The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Refletindo o rápido crescimento da tecnologia da informação, a configuração de aplicativos de software, como processadores de texto e planilhas, é ao mesmo tempo sofisticada e complicada. Muitas vezes é difícil para os usuários identificarem funções relevantes no manual on-line para uma aplicação alvo. Neste artigo, propomos um método de resposta a perguntas que encontra funções relacionadas à solicitação do usuário. Para aprimorar nosso método, abordamos dois problemas de “incompatibilidade”. O primeiro problema está associado a uma incompatibilidade de vocabulário, onde o mesmo conceito é representado por palavras diferentes no manual e na pergunta do usuário. O segundo problema está associado a uma incompatibilidade de função. Embora o usuário possa ter uma função hipotética para um propósito em mente, esse propósito às vezes pode ser alcançado por outras funções. Para resolver esses problemas de incompatibilidade, extraímos da Web termos relacionados às funções de software, para que a pergunta do usuário possa ser correspondida à função relevante com alta precisão. Demonstramos a eficácia do nosso método experimentalmente.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Atsushi FUJII, Seiji TAKEGATA, "Question Answering for the Operation of Software Applications: A Document Retrieval Approach" in IEICE TRANSACTIONS on Information,
vol. E93-D, no. 6, pp. 1369-1377, June 2010, doi: 10.1587/transinf.E93.D.1369.
Abstract: Reflecting the rapid growth of information technology, the configuration of software applications such as word processors and spreadsheets is both sophisticated and complicated. It is often difficult for users to identify relevant functions in the online manual for a target application. In this paper, we propose a method for question answering that finds functions related to the user's request. To enhance our method, we addressed two "mismatch" problems. The first problem is associated with a mismatch in vocabulary, where the same concept is represented by different words in the manual and in the user's question. The second problem is associated with a mismatch in function. Although the user may have a hypothetical function for a purpose in mind, this purpose can sometimes be accomplished by other functions. To resolve these mismatch problems, we extract terms related to software functions from the Web, so that the user's question can be matched to the relevant function with high accuracy. We demonstrate the effectiveness of our method experimentally.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E93.D.1369/_p
Copiar
@ARTICLE{e93-d_6_1369,
author={Atsushi FUJII, Seiji TAKEGATA, },
journal={IEICE TRANSACTIONS on Information},
title={Question Answering for the Operation of Software Applications: A Document Retrieval Approach},
year={2010},
volume={E93-D},
number={6},
pages={1369-1377},
abstract={Reflecting the rapid growth of information technology, the configuration of software applications such as word processors and spreadsheets is both sophisticated and complicated. It is often difficult for users to identify relevant functions in the online manual for a target application. In this paper, we propose a method for question answering that finds functions related to the user's request. To enhance our method, we addressed two "mismatch" problems. The first problem is associated with a mismatch in vocabulary, where the same concept is represented by different words in the manual and in the user's question. The second problem is associated with a mismatch in function. Although the user may have a hypothetical function for a purpose in mind, this purpose can sometimes be accomplished by other functions. To resolve these mismatch problems, we extract terms related to software functions from the Web, so that the user's question can be matched to the relevant function with high accuracy. We demonstrate the effectiveness of our method experimentally.},
keywords={},
doi={10.1587/transinf.E93.D.1369},
ISSN={1745-1361},
month={June},}
Copiar
TY - JOUR
TI - Question Answering for the Operation of Software Applications: A Document Retrieval Approach
T2 - IEICE TRANSACTIONS on Information
SP - 1369
EP - 1377
AU - Atsushi FUJII
AU - Seiji TAKEGATA
PY - 2010
DO - 10.1587/transinf.E93.D.1369
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E93-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2010
AB - Reflecting the rapid growth of information technology, the configuration of software applications such as word processors and spreadsheets is both sophisticated and complicated. It is often difficult for users to identify relevant functions in the online manual for a target application. In this paper, we propose a method for question answering that finds functions related to the user's request. To enhance our method, we addressed two "mismatch" problems. The first problem is associated with a mismatch in vocabulary, where the same concept is represented by different words in the manual and in the user's question. The second problem is associated with a mismatch in function. Although the user may have a hypothetical function for a purpose in mind, this purpose can sometimes be accomplished by other functions. To resolve these mismatch problems, we extract terms related to software functions from the Web, so that the user's question can be matched to the relevant function with high accuracy. We demonstrate the effectiveness of our method experimentally.
ER -