Catálogo de publicaciones - libros

In addition to describing facts and events, texts often communicate information about the attitude of the writer or various participants towards material being described. The most salient clues about attitude are provided by the lexical choice of the writer but, as discussed below, the organization of the text also contributes information relevant to assessing attitude. We argue that the current work in this area that concentrates mainly on the negative or positive attitude communicated by individual terms (Edmonds and Hirst, 2002; Hatzivassiloglou and McKeown, 1997; Turney and Littman, 2002; Wiebe et al., 2001) is incomplete and often gives the wrong results when implemented directly. We then describe how the base attitudinal valence of a lexical item is modified by lexical and discourse context and propose a simple, “proof of concept” implementation for some contextual shifters.

Attribution is a phenomenon of great interest and a principled treatment is important beyond the realm of newspaper articles. The way natural language has evolved to reflect our understanding of attribution in the form of reported speech can guide investigations into principled representations forming the basis for shallow text mining as well as belief revision or maintenance.

A number of attitudinal expressions are identified and analyzed using dependency based syntactic analysis. A claim is made that attitudinal loading of lexical items is dynamic rather than lexical and that attitudinal loading of individual lexical items is acquired through their use in attitudinally loaded structures.

We describe a qualitative analysis of a corpus of clinical genetics patient letters. In this genre, a single letter is intended to serve multiple functions and is designed for multiple audiences. The goal of the analysis was to identify stylistically-related features for a natural language generation system. We found that, perhaps because of the multiple intended functions and audiences, within a single letter more than one writing style (set of realization choices) can be observed, and the sets of features are associated with different perspectives. Thus, an NLG system must take perspective into account to generate stylistically appropriate text in this application. The paper outlines the perspectives and the features associated with each that were identified in the corpus.

A reader’s perception of even an “objective” text is to some degree subjective. We present the results of a pilot study in which we looked at the degree of subjectivity in readers’ perceptions of lexical semantic relations, which are the building blocks of the lexical chains used in many applications in natural language processing. An example is presented in which the subjectivity reflects the reader’s attitude.

The Weighted Referential Activity Dictionary (WRAD) is a dictionary (word list) containing 696 items, with weights ranging between −1 and +1, used for computer modeling of a psycholinguistic variable, Referential Activity (RA), in spoken and written language. The RA dimension concerns the degree to which language reflects connection to nonverbal experience, including imagery, and bodily and emotional experience, and evokes corresponding experience in the listener or reader. RA is primarily indicated by attributes of language style independent of content. High RA language is vivid and evocative; low RA language may be abstract, general, vague or diffuse. RA ratings have been widely used in psycholinguistic and clinical research. RA was initially measured using scales scored by judges; the CRA (Mergenthaler and Bucci, 1999), a binary dictionary, was the first computerized RA measure developed to model judges’ RA ratings. The WRAD, a weighted dictionary, shows higher correlations with RA ratings in all text types tested. The development of the WRAD and its applications are made possible by the authors’ Discourse Attributes Analysis Program (DAAP), which uses smooth local weighted averaging to capture the ebb and flow of RA and similar variables.

This chapter presents a theoretical framework and preliminary results for manual categorization of explicit certainty information in 32 English newspaper articles. Our contribution is in a proposed categorization model and analytical framework for certainty identification. Certainty is presented as a type of subjective information available in texts. Statements with explicit certainty markers were identified and categorized according to four hypothesized dimensions — level, perspective, focus, and time of certainty. The preliminary results reveal an overall promising picture of the presence of certainty information in texts, and establish its susceptibility to manual identification within the proposed four-dimensional certainty categorization analytical framework. Our findings are that the editorial sample group had a significantly higher frequency of markers per sentence than did the sample group of the news stories. For editorials, high level of certainty, writer’s point of view, and future and present time were the most populated categories. For news stories, the most common categories were high and moderate levels, directly involved third party’s point of view, and past time. These patterns have positive practical implications for automation.

In recent work, Wiebe et al. (2003) propose a semantic representation for encoding the opinions and perspectives expressed at any given point in a text. This paper evaluates the opinion annotation scheme for multiperspective vs. fact-based question answering using a new question and answer corpus.

In addition to factual content, many texts contain an emotional dimension. This emotive, or affect, dimension has not received a great amount of attention in computational linguistics until recently. However, now that messages (including spam) have become more prevalent than edited texts (such as newswire), recognizing this emotive dimension of written text is becoming more important. One resource needed for identifying affect in text is a lexicon of words with emotion-conveying potential. Starting from an existing affect lexicon and lexical patterns that invoke affect, we gathered a large quantity of text to measure the coverage of our existing lexicon. This chapter reports on our methods for identifying new candidate affect words and on our evaluation of our current affect lexicons. We describe how our affect lexicon can be extended based on results from these experiments.

A computational semantic lexicon of French verbs of feeling, emotion, and psychological states is presented here, as well as , a software program using this lexicon to provide an interpretation and to generate paraphrases. Semantic representations are described by means of a set of feature structures. Sixty newspaper “letters to the Editor” were taken as a domain for the evaluation of this work.