Automatic Generation and Scoring of Positive Interpretations from Negated Statements

Proceedings of NAACL-HLT 2016, pages 1431–1441, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Automatic Generation and Scoring of Positive Interpretations from Negated Statements Eduardo Blanco and Zahra Sarabi Human Intelligence and Language Technologies Lab University of North Texas Denton, TX, 76203 eduardo.blanco@unt.edu, zahrasarabi@my.unt.edu Abstract This paper presents a methodology to extract positive interpretations from negated state- ments. First, we automatically generate plau- sible interpretations using well-known gram- mar rules and manipulating semantic roles. Second, we score plausible alternatives ac- cording to their likelihood. Manual annota- tions show that the positive interpretations are intuitive to humans, and experimental results show that the scoring task can be automated. 1 Introduction Negation is an intricate phenomenon present in all human languages (Hoeksema, 2000), and studied from a theoretical perspective since Aristotle. Ac- quiring and understanding negation is more chal- lenging than language in general: children acquire negation after learning to communicate (Nordmeyer and Frank, 2013), and adults take longer to pro- cess negative sentences than positive ones (Clark and Chase, 1972). In any given language, humans communicate in positive terms most of the time, and use negation to express something unusual or an ex- ception (Horn, 1989). In classical logic, negation is a simple unary op- erator that reverses the truth value of a proposi- tion. In natural language, negation is always marked (Horn and Wansing, 2015) and it is used to re- verse polarity, i.e., turning something affirmative into negative, or something negative into affirma- tive. Albeit most sentences are affirmative, negation is rather ubiquitous (Morante and Sporleder, 2012): In scientific papers, 13.76% of statements contain a negation (Szarvas et al., 2008); in product reviews, 19% (Councill et al., 2010); and in a selection of Conan Doyle stories, 22.23% (Morante and Daele- mans, 2012). In health records, 12.3% of concepts are tagged as negated (Elkin et al., 2005); and in OntoNotes (Hovy et al., 2006), 10.15% of state- ments contain a verb negated with not, n’t or never. From a theoretical perspective, it is accepted that negation conveys positive meaning (Rooth, 1992; Huddleston and Pullum, 2002). For example, when reading (1) John doesn’t eat meat, humans intu- itively understand that (1a) John eats something other than meat, and (1b) Some people eat meat, but not John. Extracting positive interpretations from negated statements automatically is not straightfor- ward: a negated statement may convey one or more positive interpretations, and not all positive interpre- tations are equally likely. For example, from (2) They didn’t order the right parts, it is very likely that (2a) They ordered the wrong parts, but (2b) Some- body ordered the right parts, but not they is unlikely. This paper presents a methodology to automati- cally extract and score positive interpretations from negated statements, as intuitively done by humans when reading text. A key feature of the work pre- sented here is that it is not tied to any existing ap- proach to extract meaning from text—we generate positive interpretations in plain text, and these pos- …

Content truncated to 500 words