Exact phrases in information retrieval for question answering

Stoyanchev, Svetlana; Song, Young Chol; Lahti, William

doi:10.3115/1641451.1641453

Cited by 17 publications

(9 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Stoyanchev S. et al [19] presented a document retrieval experiment on QA and evaluated the use of named entity and nouns, verbs & prepositional phrases as exact match phrases in document retrieval query. Gaizauskeus & Humphrys [3] described an approach that links IR system with NLP system that performs reasonable, kangaveri [8] presented an approach of using knowledge base to improve accuracy that returns the same answer that was submitted previously.…”

Section: B Information Retrievalmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Question answering system: A survey

Mathur

Haider

2015

2015 International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials

View full text Add to dashboard Cite

Question answering (QA) is new research domainin the field of Information Science comes into focus in last few decades. Question answering systems are pretty much different from web based search engines which works on the principal of Information Retrieval(IR), however QA systems works on the concept of Information Retrieval (IR) as well as Information Extraction (IE). Web based search engines takes user's query in natural language and responds the same with references and URLs of related documents and websites, but they failed when a user wants precise answer for their query. By considering these limitations of search engines people finds that there is a need for such a system which answer the user's query rather responds with references or URLs of related documents. User should be provided with the precise answer to their question. They are one step ahead of web search engines which provides relevant documents against users query however QA system provides precise answer. A QA system comprises of three core components question classification, information retrieval and answer extraction module. Answer extraction module distinguishes QA system from web search engines. Question classification module plays an important role in QA since it identifies the type of information user have asked for. Similarly information retrieval is also important, because if none of the retrieved document contains answer sets no further processing can be done.

show abstract

Section: B Information Retrievalmentioning

confidence: 99%

Notice of Violation of IEEE Publication Principles: Question answering system: A survey

Mathur

Haider

2015

2015 International Conference on Smart Technologies and Management for Computing, Communication, Controls, Energy and Materials

View full text Add to dashboard Cite

show abstract

“…Basically, employing a WHY-type question set in the training and attempting to build a typological answer extraction model seems to be promising. Several early attempts such as [16], [17] and [18] also express similar candidate answer formulation models. When it comes to the feature selection and applicability in the question processing steps, model developed by Higashinaka and Isozaki can be considered as a more improved procedure.…”

Section: Related Workmentioning

confidence: 99%

Interaction History Based Answer Formulation for Question Answering

Perera

Nand

2014

Knowledge Engineering and the Semantic Web

View full text Add to dashboard Cite

Abstract. With the rapid growth in information access methodologies, question answering has drawn considerable attention among others. Though question answering has emerged as an interesting new research domain, still it is vastly concentrated on question processing and answer extraction approaches. Latter steps like answer ranking, formulation and presentations are not treated in depth. Weakness we found in this arena is that answers that a particular user has acquired are not considered, when processing new questions. As a result, current systems are not capable of linking two questions such as, "When is the Apple founded?" with a previously processed question "When is the Microsoft founded ?" generating an answer in the form of "Apple is founded one year later Microsoft founded, in 1976". In this paper we present an approach towards question answering to devise an answer based on the questions already processed by the system for a particular user which is termed as interaction history for the user. Our approach is a combination of question processing, relation extraction and knowledge representation with inference models. During the process we primarily focus on acquiring knowledge and building up a scalable user model to formulate future answers based on current answers that same user has processed. According to evaluation we carried out based on the TREC resources shows that proposed technology is promising and effective in question answering.

show abstract

“…The natural language toolkit (NLTK) (Loper and Bird, 2002 Moreover, the study addressed by Stoyanchev et al (2008), which develops a question answering system, employs the NLTK toolkit to analyse questions linguistically. Particularly, the NLTK tool is utilised to extract noun, verb and prepositional phrases (phrase chunking) from two datasets: the AQUAINT corpus (Graff, 2002) (a collection of news documents) and the web.…”

Section: Information Extraction Systemsmentioning

confidence: 99%