Filters








4,645 Hits in 4.2 sec

A Semantic QA-Based Approach for Text Summarization Evaluation [article]

Ping Chen, Fei Wu, Tong Wang, Wei Ding
2018 arXiv   pre-print
We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it.  ...  Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation  ...  A QA-Based method for semantic comparison of texts Our automated evaluation method will leverage two NLP fields: Question Generation (QG), and Question Answering (QA).  ... 
arXiv:1704.06259v2 fatcat:pmrqakcnibazzf6kfdwdhklsv4

Biomedical question answering: A survey

Sofia J. Athenikos, Hyoil Han
2010 Computer Methods and Programs in Biomedicine  
In particular, we used "semantic knowledge-based QA" as a category under which to subsume QA techniques and approaches, both corpus-based and knowledge base (KB)-based, that utilize semantic knowledge-informed  ...  Objectives: In this survey, we reviewed the current state of the art in biomedical QA (Question Answering), within a broader framework of semantic knowledge-based QA approaches, and projected directions  ...  Acknowledgement We would like to thank the anonymous reviewers for their helpful feedback. r e f e r e n c e s  ... 
doi:10.1016/j.cmpb.2009.10.003 pmid:19913938 fatcat:tv4sel4llbcnjppnn7g2tygqze

Examining the role of statistical and linguistic knowledge sources in a general-knowledge question-answering system

Claire Cardie, Vincent Ng, David Pierce, Chris Buckley
2000 Proceedings of the sixth conference on Applied natural language processing -  
The system combines techniques for standard ad-hoc information retrieval (IR), query-dependent text summarization, and shallow syntactic and semantic sentence analysis.  ...  We describe and evaluate an implemented system for general-knowledge question answering.  ...  This approach to text summarization was shown to be quite successful in the recent SUMMAC evaluation of text summarization systems (Mani et al., 1999; Buckley et al., 1999) .  ... 
doi:10.3115/974147.974172 dblp:conf/anlp/CardieNPB00 fatcat:vr6kz475ynblvmjdtpkcbjifti

Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation [article]

Clément Rebuffel, Thomas Scialom, Laure Soulier, Benjamin Piwowarski, Sylvain Lamprier, Jacopo Staiano, Geoffrey Scoutheeten, Patrick Gallinari
2021 arXiv   pre-print
To this purpose, we propose a method to build synthetic multimodal corpora enabling to train multimodal components for a data-QuestEval metric.  ...  QuestEval is a reference-less metric used in text-to-text tasks, that compares the generated summaries directly to the source text, by automatically asking and answering questions.  ...  ., , 2021 on QG/QA-based metrics for the automated evaluation of generated texts.  ... 
arXiv:2104.07555v3 fatcat:636ecmymjnbpfgyyqp5xbk6bum

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  
The large QA corpus has been dynamically clustered with semantic features paves a way for efficient document's retrieval.  ...  Results obtained from statistical significance test with hypothesis testing and evaluation with standard metrics proves the significant improvement in generating text summarization using QA corpus.  ...  Document clusters are dynamically generated based on the syntactic and semantic similarities with the query keywords for storing QA pairs.  ... 
doi:10.5815/ijeme.2020.03.04 fatcat:wokhamjdo5fwvhf5ojtmovntxy

The Factual Inconsistency Problem in Abstractive Text Summarization: A Survey [article]

Yichong Huang, Xiachong Feng, Xiaocheng Feng, Bing Qin
2021 arXiv   pre-print
This inconsistency between the original text and the summary has caused various concerns over its applicability, and the previous evaluation methods of text summarization are not suitable for this issue  ...  In this survey, we focus on presenting a comprehensive review of these fact-specific evaluation methods and text summarization models.  ...  QA-based Inspired by other question answering (QA) based automatic metrics in text summarization, Durmus et al. [2020; propose QA based factual consistency evaluation metrics QAGS and FEQA separately  ... 
arXiv:2104.14839v2 fatcat:37glddlmnbdnfnpk45jelcejuu

Multimedia Question Answering

Richang Hong, Meng Wang, Guangda Li, Liqiang Nie, Zheng-Jun Zha, Tat-Seng Chua
2012 IEEE Multimedia  
In contrast, MMQA can use multimodality summarization or semantic summarization to present an answer by summarizing the retrieved potential answers from various sources (text, image, audio, video, or a  ...  Lee, and Trevor Darrell were the first to present image-based QA. 3 They described a photo-based QA system for finding information about physical objects. Their approach consisted of three layers.  ... 
doi:10.1109/mmul.2011.53 fatcat:kixa3tq6yraafglyrlhx5xehwi

