Overview of the Answer Validation Exercise 2008

Rodrigo, Álvaro; Peñas, Anselmo; Verdejo, Felisa

doi:10.1007/978-3-642-04447-2_35

Cited by 29 publications

(11 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The best result was obtained by DFKI in English domain with precision and recall were about 44% and 71%. Last report from AVE was done by [8] in AVE 2008. They presented the changes in the evaluation with respect to the last edition, and the results of this third edition.…”

Section: Fig2 Approaches Based On Av's Methodsmentioning

confidence: 99%

“…The meetings were held three times in 2006-2008 [6][7][8] which proposed Recognition Textual Entailment (RTE) [9] as the primary approach where the hypotheses have been built semiautomatically turning the questions and the answers into an affirmative form. Participant systems must return a value YES or NO for each pair of text-hypothesis to indicate if the text entails the hypothesis or not.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Survey on Answer Validation for Indonesian Question Answering System (IQAS)

Abdiansah¹,

Azhari²,

Sari³

2018

IJISA

View full text Add to dashboard Cite

Abstract-Research on Question Answering System (QAS) has been done mainly in English. Unfortunately, for Indonesian, it is still rarely explored whereas Indonesian is the official language used more than 250 million people. Research in the area of Indonesian Question Answering System (IQAS) began in 2005s, and since then only few number of IQAS have been developed. One of the important issues in IQAS is Answer Validation (AV), which is a system that can determine the correctness of QAS. To identify the future scope of research in this area, the need of comprehensive survey on IQAS and AV arises naturally. The goals of this survey are to find the cutting-edge method used in AV and to prove that AV has not been implemented on IQAS. Based on the results, we suggest new opportunities and research challenges for IQAS community.

show abstract

Section: Fig2 Approaches Based On Av's Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Survey on Answer Validation for Indonesian Question Answering System (IQAS)

Abdiansah¹,

Azhari²,

Sari³

2018

IJISA

View full text Add to dashboard Cite

show abstract

“…Textual entailment has never been applied explicitly to fact checking problems, but they obviously meet at some points [37]. Many evaluation campaigns and benchmarks are related to textual entailment, as well as paraphrase detection in general, among which PASCAL challenge [13], Answer Validation Exercise [71], the MSRP paraphrase corpus [15] or the SNLI corpus [10]. Most of these tasks and data represent similarity between pairs of text as a binary yes/no classification decision.…”

Section: Claim Accuracy Assessmentmentioning

confidence: 99%

A Content Management Perspective on Fact-Checking

Cazalens

Lamarre

Leblay³

et al. 2018

Companion of the the Web Conference 2018 on the Web Conference 2018 - WWW '18

View full text Add to dashboard Cite

Fact checking has captured the attention of the media and the public alike; it has also recently received strong attention from the computer science community, in particular from data and knowledge management, natural language processing and information retrieval; we denote these together under the term "content management". In this paper, we identify the fact checking tasks which can be performed with the help of content management technologies, and survey the recent research works in this area, before laying out some perspectives for the future. We hope our work will provide interested researchers, journalists and fact checkers with an entry point in the existing literature as well as help develop a roadmap for future research and development work.

show abstract

“…Section 3 presents the results analysis, and Section 4 exposes our conclusions and outlines some future work directions. Table 1 shows the answer validation results corresponding to our two submitted runs to Spanish AVE 2008 [3]. It also shows the results for the baseline (a 100% VALIDATED).…”

Section: Introductionmentioning

confidence: 98%

Analyzing the Use of Non-overlap Features for Supervised Answer Validation

Téllez-Valero¹,

Juárez-González²,

Montes-y-Gómez³

et al. 2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. This year we evaluated our supervised answer validation method at both, the Spanish Answer Validation Exercise (AVE) and the Spanish Question Answering Main Task. This paper describes and analyzes our evaluation results from both tracks. In resume, the F-measure of the proposed method outperformed the baseline result of the AVE 2008 task by more than 100%, and enhanced the performance of our question answering system, showing a gain in accuracy of 22% for answering factoid questions. A detailed analysis of the results shows that the proposed non-overlap features are most discriminative than the traditional overlap ones. In particular, these novel features allowed increasing the F-measure result of our method by 26%.

show abstract

Overview of the Answer Validation Exercise 2008

Cited by 29 publications

References 15 publications

Survey on Answer Validation for Indonesian Question Answering System (IQAS)

Survey on Answer Validation for Indonesian Question Answering System (IQAS)

A Content Management Perspective on Fact-Checking

Analyzing the Use of Non-overlap Features for Supervised Answer Validation

Contact Info

Product

Resources

About