An effective approach for automatic interpretation of Chinese nominal compounds
| Pages | 101-106 |
| Date | 15 May 2017 |
| DOI | https://doi.org/10.1108/IDD-01-2017-0007 |
| Published date | 15 May 2017 |
| Author | Weiguang Qu,Rubing Dai,Taizhong Wu,Jian Liu,Junsheng Zhou,Yanhui Gu,Ge Xu |
| Subject Matter | Library & information science,Library & information services,Lending,Document delivery,Collection building & management,Stock revision,Consortia |
An effective approach for automatic
interpretation of Chinese nominal compounds
Weiguang Qu
School of Computer Science and Technology, Nanjing Normal University, Nanjing, China and
Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou, China
Rubing Dai
School of Chinese Language and Literature, Nanjing Normal University, Nanjing, China
Taizhong Wu, Jian Liu, Junsheng Zhou and Yanhui Gu
School of Computer Science and Technology, Nanjing Normal University, Nanjing, China, and
Ge Xu
Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, Minjiang University, Fuzhou, China
Abstract
Purpose – Automatic interpretation of Nominal Compounds is a crucial issue for many applications, for example, sentence understanding, machine
translation, question-answering system and so forth. Many automatic interpretation models of Nominal Compounds use the strategies based on
verbs or rules to obtain the interpretation of compounds. However, the performances of these models are still limited. The purpose of this paper
is to propose an effective approach for automatic interpretation of Chinese nominal compounds.
Design/methodology/approach – The authors propose a top-down and bottom-up model based on rules and large-scale corpus for automatic
interpretation of Nominal Compounds.
Findings – Experimental results demonstrate that the proposed model outperforms the state-of-the-art automatic interpretation model.
Originality/value – The paper is an up-to-date study of automatic interpretation for Nominal Compounds. It can help people understand the
meaning of Nominal Compounds in reading. With a better understanding of Nominal Compounds, we can discover more hidden knowledge in them.
Keywords Information technology, Resources, Information retrieval, Resource management, Information management, Research
Paper type Research paper
Introduction
Automatic interpretation aims to construct the interpretation
of text which represents semantic meanings and help people
understand text better. Chinese Nominal Compound is a
phrase that contains two nouns which are constituted together
directly (Ma, 1999), for example, “huanjing wenti, 环境 问题
(Environmental issues)” and “pingguo shouji, 苹果 手机
(iPhone)”, which is common in social media data. In syntax
analysis, the Nominal Compounds can be classified into four
types of relation: head-modifier relation, coordinate relation,
appositive relation and subject-predicate relation. Automatic
interpretation of Chinese Nominal Compound could be
applied to dig out the semantics under Nominal Compounds
for further analysis and applications, such as information
retrieval (Wei and Yuan, 2014), sentence understanding,
machine translation, question-answering system and so forth.
For example, social media is growing rapidly and provides
large-scale text for research (Effing and Spil, 2016). Some
compounds in these texts cannot be understood and often
cause misunderstanding, such as “苹果 手机 (iPhone)” may
be misunderstood as “苹果和手机 (apple and phone)”. If we
can paraphrase “苹果 手机”as“苹果公司生产的手机 (phone
produced by Apple Inc.)”, then we could understand the
knowledge of the whole text better.
The automatic interpretation models of Nominal
Compounds mainly apply three strategies: top-down strategy
(Levin, 1978;Zhao et al., 2007;Su and Baldwin, 2006;Li,
2009;Butnariu and Veale, 2008), bottom-up strategy (Nakov
and Hearst, 2006;Nakov, 2008;Li et al., 2010;Wang et al.,
2010,2016;Pasca, 2015a,2015b) and top-down and
bottom-up strategy (Wei and Yuan, 2014).
Top-down strategies use the semantic relations predefined
to obtain the interpretation of Nominal Compounds, which is
similar to pattern recognition task. Zhao et al. (2007) apply a
The current issue and full text archive of this journal is available on
Emerald Insight at: www.emeraldinsight.com/2398-6247.htm
Information Discovery and Delivery
45/2 (2017) 101–106
© Emerald Publishing Limited [ISSN 2398-6247]
[DOI 10.1108/IDD-01-2017-0007]
This work is partially supported by projects 61272221, 61472191 under
the National Natural Science Foundation of China, project 12YYA002
under Jiangsu Province Fund of Social Science, project 15KJA420001
under the Natural Science Research of Jiangsu Higher Education
Institutions of China, project MJUKF201705 under Open Fund Project of
Fujian Provincial Key Laboratory of Information Processing and
Intelligent Control (Minjiang University) and project 211180A41601
under Open Project of Shandong Provincial Key Laboratory of Language
Resource Development and Application.
Received 20 January 2017
Revised 24 March 2017
Accepted 3 April 2017
101
To continue reading
Request your trial