Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 5833 - 5847 December 7-11, 2022 ©2022 Association for Computational Linguistics Leveraging Affirmative Interpretations from Negation Improves Natural Language Understanding Md Mosharaf Hossain8,U∗and Eduardo Blanco7 8Department of Computer Science and Engineering, University of North Texas UAmazon 7Department of Computer Science, University of Arizona mdmosharafhossain@my.unt.edu hosmdmos@amazon.com eduardoblanco@arizona.edu Abstract Negation poses a challenge in many natural lan- guage understanding tasks. Inspired by the fact that understanding a negated statement often requires humans to infer affirmative interpre- tations, in this paper we show that doing so benefits models for three natural language un- derstanding tasks. We present an automated procedure to collect pairs of sentences with negation and their affirmative interpretations, resulting in over 150,000 pairs. Experimental results show that leveraging these pairs helps (a) T5 generate affirmative interpretations from negations in a previous benchmark, and (b) a RoBERTa-based classifier solve the task of nat- ural language inference. We also leverage our pairs to build a plug-and-play neural generator that given a negated statement generates an af- firmative interpretation. Then, we incorporate the pretrained generator into a RoBERTa-based classifier for sentiment analysis and show that doing so improves the results. Crucially, our proposal does not require any manual effort. 1 Introduction Natural Language Understanding is a crucial com- ponent to build intelligent systems that interact with humans seamlessly. While recent papers some- times report so-called superhuman performance, simple adversarial attacks including adding nega- tion and other input modifications remain a chal- lenge despite they are obvious to humans (Naik et al., 2018; Wallace et al., 2019). Further, many researchers have found that state-of-the-art systems struggle with texts containing negation. For ex- ample, Kassner and Schütze (2020) show that pre- trained language models such as BERT (Devlin et al., 2019) do not differentiate between negated and non-negated cloze questions (e.g., Birds can- not [MASK] vs. Birds can [MASK]). Other stud- ies show that transformers perform much worse in many other natural language understanding ∗Work was done prior to joining Amazon. English-Norwegian (en-no) parallel sentences: (en) There is no more than one Truth. (no) Og det finnes kun en Sannhet. Backtranslation: And there is only one truth. English-Spanish (en-es) parallel sentences: (en) The term gained traction only after 1999. (es) El término no se popularizó hasta después del 1999. Backtranslation: The term was not popular until 1999. Figure 1: Parallel sentences from bitext corpora (English-Norwegian and English-Spanish) and back- translations into English. Either the original English sentence or the backtranslation contains a negation, and the other one is an affirmative interpretation. In this paper, we show that leveraging sentences with nega- tion and their affirmative interpretations is beneficial for several natural language understanding tasks including natural language inference and sentiment analysis. tasks when there is a negation in the input sen- tence (Ribeiro et al., 2020; Ettinger, 2020; Hossain et al., 2020b; Hosseini et al., 2021; Hossain et al., 2022a; Truong et al., 2022). In this paper, we address this challenge building …

Content truncated to 500 words