Showing papers by "Paul Cook published in 2010"

Automatically Identifying Changes in the Semantic Orientation of Words.

Abstract: The meanings of words are not fixed but in fact undergo change, with new word senses arising and established senses taking on new aspects of meaning or falling out of usage Two types of semantic change are amelioration and pejoration; in these processes a word sense changes to become more positive or negative, respectively In this first computational study of amelioration and pejoration we adapt a web-based method for determining semantic orientation to the task of identifying ameliorations and pejorations in corpora from differing time periods We evaluate our proposed method on a small dataset of known historical ameliorations and pejorations, and find it to perform better than a random baseline Since this test dataset is small, we conduct a further evaluation on artificial examples of amelioration and pejoration, and again find evidence that our proposed method is able to identify changes in semantic orientation Finally, we conduct a preliminary evaluation in which we apply our methods to the task of finding words which have recently undergone amelioration or pejoration

Automatically identifying the source words of lexical blends in english

Abstract: Newly coined words pose problems for natural language processing systems because they are not in a system's lexicon, and therefore no lexical information is available for such words. A common way to form new words is lexical blending, as in cosmeceutical, a blend of cosmetic and pharmaceutical. We propose a statistical model for inferring a blend's source words drawing on observed linguistic properties of blends; these properties are largely based on the recognizability of the source words in a blend. We annotate a set of 1,186 recently coined expressions which includes 515 blends, and evaluate our methods on a 324-item subset. In this first study of novel blends we achieve an accuracy of 40% on the task of inferring a blend's source words, which corresponds to a reduction in error rate of 39% over an informed baseline. We also give preliminary results showing that our features for source word identification can be used to distinguish blends from other kinds of novel words.

No Sentence Is Too Confusing To Ignore

Abstract: We consider sentences of the form No X is too Y to Z, in which X is a noun phrase, Y is an adjective phrase, and Z is a verb phrase. Such constructions are ambiguous, with two possible (and opposite!) interpretations, roughly meaning either that "Every X Zs", or that "No X Zs". The interpretations have been noted to depend on semantic and pragmatic factors. We show here that automatic disambiguation of this pragmatically complex construction can be largely achieved by using features of the lexical semantic properties of the verb (i.e., Z) participating in the construction. We discuss our experimental findings in the context of construction grammar, which suggests a possible account of this phenomenon.

Proceedings of the NAACL HLT 2010 Second Workshop on Computational Approaches to Linguistic Creativity

Abstract: It is generally agreed upon that creativity is an important property of human language. For example, speakers routinely coin new words, employ novel metaphors, and play with words through puns. Indeed, such creative processes take place at all levels of language from the lexicon, to syntax, semantics, and discourse. Creativity allows speakers to express themselves with their own individual style. It further provides new ways of looking at the world, by describing something through the use of unusual comparisons for effect or emphasis, and thus making language more engaging and fun. Listeners are typically able to understand creative language without any difficulties. On the other hand, generating and recognizing creative language presents a tremendous challenge for natural language processing (NLP) systems. The recognition of instances of linguistic creativity, and the computation of their meaning, constitute one of the most challenging problems for a variety of NLP tasks, such as machine translation, text summarization, information retrieval, dialog systems, and sentiment analysis. Moreover, models of linguistic creativity are necessary for systems capable of generating story narratives, jokes, or poetry. Nevertheless, despite the importance of linguistic creativity in many NLP tasks, it still remains unclear how to model, simulate, or evaluate linguistic creativity. Furthermore, research on topics related to linguistic creativity has not received a great deal of attention at major computational linguistics conferences in recent years.