Boosting Chinese Question Answering with Two Lightweight Methods

2003

ABSTRACT Document or passage retrieval is typically used as the first step in current question answering systems. The accuracy of the answer that is extracted from the passages and the efficiency of the question answering process will depend to some extent on the quality of this initial ranking. We show how language model approaches can be used to improve answer passage ranking.

Proceedings of the 28th annual …, 2005

State-of-the-art question answering (QA) systems employ termdensity ranking to retrieve answer passages. Such methods often retrieve incorrect passages as relationships among question terms are not considered. Previous studies attempted to address this problem by matching dependency relations between questions and answers.

2007

In this paper, we describe the JAVELIN Cross Language Question Answering system, which includes modules for question analysis, keyword translation, document retrieval, information extraction and answer generation. In the NTCIR6 CLQA2 evaluation, our system achieved 19% and 13% accuracy in the English-to-Chinese and English-to-Japanese subtasks, respectively. An overall analysis and a detailed module-by-module analysis are presented.

2005

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.

China-Ireland International Conference on Information and Communications Technologies (CIICT 2007), 2007

Question-answering (QA) is a next-generation search technology which aims to provide answers to a user's question from a collection of documents. Cross-Language QA (CLQA) extends this paradigm to answering questions from a collection in a different language to the question itself. The accuracy with which a CLQA system answers questions depends on the QA system and translation between the question and the information source. We report results from an evaluation of English-Chinese CLQA comparing question translation using standard machine translation systems and extended translation incorporating web mining to enhance the translation dictionary against a baseline of monolingual Chinese QA. Results from these experiments show that our noun phrase recognition and translation techniques lead to a significant improvement in CLQA effectiveness. Moreover, the syntactic form of a question can be impaired during query translation, and thus potentially degrades the overall CLQA system performance.

Question answering task is now being done in TREC8 using English documents. We examined question answering task in Japanese sentences. Our method selects the answer by matching the question sentence with knowledge-based data written in natural language. We use syntactic information to obtain highly accurate answers. 1 Introduction Question answering task has been done in TREC8 using English documents [1]. Here, we examine question answering task in Japanese sentences 1;2 . Our approach is to use syntactic information. 2 Question Answering System 2.1 Outline 1. The system detects keywords in question sentences, and then detects sentences in which the sum of the keywords' IDF values is high 3 . 2. The question sentences and the detected sentences are parsed by the Japanese syntactic analyzer [8]. (This allows us to obtain the dependency structures.) 3. The answer is selected by matching a question sentence and the detected sentences using syntactic information. How this is ...

2005

2005 International Conference on Natural Language Processing and Knowledge Engineering

Question classification plays an important role in question-answering systems. Chinese question classification is the process that analyzes a question and labels it based on its question type and expected answer type. In this paper, we propose an integrated knowledge-based and machine learning approach for Chinese question classification that focuses on factoid question answering. We develop a Chinese question classification scheme for CLQA CC (Cross Language Question Answering Chinese to Chinese) factoid question answering, and define a coarse-grained and fine-grained classification taxonomy for a Chinese question-answering system. We adopt INFOMAP inference engine to support the knowledge-based approach for Chinese questions, which can be formulated as templates and use SVM (Support Vector Machines) as the machine learning approach for large collections of labeled Chinese questions. Our experimental results show that the accuracy of Chinese question classification using INFOMAP alone is 88%, and 73.5% with SVM alone. In contrast, classification based on a hybrid approach that incorporates SVM and INFOMAP yields an accuracy rate of 92%.

Journal Data & Knowledge Engineering, 2008

In this paper, we discuss a novel technique based on semantic constraints to improve the performance and portability of a reformulation-based question answering system. First, we present a method for acquiring semantic-based reformulations automatically. The goal is to generate patterns from sentences retrieved from the Web based on lexical, syntactic and semantic constraints. Once these constraints have been defined, we present a method to evaluate and re-rank candidate answers that satisfy these constraints using redundancy. The two approaches have been evaluated independently and in combination. The evaluation on 493 questions from TREC-11 shows that the automatically acquired semantic patterns increase the MRR by 26%, the re-ranking using semantic redundancy increases the MRR by 67%, and the two approaches combined increase the MRR by 73%. This new technique allows us to avoid the manual work of formulating semantically equivalent reformulations; while still increasing performance.

Conference and Labs of the Evaluation Forum, 2008

The German question answering (QA) system IRSAW (formerly: InSicht) participated in QA@CLEF for the fifth time. IRSAW was introduced in 2007 by integrating the deep answer producer InSicht, several shallow answer producers, and a logical validator. InSicht builds on a deep QA approach: it transforms documents to semantic representations using a parser, draws inferences on semantic representations with rules, and matches semantic representations derived from questions and documents. InSicht was improved for QA@CLEF 2008 mainly in the following two areas. The coreference resolver was trained on question series instead of newspaper texts in order to be better applicable for follow-up questions. Questions are decomposed by several methods on the level of semantic representations. On the shallow processing side, the number of answer producers was increased from two to four by adding FACT, a fact index, and SHASE, a shallow semantic network matcher. The answer validator introduced in 2007 was replaced by the faster RAVE validator designed for logic-based answer validation under time constraints. Using RAVE for merging the results of the answer producers, monolingual German runs and bilingual runs with source language English and Spanish were produced by applying the machine translation web service Promt. An error analysis shows the main problems for the precision-oriented deep answer producer InSicht and the potential offered by the recalloriented shallow answer producers.