Predicting the Focus of Negation: Model and Error Analysis

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 8389–8401 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 8389 Predicting the Focus of Negation: Model and Error Analysis Md Mosharaf Hossain* Kathleen Hamilton** Alexis Palmer** Eduardo Blanco* *Department of Computer Science and Engineering, University of North Texas mdmosharafhossain@my.unt.edu, eduardo.blanco@unt.edu **Department of Linguistics, University of North Texas kathleenhamilton@my.unt.edu, alexis.palmer@unt.edu Abstract The focus of a negation is the set of tokens intended to be negated, and a key component for revealing affirmative alternatives to negated utterances. In this paper, we experiment with neural networks to predict the focus of negation. Our main novelty is leveraging a scope detector to introduce the scope of negation as an addi- tional input to the network. Experimental re- sults show that doing so obtains the best results to date. Additionally, we perform a detailed error analysis providing insights into the main error categories, and analyze errors depending on whether the model takes into account scope and context information. 1 Introduction Negation is a complex phenomenon present in all human languages. Horn (2010) put it beautifully when he wrote “negation is what makes us human, imbuing us with the capacity to deny, to contra- dict, to misrepresent, to lie, and to convey irony.” Broadly speaking, negation “relates an expression e to another expression with a meaning that is in some way opposed to the meaning of e” (Horn and Wansing, 2017). The key challenge to under- standing negation is thus to figure out the meaning that is in some way opposed to e—a semantic and highly ambiguous undertaking that comes naturally to humans in everyday communication. Negation is generally understood to carry pos- itive meaning, or in other words, to suggest an affirmative alternative. For example, John didn’t leave the house implicates that John stayed inside the house. Hasson and Glucksberg (2006) show that comprehending negation involves considering the representation of affirmative alternatives. While not fully understood, there is evidence that nega- tion involves reduced access to the affirmative men- tal representation (Djokic et al., 2019). Orenes et al. (2014) provide evidence that humans switch to the affirmative alternative in binary scenarios (e.g., from not red to green when processing The figure could be red or green. The figure is not red). In such multary scenarios, however, humans keep the negated representation unless the affirmative in- terpretation is obvious from context (e.g., humans keep not red when processing The figure is red, green, yellow or blue. The figure is not red.). From a linguistic perspective, negation is under- stood in terms of scope and focus (Section 2). The scope is the part of the meaning that is negated, and the focus is the part of the scope that is most prominently or explicitly negated (Huddleston and Pullum, 2002). Identifying the focus is a semantic task, and it is critical for revealing implicit affir- mative alternatives. Indeed, the focus of negation usually contains only a few tokens, and it is rarely grammatically …

Content truncated to 500 words