Ekaterina Shutova

Statistical metaphor processing

Metaphor is highly frequent in language, which makes its computational processing indispensable for real-world NLP applications addressing semantic tasks. Previous approaches to metaphor modeling rely on task-specific hand-coded knowledge and operate on a limited domain or a subset of phenomena. We present the first integrated open-domain statistical model of metaphor processing in unrestricted text. Our method first identifies metaphorical expressions in running text and then paraphrases them with their literal paraphrases. Such a text-to-text model of metaphor interpretation is compatible with other NLP applications that can benefit from metaphor resolution. Our approach is minimally supervised, relies on the state-of-the-art parsing and lexical acquisition technologies (distributional clustering and selectional preference induction), and operates with a high accuracy.

SemEval-2015 Task 11: Sentiment Analysis of Figurative Language in Twitter

This report summarizes the objectives and evaluation of the SemEval 2015 task on the sentiment analysis of figurative language on Twitter (Task 11). This is the first sentiment analysis task wholly dedicated to analyzing figurative language on Twitter. Specifically, three broad classes of figurative language are considered: irony, sarcasm and metaphor. Gold standard sets of 8000 training tweets and 4000 test tweets were annotated using workers on the crowdsourcing platform CrowdFlower. Participating systems were required to provide a fine-grained sentiment score on an 11-point scale (-5 to +5, including 0 for neutral intent) for each tweet, and systems were evaluated against the gold standard using both a Cosinesimilarity and a Mean-Squared-Error measure.

Linguistic properties of multi-word passphrases

We examine patterns of human choice in a passphrase-based authentication system deployed by Amazon, a large online merchant. We tested the availability of a large corpus of over 100,000 possible phrases at Amazons registration page, which prohibits using any phrase already registered by another user. A number of large, readily-available lists such as movie and book titles prove effective in guessing attacks, suggesting that passphrases are vulnerable to dictionary attacks like all schemes involving human choice. Extending our analysis with natural language phrases extracted from linguistic corpora, we find that phrase selection is far from random, with users strongly preferring simple noun bigrams which are common in natural language. The distribution of chosen passphrases is less skewed than the distribution of bigrams in English text, indicating that some users have attempted to choose phrases randomly. Still, the distribution of bigrams in natural language is not nearly random enough to resist offline guessing, nor are longer three- or four-word phrases for which we see rapidly diminishing returns.

Design and evaluation of metaphor processing systems

System design and evaluation methodologies receive significant attention in natural language processing (NLP), with the systems typically being evaluated on a common task and against shared data sets. This enables direct system comparison and facilitates progress in the field. However, computational work on metaphor is considerably more fragmented than similar research efforts in other areas of NLP and semantics. Recent years have seen a growing interest in computational modeling of metaphor, with many new statistical techniques opening routes for improving system accuracy and robustness. However, the lack of a common task definition, shared data set, and evaluation strategy makes the methods hard to compare, and thus hampers our progress as a community in this area. The goal of this article is to review the system features and evaluation strategies that have been proposed for the metaphor processing task, and to analyze their benefits and downsides, with the aim of identifying the desired properties of metaphor processing systems and a set of requirements for their evaluation.

Metaphor Interpretation Using Paraphrases Extracted from the Web

Interpreting metaphor is a hard but important problem in natural language processing that has numerous applications. One way to address this task is by finding a paraphrase that can replace the metaphorically used word in a given context. This approach has been previously implemented only within supervised frameworks, relying on manually constructed lexical resources, such as WordNet. In contrast, we present a fully unsupervised metaphor interpretation method that extracts literal paraphrases for metaphorical expressions from the Web. It achieves a precision of , which is high for an unsupervised paraphrasing approach. Moreover, the method significantly outperforms both the baseline and the selectional preference-based method of Shutova employed in an unsupervised setting.

