Automated Question Answering: Review of the Main Approaches

Andrenucci, Andrea; Sneiders, Eriks

doi:10.1109/icita.2005.78

Cited by 44 publications

(36 citation statements)

References 21 publications

(22 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Example: 1) $department-department*, section*, building*, room*, lab*, field Synonym file: dprtmnt-dprtmnt*, setn*, bldng*, rm*, lb*, fld* 2) $go -get, reach, find 3) $describe -describ*, depict*, illustr*, specif*, character*, clarif* To improve the quality of the synonyms list, we also have identified the usage of WordNet [5] through which we can expand our query terms.…”

Section: How To Enhance Template Matchingmentioning

confidence: 99%

See 1 more Smart Citation

Performance Evaluation Techniques for an Automatic Question Answering System

Gunawardena¹,

Pathirana²,

Lokuhetti³

et al. 2015

IJMLC

View full text Add to dashboard Cite

Section: How To Enhance Template Matchingmentioning

confidence: 99%

“…RELATED WORK Automated Question Answering [5] discusses template-based approach in details. Text Retrieval Conference (TREC) [6].…”

Section: Introductionmentioning

confidence: 99%

Performance Evaluation Techniques for an Automatic Question Answering System

Gunawardena¹,

Pathirana²,

Lokuhetti³

et al. 2015

IJMLC

View full text Add to dashboard Cite

“…R contains a set of Av and Au is sequence of text, they are be a pair of ngrams in X and Y. Let R : x 1 … x k and Au : y 1 … y l (9) Where and contains at least one complete n-gram. Researcher used n-gram, to find the similarity between Du and Ds and consider the position of letter so researcher will find similarity even not really exact.…”

Section: Algorithm Of Finding Structured-unstructured Featuresmentioning

confidence: 99%

“…[9] explains 3 mains questionanswering approaches based on Natural Language Processing, Information Retrieval, and question templates. [10] proposed another approaches according to the resource on the web.…”

Section: Introductionmentioning

confidence: 99%

Finding Structured and Unstructured Features to Improve the Search Result of Complex Question

Wardani¹

2012

Jurnal Sistem Informasi

View full text Add to dashboard Cite

The current researches on question answer usually achieve the answer only from unstructured text resources such as collection of news or pages. According to our observation from Yahoo!Answer, users sometimes ask in complex natural language questions which contain structured and unstructured features. Generally, answering the complex questions needs to consider not only unstructured but also structured resource. In this work, researcher propose a new idea to improve accuracy of the answers of complex questions by recognizing the structured and unstructured features of questions and them in the web. Our framework consists of three parts: Question Analysis, Resource Discovery, and Analysis of The Relevant Answer. In Question Analysis researcher used a few assumptions and tried to find structured and unstructured features of the questions. In the resource discovery researcher integrated structured data (relational database) and unstructured data (web page) to take the advantage of two kinds of data to improve and to get the correct answers. We can find the best top fragments from context of the relevant web pages in the Relevant Answer part and then researcher made a score matching between the result from structured data and unstructured data, then finally researcher used QA template to reformulate the questions.

show abstract

“…Streamlining the formulation of questions has been addressed through several approaches ( [1]). In [5] authors have developed a catalog of question templates to facilitate query formulation, where users must define a corresponding scenario for each query.…”

Section: Introductionmentioning

confidence: 99%

Developing Query Patterns

Constantopoulos

Dritsou

Foustoucos

2009

Research and Advanced Technology for Digital Libraries

View full text Add to dashboard Cite

Abstract. Query patterns enable effective information tools and provide guidance to users interested in posing complex questions about objects. Semantically, query patterns represent important questions, while syntactically they impose the correct formulation of queries. In this paper we address the development of query patterns at successive representation layers so as to expose dominant information requirements on one hand, and structures that can support effective user interaction and efficient implementation of query processing on the other. An empirical study for the domain of cultural heritage reveals an initial set of recurrent questions, which are then reduced to a modestly sized set of query patterns. A set of Datalog rules is developed in order to formally define these patterns which are also expressed as SPARQL queries.

show abstract

Automated Question Answering: Review of the Main Approaches

Cited by 44 publications

References 21 publications

Performance Evaluation Techniques for an Automatic Question Answering System

Performance Evaluation Techniques for an Automatic Question Answering System

Finding Structured and Unstructured Features to Improve the Search Result of Complex Question

Developing Query Patterns

Contact Info

Product

Resources

About