Moon, Huan He, Hongfang Liu, Jungwei W. Fan
2022 arXiv   pre-print
Objectives Create a dataset for the development and evaluation of clinical question-answering (QA) systems that can handle multi-answer questions.  ...  Conclusion We created and shared a clinical QA dataset with a focus on multi-answer questions to represent real-world scenarios.  ...  Although the RxWhyQA focuses on why-questions derived from a specific corpus and drug-reason relations, it offers an initial benchmark of multi-answer clinical QA and a reference for future work to repurpose  ... 
arXiv:2201.02517v1 fatcat:uafskzhs5relhgeli4lvgr4vvu

Query Focused Multi-Document Summarization with Distant Supervision [article]

Yumo Xu, Mirella Lapata
2020 arXiv   pre-print
We consider the problem of better modeling query-cluster interactions to facilitate query focused multi-document summarization (QFS).  ...  In this work, we leverage distant supervision from question answering where various resources are available to more explicitly capture the relationship between queries and documents.  ...  Introduction Query Focused Multi-Document Summarization (QFS; Dang 2006) aims to create a short summary from a set of documents that answers a specific query.  ... 
arXiv:2004.03027v1 fatcat:m473vytlvfhz5op5gr6f7r44iq

SIGIR 2016 Workshop WebQA II

Alessandro Moschitti, Lluiís Márquez, Preslav Nakov, Eugene Agichtein, Charles Clarke, Idan Szpektor
2016 Proceedings of the 39th International ACM SIGIR conference on Research and Development in Information Retrieval - SIGIR '16  
, yet are more useful than a full document.  ...  ., Task 3 [14, 15] , which focused on answering new questions using a CQA forum (Qatar Living).  ... 
doi:10.1145/2911451.2917767 dblp:conf/sigir/MoschittiMNACS16 fatcat:ycda2zqazfei7kmsr7pokgcxl4

Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs

Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes
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)  
For two generative tasks with very long text input, long-form question answering and multidocument summarization, feeding graph representations as input can achieve better performance than using retrieved  ...  Toward abstractive summarization using semantic representations. arXiv preprint arXiv:1805.10399.  ...  Introduction Effective information synthesis is at the core of many Natural Language Processing applications, such as open-domain question answering and multi-document summarization.  ... 
doi:10.18653/v1/d19-1428 dblp:conf/emnlp/FanGBB19 fatcat:u4uju6ob7rcnvd3mqcavkgc6ey
« Previous Showing results 1 — 15 out of 62,475 results