Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, pages 2820–2830, November 16–20, 2020. c⃝2020 Association for Computational Linguistics 2820 Discourse Self-Attention for Discourse Element Identification in Argumentative Student Essays Wei Song1, Ziyao Song1, Ruiji Fu2,3, Lizhen Liu1, Miaomiao Cheng1, Ting Liu4 1College of Information Engineering and Academy for Multidisciplinary Studies, Capital Normal University, Beijing, China 2State Key Laboratory of Cognitive Intelligence, iFLYTEK Research, China 3iFLYTEK AI Research (Hebei), Langfang, China 4Research Center for Social Computing and Information Retrieval, Harbin Institute of Technology, Harbin, China {wsong, zysong, liz liu7480, B365}@cnu.edu.cn, rjfu@iflytek.com, tliu@ir.hit.edu.cn Abstract This paper proposes to adapt self-attention to discourse level for modeling discourse ele- ments in argumentative student essays. Specif- ically, we focus on two issues. First, we propose structural sentence positional encod- ings to explicitly represent sentence positions. Second, we propose to use inter-sentence at- tentions to capture sentence interactions and enhance sentence representation. We con- duct experiments on two datasets: a Chinese dataset and an English dataset. We find that (i) sentence positional encodings can lead to a large improvement for identifying discourse elements; (ii) a structural relative positional en- coding of sentences shows to be most effective; (iii) inter-sentence attention vectors are useful as a kind of sentence representation for identi- fying discourse elements. 1 Introduction Discourse describes how a document is organized. This paper focuses on the task of discourse ele- ment identification (DEI) in argumentative student essays. Discourse elements represent the func- tion and contribution of every discourse unit to the discourse. Burstein et al. (2003) formulate dis- course elements as 5 categories: introduction, the- sis, main idea, supporting and conclusion, while ar- gument components such as major claim, claim and premise are used as discourse elements in argumen- tation structure parsing in persuasive essays (Stab and Gurevych, 2014). DEI can benefit automated essay scoring in many aspects: modeling organi- zation, inferring topics and opinions or used as features for scoring systems (Attali and Burstein, 2006; Burstein et al., 2001; Persing et al., 2010; Song et al., 2020). Despite its importance, DEI is challenging. First, the ambiguity of sentences makes learn- ing models difficult to distinguish some discourse elements. For example, the thesis is defined as expressing the central claim of the author and the main ideas support the thesis from specific aspects. However, it is hard to distinguish them from their content and style. Second, the discourse element of a specific sen- tence depends on context. As a result, considering individual sentences only would have difficulties in identifying discourse elements. The relations and relatedness among multiple sentences should be explored. Third, the data imbalance problem is serious, e.g., the number of elaboration sentences could be 10 times more than the number of thesis sen- tences. The minority discourse elements (such as thesis, main ideas or major claim) are harder to be recalled although they have important roles in many scenarios, e.g., evaluating the organization of essays (Attali and Burstein, 2006). In this paper, we propose a method to explicitly …

Content truncated to 500 words