A supervised learning approach to biological question answering

Authors:
Ryan T. K. Lin;Justin Liang-Te Chiu;Hong-Jie Dai;Richard Tzong-Han Tsai;Min-Yuh Day;Wen-Lian Hsu
Affiliations:
Institute of Information Science, Academia Sinica, Taipei, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan and Department of Computer Science & Information Engineering, National Taiwan University, Taipei, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan and Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan;(Correspd. Tel.: +886 3 4638800 ext. 2367 ext. 7062/ Fax: +886 3 4638850/ E-mail: thtsai@saturn.yzu.edu.tw) Department of Computer Science & Engineering, Yuan Ze University, Taoyuan, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan and Department of Computer Science, National Tsing-Hua University, Hsinchu, Taiwan
Venue:
Integrated Computer-Aided Engineering - Selected papers from the IEEE Conference on Information Reuse and Integration (IRI), July 13-15, 2008
Year:
2009

Citing 18
Cited 6

Approaches to passage retrieval in full text information systems

SIGIR '93 Proceedings of the 16th annual international ACM SIGIR conference on Research and development in information retrieval
A language modeling approach to information retrieval

Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
Expertise identification using email communications

CIKM '03 Proceedings of the twelfth international conference on Information and knowledge management
The derivation of a grammatically indexed lexicon from the Longman Dictionary of Contemporary English

ACL '87 Proceedings of the 25th annual meeting on Association for Computational Linguistics
Question answering passage retrieval using dependency relations

Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Support Vector Learning for Semantic Argument Classification

Machine Learning
Statistical precision of information retrieval evaluation

SIGIR '06 Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval
Bidirectional inference with the easiest-first strategy for tagging sequence data

HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Combining structure and function-based descriptors for component retrieval in software digital libraries

Integrated Computer-Aided Engineering
Detecting data records in semi-structured web sites based on text token clustering

Integrated Computer-Aided Engineering
A knowledge retrieval model using ontology mining and user profiling

Integrated Computer-Aided Engineering
Utilizing phrase-similarity measures for detecting and clustering informative RSS news articles

Integrated Computer-Aided Engineering
Ontology-based inference for causal explanation

Integrated Computer-Aided Engineering
Rule-based dependency models for security protocol analysis

Integrated Computer-Aided Engineering
Exploiting context for biomedical entity recognition: from syntax to the web

JNLPBA '04 Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications
Biomedical named entity recognition using conditional random fields and rich feature sets

JNLPBA '04 Proceedings of the International Joint Workshop on Natural Language Processing in Biomedicine and its Applications
Improving noun phrase coreference resolution by matching strings

IJCNLP'04 Proceedings of the First international joint conference on Natural Language Processing
A supervised learning approach to entity search

AIRS'06 Proceedings of the Third Asia conference on Information Retrieval Technology

An efficient fingerprint image compression technique based on wave atoms decomposition and multistage vector quantization

Integrated Computer-Aided Engineering
Automatic image search based on improved feature descriptors and decision tree

Integrated Computer-Aided Engineering
A study of the application of ontology to an FAQ automatic classification system

Expert Systems with Applications: An International Journal
A model for mining material properties for radiation shielding

Integrated Computer-Aided Engineering
Computationally automated questioning strategies for fast cost functions convergence at supply chain stockout evaluation

Integrated Computer-Aided Engineering
A hybrid linear text segmentation algorithm using hierarchical agglomerative clustering and discrete particle swarm optimization

Integrated Computer-Aided Engineering

Quantified Score

Hi-index	0.00

Visualization

Abstract

Biologists rely on keyword-based search engines to retrieve superficially relevant papers, from which they must filter out the irrelevant information manually. Question answering (QA) systems can offer more efficient and user-friendly ways of retrieving such information. Two contributions are provided in this paper. First, a factoid QA system is developed to employ a named entity recognition module to extract answer candidates and a linear model to rank them. The linear model uses various semantic features, such as named entity types and semantic roles. To tune the weights of features used by the model, a novel supervised learning algorithm, which only needs small amounts of training data, is provided. Second, a QA system may assign several answers with the same score, making evaluation unfair. To solve this problem, an efficient formula for a mean average reciprocal rank (MARR) is proposed to reduce the complexity of its computation. After employing all effective semantic features, our system achieves a top-1 MARR of 74.11% and top-5 MARR of 76.68%. In comparison of the baseline system, the top-1 and top-5 MARR increase by 9.5% and 7.1%. In addition, the experiment result on test set shows our ranking method, which achieves 55.58% top-1 MARR and 66.99% top-5 MARR, significantly surpasses traditional BM25 and simple voting in performance by averagely 35.23% and 36.64%, respectively.