Yanfen Hao

An Ironic Fist in a Velvet Glove: Creative Mis-Representation in the Construction of Ironic Similes

Irony is an effective but challenging mode of communication that allows a speaker to express viewpoints rich in sentiment with concision, sharpness and humour. Creative irony is especially common in online documents that express subjective and deeply-felt opinions, and thus represents a significant obstacle to the accurate analysis of sentiment in web texts. In this paper we look at one commonly used framing device for linguistic irony—the simile—to show how even the most creative uses of irony are often marked in ways that make them computationally feasible to detect. We conduct a very large corpus analysis of web-harvested similes to identify the most interesting characteristics of ironic comparisons, and provide an empirical evaluation of a new algorithm for separating ironic from non-ironic similes.

A Fluid Knowledge Representation for Understanding and Generating Creative Metaphors

Creative metaphor is a phenomenon that stretches and bends the conventions of semantic description, often to humorous and poetic extremes. The computational modeling of metaphor thus requires a knowledge representation that is just as stretchable and semantically accommodating. We present here a flexible knowledge representation for metaphor interpretation and generation, called Talking Points, and describe how talking points can be acquired on a large scale from WordNet (Fellbaum, 1998) and from the web. We show how talking points can be fluidly connected to form a slipnet, and demonstrate that talking points provide an especially concise representation for concepts in general.

A context-sensitive framework for lexical ontologies

Human categorization is neither a binary nor a context-free process. Rather, the criteria that govern the use and recognition of certain concepts may be satisfied to different degrees in different contexts. In light of this reality, the idealized, static structure of a lexical-ontology like WordNet appears both excessively rigid and unduly fragile when faced with real texts that draw upon different contexts to communicate different world-views. In this paper we describe a syntagmatic, corpus-based approach to redefining the concepts of a lexical-ontology like WordNet in a functional, gradable and context-sensitive fashion. We describe how the most diagnostic properties of concepts, on which these functional definitions are based, can be automatically acquired from the Web, and demonstrate how these properties are more predictive of how concepts are actually used and perceived than properties derived from other sources (such as WordNet itself).

In the mood for affective search with web stereotypes

Models of sentiment analysis in text require an understanding of what kinds of sentiment-bearing language are generally used to describe specific topics. Thus, fine-grained sentiment analysis requires both a topic lexicon and a sentiment lexicon, and an affective mapping between both. For instance, when one speaks disparagingly about a city (like London, say), what aspects of city does one generally focus on, and what words are used to disparage those aspects? As when we talk about the weather, our language obeys certain familiar patterns - what we might call clichés and stereotypes - when we talk about familiar topics. In this paper we describe the construction of an affective stereotype lexicon, that is, a lexicon of stereotypes and their most salient affective qualities. We show, via a demonstration system called MOODfinger, how this lexicon can be used to underpin the processes of affective query expansion and summarization in a system for retrieving and organizing news content from the Web. Though we adopt a simple bipolar +/- view of sentiment, we show how this stereotype lexicon allows users to coin their own nuanced moods on demand.