Survey of Scientific Document Summarization Techniques

Sheena Kurian K, Sheena Mathew
2020 Computer Science  
The different methods commonly used in automatic text summarization are discussed in this paper with their pros and cons.  ...  Commonly used evaluation techniques and datasets in this field are also discussed. Rouge and Pyramid scores of the different methods are tabulated for easy comparison of the results.  ...  Semantic-based Approaches Semantic-based approaches need deeper natural language processing and natural language generation techniques for text regeneration.  ... 
doi:10.7494/csci.2020.21.2.3356 fatcat:mbklxkl5dfaq7ax452p3bptluq

Extractive Text Summarization Using Recent Approaches: A Survey

Avaneesh Kumar Yadav, Ashish Kumar Maurya, Ranvijay, Rama Shankar Yadav
2021 Ingénierie des Systèmes d'Information  
Many authors proposed various techniques for both types of text summarization. This paper presents a survey of extractive text summarization on graphical-based techniques.  ...  Text summarization is a process that generates a brief version of the document in the form of a meaningful summary.  ...  ACKNOWLEDGMENT We thank innominate reviewers for helpful advices. This research was partially supported by Ministry of Human Resource Development (MHRD), Government of India (GoI).  ... 
doi:10.18280/isi.260112 fatcat:zwo7neckujanliou7arlaiccj4

A Brief Survey of Question Answering Systems

Michael Caballero
2021 International Journal of Artificial Intelligence & Applications  
After discussing QA history, this paper summarizes the different approaches to the architecture of QA systems -- whether they are closed or open-domain and whether they are text-based, knowledge-based,  ...  This survey summarizes the history and current state of the field and is intended as an introductory overview of QA systems.  ...  As Dimitrakis et al. writes: "A limitation of the previous approaches [text-based and knowledge-based QA systems] is that a single type of source can be insufficient to provide the ideal answer.  ... 
doi:10.5121/ijaia.2021.12501 fatcat:jhydawao5vgaxoghxrp6v37f2q

QA-Align: Representing Cross-Text Content Overlap by Aligning Question-Answer Propositions [article]

Daniela Brook Weiss, Paul Roit, Ayal Klein, Ori Ernst, Ido Dagan
2021 arXiv   pre-print
We employ crowd-workers for constructing a dataset of QA-based alignments, and present a baseline QA alignment model trained over our dataset.  ...  Multi-text applications, such as multi-document summarization, are typically required to model redundancies across related texts.  ...  Acknowledgments We would like to thank the anonymous reviewers for their thorough and insightful comments.  ... 
arXiv:2109.12655v1 fatcat:5o2axfat4nam7ecdh227i7ua7q

Assessing the performance of Olelo, a real-time biomedical question answering application

Mariana Neves, Fabian Eckert, Hendrik Folkerts, Matthias Uflacker
2017 BioNLP 2017  
a new extension based on semantic role labeling (SRL) that we are considering for our application.  ...  We recently developed Olelo, a QA system for biomedicine which includes various NLP components, such as question processing, document and passage retrieval, answer processing and multi-document summarization  ...  For summary questions, a custom summary is generated based on the relevant sentence and corresponding named entities. Our approach is based on a graph-based approach for sentence selection .  ... 
doi:10.18653/v1/w17-2344 dblp:conf/bionlp/NevesEFU17 fatcat:lerk6gynazallo6vamr4coqubq

Semantic Answer Similarity for Evaluating Question Answering Models [article]

Julian Risch and Timo Möller and Julian Gutsch and Malte Pietsch
2021 arXiv   pre-print
Therefore, there is a need for an evaluation metric that is based on semantics instead of pure string similarity.  ...  In this short paper, we present SAS, a cross-encoder-based metric for the estimation of semantic answer similarity, and compare it to seven existing metrics.  ...  A recent tutorial summarizes evaluation metrics used in NLG, including but not limited to the QA task (Khapra and Sai, 2021) .  ... 
arXiv:2108.06130v3 fatcat:omyydvcy6nbodp6famdhcrcqwq

Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary [article]

Daniel Deutsch, Tania Bedrax-Weiss, Dan Roth
2021 arXiv   pre-print
QA-based methods directly measure a summary's information overlap with a reference, making them fundamentally different than text overlap metrics.  ...  In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA).  ...  This research is supported by a Focused Award from Google.  ... 
arXiv:2010.00490v3 fatcat:5gcystpmbrhalpl7nvls4az24m

Towards Question-Answering as an Automatic Metric for Evaluating the Content Quality of a Summary

Daniel Deutsch, Tania Bedrax-Weiss, Dan Roth
2021 Transactions of the Association for Computational Linguistics  
QA-based methods directly measure a summary's information overlap with a reference, making them fundamentally different than text overlap metrics.  ...  In this work, we propose a metric to evaluate the content quality of a summary using question-answering (QA).  ...  This research is supported by a Focused Award from Google.  ... 
doi:10.1162/tacl_a_00397 fatcat:464bpobwvfakdhnhij23ratbxy
« Previous Showing results 1 — 15 out of 4,645 results