Abstract not found

Automatic summarization of open-domain spoken dialogues is a relatively new research area. This article introduces the task and the challenges involved and motivates and presents an approach for obtaining automatic-extract summaries for human transcripts of multiparty dialogues of four different genres, without any restriction on domain. We address the following issues, which are intrinsic to spoken-dialogue summarization and typically can be ignored when summarizing written text such as news wire data: (1) detection and removal of speech disfluencies; (2) detection and insertion of sentence boundaries; and (3) detection and linking of cross-speaker information units (question-answer pairs). A system evaluation is performed using a corpus of 23 dialogue excerpts with an average duration of about 10 minutes, comprising 80 topical segments and about 47,000 words total. The corpus was manually annotated for relevant text spans by six human annotators. The global evaluation shows that for the two more informal genres, our summarization system using dialoguespecific components significantly outperforms two baselines: (1) a maximum-marginal-relevance ranking algorithm using TF*IDF term weighting, and (2) a LEAD baseline that extracts the first n words from a text. 1.

We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the largescale acquisition of word-semantic information, e.g. the construction of domainindependent lexica. The backbone of the annotation are semantic roles in the frame semantics paradigm. We report experiences and evaluate the annotated data from the first project stage. On this basis, we discuss the problems of vagueness and ambiguity in semantic annotation. 1

Annotation projects dealing with complex semantic or pragmatic phenomena face the dilemma of creating annotation schemes that oversimplify the phenomena, or that capture distinctions conventional reliability metrics cannot measure adequately. The solution to the dilemma is to develop metrics that quantify the decisions that annotators are asked to make. This paper discusses MASI, distance metric for comparing sets, and illustrates its use in quantifying the reliability of a specific dataset. Annotations of Summary Content Units (SCUs) generate models referred to as pyramids which can be used to evaluate unseen human summaries or machine summaries. The paper presents reliability results for five pairs of pyramids created for document sets from the 2003 Document Understanding Conference (DUC). The annotators worked independently of each other. Differences between application of MASI to pyramid annotation and its previous application to co-reference annotation are discussed. In addition, it is argued that a paradigmatic reliability study should relate measures of inter-annotator agreement to independent assessments, such as significance tests of the annotated variables with respect to other phenomena. In effect, what counts as sufficiently reliable intera-annotator agreement depends on the use the annotated data will be put to. 1.

We address the problem of distinguishing between two sources of disagreement in annotations: genuine subjectivity and slip of attention. The latter is especially likely when the classification task has a default class, as in tasks where annotators need to find instances of the phenomenon of interest, such as in a metaphor detection task discussed here. We apply and extend a data analysis technique proposed by Beigman Klebanov and Shamir (2006) to first distill reliably deliberate (non-chance) annotations and then to estimate the amount of attention slips vs genuine disagreement in the reliably deliberate annotations. 1

This paper describes a reader-based experiment on lexical cohesion, detailing the task given to readers and the analysis of the experimental data. We conclude with discussion of the usefulness of the data in future research on lexical cohesion.

The purpose of this article is to examine methodological challenges in the study of computer-mediated learning communities and propose strategies for advancing research methodology. Two major methodological issues are addressed. First, there is a growing concern for researchers to address a broader range of social, political, and cultural factors when studying computer-mediated learning communities. A second and related problem concerns challenges about the measurement of learning processes and interactions in computer-mediated learning communities. Advances in second-order cybernetics (Krippendorff, 1991, 1994) and language pragmatics (Searle, 1969) are explored in relation to research methodology requirements for studying computer-mediated learning communities. A conversational system modeling (CSM) strategy is offered as a guide for researchers studying computer-mediated learning communities. The assumption is that learning communities are embedded in complex conversations and sociopolitical and sociocultural influences that must be addressed by research on CMC learning environments.

This study examines the validity of a norm-reinforcement approach as a complementary model to direct media effects on health behavior change. Focusing on news coverage effects on youth binge drinking between 1978 and 1996, it was hypothesized that the media may have contributed to the reduction in this behavior by increasing perceptions of social disapproval.The predictive power of this approach was then compared with that of other plausible models (namely, a direct effect model and a model proposing media effects that are mediated by policy actions). The findings from two separate tests (a timeseries regression and the ideodynamic method) suggest that although a direct route of media effects on binge-drinking behavior produced evidence of null effects, there was evidence that the impact of news stories on this behavior was mediated by policy actions as well as by changes in the social acceptability of this behavior. Implications of this approach to the study of media effects on health behavior change are discussed. Many contemporary public health problems are a consequence of lifestyle behaviors such as smoking, alcohol abuse, and unprotected sex (McGinnis & Foege, 1993). Health communication campaigns have been the primary vehicle for educating the public about the negative consequences of performing these behaviors (J. Brown & Walsh-Childers, 1994; Lapinski & Witte, 1998; Rice & Atkin, 1989). Through the dissemination of persuasive health information to the public, these campaigns seek to influence behavioral attitudes and beliefs that will encourage individuals to quit unhealthy practices. Overall, however, there is little and inconclusive evidence of association between

This dissertation investigates the factors that influence the learning of subsidiaries from their local environment and the sequential knowledge outflow from the subsidiaries. Scholars have recognized the ability to learn from diverse local environments as a critical source of competitive advantage for multinational corporations (MNCs). However, the factors influencing the extent to which MNCs learn from local environments in order to develop innovative capabilities have not been well understood. Considering the complexity of institutional environments faced by subsidiaries, this dissertation explores cross-level factors that influence subsidiary learning from diverse local environments. At interface levels, a subsidiary’s local embeddedness and its learning strategy influence the awareness of local strategic knowledge by the subsidiary. At context levels, local market competition and corporate entrepreneurial culture affect the motivation of a subsidiary to learn from diverse local environments. Finally at subsidiary level, top management team heterogeneity impacts the capability of a subsidiary to learn. This dissertation applies both qualitative and quantitative research methods. Multiplecase studies provide rich details, while survey research tests the generalizability of the proposed

We describe the ongoing construction of a large, semantically annotated corpus resource as reliable basis for the largescale acquisition of word-semantic information, e.g. the construction of domainindependent lexica. The backbone of the annotation are semantic roles in the frame semantics paradigm. We report experiences and evaluate the annotated data from the first project stage. On this basis, we discuss the problems of vagueness and ambiguity in semantic annotation.