A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, pages 5206–5215, Hong Kong, China, November 3–7, 2019. c⃝2019 Association for Computational Linguistics 5206 A Context-based Framework for Modeling the Role and Function of On-line Resource Citations in Scientific Literature He Zhao1, Zhunchen Luo2, Chong Feng1†, Anqing Zheng1, Xiaopeng Liu2 1Beijng Institute of Technology, School of Computer Science, Beijing, China 2Information Research Center of Military Science, PLA Academy of Military Science, Beijing, China zhaohe1995@outlook.com zhunchenluo@gmail.com fengchong@bit.edu.cn aqzheng1995@outlook.com liuxiaopeng1975@163.com Abstract We introduce a new task of modeling the role and function for on-line resource citations in scientific literature. By categorizing the on- line resources and analyzing the purpose of resource citations in scientific texts, it can greatly help resource search and recommen- dation systems to better understand and man- age the scientific resources. For this novel task, we are the first to create an annotation scheme, which models the different granu- larity of information from a hierarchical per- spective. And we construct a dataset SciRes, which includes 3,088 manually annotated re- source contexts. In this paper, we propose a possible solution by using a multi-task frame- work to build the scientific resource classifier (SciResCLF) for jointly recognizing the role and function types. Then we use the classifi- cation results to help a scientific resource rec- ommendation (SciResREC) task. Experiments show that our model achieves the best results on both the classification task and the recom- mendation task. The SciRes dataset1 will be released for future research. 1 Introduction In this paper, we introduce a new task of modeling the role and function for on-line resource citations in scientific literature. With the number of scien- tific publications growing dramatically, numerous on-line resources are mentioned, released and used within the scientific literature. Tracing and mod- eling these resources such as software, tools and datasets can greatly help researchers by develop- ing scientific resource searching and recommen- dation systems or constructing scientific resource knowledge graphs. Google has launched a new search engine2 in 2018 to help scientists find the †Corresponding author. 1https://github.com/zhaohe1995/SciRes 2https://toolbox.google.com/ datasetsearch Figure 1: Examples for the two types of resource ci- tations in scientific literature. We note the arguments (which are mostly the key verbs before the citation) for identifying the resource function and the arguments (which are mostly the target nominals before the cita- tion) for identifying the resource role. datasets they need, whereas the retrieved datasets can only be matched with their official names. Other current academic search engines such as Google Scholar can be only used for detecting the relevant papers where a certain resource is men- tioned. However, the limitation actually exists is that the user can not learn more fine-grained infor- mation such as what role the resource plays in its paper and why the resource is cited in its contexts. To improve present works, we propose a context- based framework to model both the resource role and the resource function for on-line resource …

Content truncated to 500 words