Conceptual metaphor theory meets the data: a corpus-based human annotation study

Metaphor makes our thoughts more vivid and fills our communication with richer imagery. Furthermore, according to the conceptual metaphor theory (CMT) of Lakoff and Johnson (Metaphors we live by. University of Chicago Press, Chicago, 1980), metaphor also plays an important structural role in the organization and processing of conceptual knowledge. According to this account, the phenomenon of metaphor is not restricted to similarity-based extensions of meanings of individual words, but instead involves activating fixed mappings that reconceptualize one whole area of experience in terms of another. CMT produced a significant resonance in the fields of philosophy, linguistics, cognitive science and artificial intelligence and still underlies a large proportion of modern research on metaphor. However, there has to date been no comprehensive corpus-based study of conceptual metaphor, which would provide an empirical basis for evaluating the CMT using real-world linguistic data. The annotation scheme and the empirical study we present in this paper is a step towards filling this gap. We test our annotation procedure in an experimental setting involving multiple annotators and estimate their agreement on the task. The goal of the study is to investigate (1) how intuitive the conceptual metaphor explanation of linguistic metaphors is for human annotators and whether it is possible to consistently annotate interconceptual mappings; (2) what are the main difficulties that the annotators experience during the annotation process; (3) whether one conceptual metaphor is sufficient to explain a linguistic metaphor or whether a chain of conceptual metaphors is needed. The resulting corpus annotated for conceptual mappings provides a new, valuable dataset for linguistic, computational and cognitive experiments on metaphor.

Literal and Metaphorical Senses in Compositional Distributional Semantic Models

Metaphorical expressions are pervasive in natural language and pose a substantial challenge for computational semantics. The inherent compositionality of metaphor makes it an important test case for compositional distributional semantic models (CDSMs). This paper is the first to investigate whether metaphorical composition warrants a distinct treatment in the CDSM framework. We propose a method to learn metaphors as linear transformations in a vector space and find that, across a variety of semantic domains, explicitly modeling metaphor improves the resulting semantic representations. We then use these representations in a metaphor identification task, achieving a high performance of 0.82 in terms of F-score.

Metaphor: A Computational Perspective

e literary imagination may take flight on the wings of metaphor, but hard-headed scientists are just as likely as doe-eyed poets to reach for a metaphor when the descriptive need arises. Metaphor is a pervasive aspect of every genre of text and every register of speech, and is as useful for describing the inner workings of a “black hole” (itself a metaphor) as it is the affairs of the human heart. e ubiquity of metaphor in natural language thus poses a significant challenge for Natural Language Processing (NLP) systems and their builders, who cannot afford to wait until the problems of literal language have been solved before turning their attention to figurative phenomena. is book offers a comprehensive approach to the computational treatment of metaphor and its figurative brethren—including simile, analogy, and conceptual blending—that does not shy away from their important cognitive and philosophical dimensions. Veale, Shutova, and Beigman Klebanov approach metaphor from multiple computational perspectives, providing coverage of both symbolic and statistical approaches to interpretation and paraphrase generation, while also considering key contributions from philosophy on what constitutes the “meaning” of a metaphor. is book also surveys available metaphor corpora and discusses protocols for metaphor annotation. Any reader with an interest in metaphor, from beginning researchers to seasoned scholars, will find this book to be an invaluable guide to what is a fascinating linguistic phenomenon.

Sense-based Interpretation of Logical Metonymy Using a Statistical Method

The use of figurative language is ubiquitous in natural language texts and it is a serious bottleneck in automatic text understanding. We address the problem of interpretation of logical metonymy, using a statistical method. Our approach originates from that of Lapata and Lascarides (2003), which generates a list of non-disambiguated interpretations with their likelihood derived from a corpus. We propose a novel sense-based representation of the interpretation of logical metonymy and a more thorough evaluation method than that of Lapata and Lascarides (2003). By carrying out a human experiment we prove that such a representation is intuitive to human subjects. We derive a ranking scheme for verb senses using an unannotated corpus, WordNet sense numbering and glosses. We also provide an account of the requirements that different aspectual verbs impose onto the interpretation of logical metonymy. We tested our system on verb-object metonymic phrases. It identifies and ranks metonymic interpretations with the mean average precision of 0.83 as compared to the gold standard.

Black Holes and White Rabbits: Metaphor Identification with Visual Features.

Metaphor is pervasive in our communication, which makes it an important problem for natural language processing (NLP). Numerous approaches to metaphor processing have thus been proposed, all of which relied on linguistic features and textual data to construct their models. Human metaphor comprehension is, however, known to rely on both our linguistic and perceptual experience, and vision can play a particularly important role when metaphorically projecting imagery across domains. In this paper, we present the first metaphor identification method that simultaneously draws knowledge from linguistic and visual data. Our results demonstrate that it outperforms linguistic and visual models in isolation, as well as being competitive with the best-performing metaphor identification methods, that rely on hand-crafted knowledge about domains and perception.