Answer Extraction by Flexible Matching, Filtering, and Interpretation
نویسندگان
چکیده
This paper describes a Korean Question Answering (KorQuA) system. For flexible text retrieval, we represent terms in a question as five data types, and retrieve passages by matching terms according to these data types. In answer extraction, we filter non-fact answers with negative or uncertain contexts, and interpret a relative expression as an absolute date answer for date type question. Through component analysis, we show that terms need to be matched flexibly according to their characteristics, answer filter make a system more reliable, and answer interpretation make a system more intelligent. We also describe construction of a Korean question answering test collection.
منابع مشابه
A Block-Grouping Method for Image Denoising by Block Matching and 3-D Transform Filtering
Image denoising by block matching and threedimensionaltransform filtering (BM3D) is a two steps state-ofthe-art algorithm that uses the redundancy of similar blocks innoisy image for removing noise. Similar blocks which can havesome overlap are found by a block matching method and groupedto make 3-D blocks for 3-D transform filtering. In this paper wepropose a new block grouping algorithm in th...
متن کاملDesign and Optimization of Neuro-Fuzzy-Based Recognition of Musical Rhythm Patterns
The task of recognizing patterns and assigning rhythmic structure to unquantized musical input is a fundamental one for interactive musical systems and for searching musical databases since melody is based on rhythm. We use a combination of combinatorial pattern matching and structural interpretation with a match quality rating by a neuro-fuzzy system that incorporates musical knowledge and ope...
متن کاملAnswer Filtering via Text Categorization in Question Answering Systems
Modern Information Technologies and Web-based services are faced with the problem of selecting, filtering and managing growing amounts of textual information to which access is usually critical. On one hand, Text Categorization models allow users to browse more easily the set of texts of their own interests, by navigating in category hierarchies. On the other hand, Question/Answering is a metho...
متن کاملQuestions-Réponses en domaine ouvert : sélection pertinente de documents en fonction du contexte de la question. (Open domain question-answering : relevant document selection geared to the question)
Title : Open domain question-answering : relevant document selection geared to the question This thesis aims at defining a unified adaptation of the document selection and answer extraction strategies, based on the document and question types, in a Question-Answering (QA) context. The solution is integrated in RITEL (a LIMSI QA system) to assess the contribution. We develop and investigate a me...
متن کاملFast and Flexible MWE Candidate Generation with the mwetoolkit
We present an experimental environment for computer-assisted extraction of Multiword Expressions (MWEs) from corpora. Candidate extraction works in two steps: generation and filtering. We focus on recent improvements in the former, for which we increased speed and flexibility. We present examples that show the potential gains for users and applications. 1 Project Description The mwetoolkitwas p...
متن کامل