Automatic Extraction of Implicit Interpretations from Modal Constructions

Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1098–1107, Austin, Texas, November 1-5, 2016. c⃝2016 Association for Computational Linguistics Automatic Extraction of Implicit Interpretations from Modal Constructions Jordan Sanders and Eduardo Blanco Human Intelligence and Language Technologies Lab University of North Texas Denton, TX, 76203 jordansanders3@my.unt.edu, eduardo.blanco@unt.edu Abstract This paper presents an approach to extract implicit interpretations from modal construc- tions. Importantly, our approach uses a de- terministic procedure to normalize eventuali- ties and generate potential interpretations. An annotation effort demonstrates that these in- terpretations are intuitive to humans and most modal constructions convey at least one inter- pretation. Experimental results show that the task is challenging but can be automated. 1 Introduction People use language to communicate not only facts, but also intentions, uncertain information and points of view. Modality can be broadly defined as a gram- matical phenomenon used to express the speaker’s opinion or attitude towards a proposition (Lyons, 1977). Modality has also been defined as “the cate- gory of meaning used to talk about possibilities and necessities, essentially, states of affairs beyond the actual.” (Hacquard, 2011). Within computational linguistics, processing modality has proven useful for, among others, recognizing textual entailment (Snow et al., 2006; MacCartney et al., 2006), ma- chine translation (Murata et al., 2005; Baker et al., 2012), and sentiment analysis (Wiebe et al., 2005). In the absence of modality markers, it is un- derstood that the author of a proposition agrees with it (Hengeveld and Mackenzie, 2008). Adding a modality marker—also referred to as cue—casts doubt on the truth of the proposition, e.g., Mary got a new job last week vs. Mary likely got a new job last week. Modality is surprisingly common (Morante and Sporleder, 2012), and notoriously difficult to an- notate and process automatically (Rubinstein et al., 2013; Vincze et al., 2011). In MEDLINE, 11% of sentences contain speculative language (Light et al., 2004) and in biomedical abstracts, 18% (Vincze et al., 2008). Rubin (2006) reports that 59% of state- ments in 80 New York Times articles include epis- temic modality. Despite modality being ubiquitous, there is not an agreed upon annotation schema. In this paper, we extract implicit interpretations intuitively understood by humans when reading modal constructions. We do not follow any specific theory of modality. Instead, we manipulate modal constructions to automatically generate potential in- terpretations, and then assign factuality scores to them. Consider statement (1) below: 1. John likely contracted the disease when a mouse bit him in the Adirondacks. Even though likely syntactically attaches to con- tracted, a natural reading suggests that John con- tracted the disease is factual; the only bit of un- certain information is how (or when) he contracted the disease. In other words, assuming that the au- thor of statement (1) is truthful, event contracted occurred with AGENT John and THEME the disease, but the MANNER (or TIME) may not have been when a mouse bit him in the Adirondacks. A key feature of the work presented in this …

Content truncated to 500 words