Automatically Inferring Implicit Properties in Similes

Proceedings of NAACL-HLT 2016, pages 1223–1232, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Automatically Inferring Implicit Properties in Similes Ashequl Qadir and Ellen Riloff School of Computing University of Utah Salt Lake City, UT 84112, USA {asheq,riloff}@cs.utah.edu Marilyn A. Walker Natural Language and Dialogue Systems Lab University of California Santa Cruz Santa Cruz, CA 95064, USA mawalker@ucsc.edu Abstract A simile is a figure of speech comparing two fundamentally different things. Sometimes, a simile will explain the basis of a comparison by explicitly mentioning a shared property. For example, “my room is as cold as Antarc- tica” gives “cold” as the property shared by the room and Antarctica. But most similes do not give an explicit property (e.g., “my room feels like Antarctica”) leaving the reader to in- fer that the room is cold. We tackle the prob- lem of automatically inferring implicit prop- erties evoked by similes. Our approach in- volves three steps: (1) generating candidate properties from different sources, (2) evaluat- ing properties based on the influence of mul- tiple simile components, and (3) aggregated ranking of the properties. We also present an analysis showing that the difficulty of infer- ring an implicit property for a simile correlates with its interpretive diversity. 1 Introduction A simile is a figure of speech comparing two essen- tially unlike things, typically using “like” or “as” (Paul, 1970). Comparing fundamentally different types of entities is what makes a simile figurative (Israel et al., 2004). Similes may be closed or open (Beardsley, 1981). A closed simile explains the basis for a comparison by explicitly mentioning a shared property. For example, the simile “my room is as cold as Antarctica” gives “cold” as the prop- erty shared by both the room and Antarctica. But most similes do not explicitly mention the basis for comparison, leaving people to infer what the enti- ties have in common. An open simile expressing the same comparison is “my room feels like Antarc- tica”, where the shared property of being cold is left implicit. In our study of similes in tweets, we found that 92% of similes are open similes so the property must be inferred. Our research tackles this problem of inferring the implicit property evoked by an open simile. Inferring the basis of comparison in a simile is central to natural language understanding and metaphor interpretation. For example, “John was like a lion in battle” is probably a statement about John’s bravery or courage, not a description of John’s physical appearance. Methods to under- stand figurative similes could also be valuable to un- derstand metaphor in other linguistic constructions, such as predicate nominals (e.g., “he is a lion”). Furthermore, identifying the implicit property of a simile could be useful for sentiment analysis, be- cause similes are often used to express positive and negative feelings (Li et al., 2012). For example, “John was like a lion in battle” contains only neutral words, but inferring “bravery” as the implicit prop- erty suggests that the simile has …

Content truncated to 500 words