ASQA: Academia Sinica Question Answering System for NTCIR-5 CLQA

نویسندگان

  • Cheng-Wei Lee
  • Cheng-Wei Shih
  • Min-Yuh Day
  • Richard Tzong-Han Tsai
  • Mike Tian-Jian Jiang
  • Chia-Wei Wu
  • Cheng-Lung Sung
  • Yu-Ren Chen
  • Shih-Hung Wu
  • Wen-Lian Hsu
چکیده

We propose a hybrid architecture for the NTCIR-5 CLQA C-C (Cross Language Question Answering from Chinese to Chinese) Task. Our system, the Academia Sinica Question-Answering System (ASQA), outputs exact answers to six types of factoid question: personal names, location names, organization names, artifacts, times, and numbers. The architecture of ASQA comprises four main components: Question Processing, Passage Retrieval, Answer Extraction, and Answer Ranking. ASQA successfully combines machine learning and knowledge-based approaches to answer Chinese factoid questions, achieving 37.5% and 44.5% Top1 accuracy for correct, and correct+unsupported answers, respectively.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Chinese-Chinese and English-Chinese Question Answering with ASQA at NTCIR-6 CLQA

For NTCIR-6 CLQA, we improved our question answering system ASQA (Academia Sinica Question Answering System), which participated in NTCIR-5 CLQA, so that it could deal with the Chinese-Chinese (C-C) subtask and the English-Chinese (E-C) subtask. There are three innovations in the improved system: (a) to handle the E-C subtask, we have built an English question classifier that adopts Question In...

متن کامل

Complex Question Answering with ASQA at NTCIR 7 ACLIA

At NTCIR 7, we implemented the Academia Sinica Question Answering (ASQA) system for complex questions. The system uses three methods to select answer strings from a news corpus. (a) It uses syntactic patterns, which are usually used by QA systems, to retrieve more precise answer strings than those derived by traditional IR. (b) Using external knowledge, the system can find accurate answers to s...

متن کامل

Overview of the NTCIR-6 Cross-Lingual Question Answering (CLQA) Task

This paper describes an overview of the NTCIR-6 Cross-Lingual Question Answering (CLQA) Task, an evaluation campaign for Cross-Lingual Question Answering technology. In NTCIR-5, the first CLQA task targeting Chinese, English, and Japanese languages was carried out. Following the success of NTCIR-5 CLQA, NTCIR-6 hosted the second campaign on the CLQA task. Since the handling of Named Entities is...

متن کامل

Japanese-to-English and English-to-Japanese Cross-Language Question-Answering System Using Decreased Adding with Multiple Answers at NTCIR-5

We describe a method of using multiple documents with decreasing weights as evidence to improve the performance of a question-answering system and how it was employed in cross-language question answering (CLQA) tasks at NTCIR-5. Sometimes, the answer to a question may be found in multiple documents. In such cases, using multiple documents for prediction would generate better answers than using ...

متن کامل

Chinese QA and CLQA: NTCIR-5 QA Experiments at UNT

This paper describes our participation in the NTCIR-5 CLQA task. Three runs were officially submitted for three subtasks: Chinese Question Answering, English-Chinese Question Answering, and Chinese-English Question Answering. We expanded our TREC experimental QA system EagleQA this year to include Chinese QA and Cross-Language QA capabilities. Various information retrieval and natural language ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2005