Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning

Multilingual Metaphor Processing: Experiments with Semi-Supervised and Unsupervised Learning Ekaterina Shutova∗ University of Cambridge Lin Sun∗∗ Greedy Intelligence Elkin Dar´ıo Guti´errez† University of California, San Diego Patricia Lichtenstein‡ University of California, Merced Srini Narayanan§ Google Research Highly frequent in language and communication, metaphor represents a significant challenge for Natural Language Processing (NLP) applications. Computational work on metaphor has traditionally evolved around the use of hand-coded knowledge, making the systems hard to scale. Recent years have witnessed a rise in statistical approaches to metaphor processing. How- ever, these approaches often require extensive human annotation effort and are predominantly evaluated within a limited domain. In contrast, we experiment with weakly supervised and unsupervised techniques—with little or no annotation—to generalize higher-level mechanisms of metaphor from distributional properties of concepts. We investigate different levels and types of supervision (learning from linguistic examples vs. learning from a given set of metaphorical mappings vs. learning without annotation) in flat and hierarchical, unconstrained and con- strained clustering settings. Our aim is to identify the optimal type of supervision for a learning algorithm that discovers patterns of metaphorical association from text. In order to investigate ∗ Computer Laboratory, William Gates Building, Cambridge CB3 0FD, UK. E-mail: es407@cam.ac.uk. ∗∗ Greedy Intelligence Ltd, Hangzhou, China. E-mail: lin.sun@greedyint.com. † Department of Cognitive Science, 9500 Gilman Dr, La Jolla, CA 92093, USA. E-mail: e4gutier@ucsd.edu. ‡ Department of Cognitive and Information Sciences, UC Merced, 5200 Lake Rd Merced, CA 95343, USA. E-mail: plichtenstein@ucmerced.edu. § Google, Brandschenkestrasse 110, 8002 Zurich, Switzerland. E-mail: srinin@google.com. Submission received: 28 September 2015; revised version received: 19 February 2016; accepted for publication: 29 May 2016. doi:10.1162/COLI a 00275 © 2017 Association for Computational Linguistics Published under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) license Computational Linguistics Volume 43, Number 1 the scalability and adaptability of our models, we applied them to data in three languages from different language groups—English, Spanish, and Russian—achieving state-of-the-art results with little supervision. Finally, we demonstrate that statistical methods can facilitate and scale up cross-linguistic research on metaphor. 1. Introduction Metaphor brings vividness, distinction, and clarity to our thought and communica- tion. At the same time, it plays an important structural role in our cognition, helping us to organize and project knowledge (Lakoff and Johnson 1980; Feldman 2006) and guide our reasoning (Thibodeau and Boroditsky 2011). Metaphors arise from system- atic associations between distinct, and seemingly unrelated, concepts. For instance, when we talk about “the turning wheels of a political regime,” “rebuilding the campaign machinery” or “mending foreign policy,” we view politics and political systems in terms of mechanisms—they can function, break, be mended, have wheels, and so forth. The existence of this association allows us to transfer knowledge and inferences from the domain of mechanisms to that of political systems. As a result, we reason about political systems in terms of mechanisms and discuss them using the mechanism terminology in a variety of metaphorical expressions. The view of metaphor as a mapping between two distinct domains was echoed by numerous theories in …

Content truncated to 500 words