Traditionally, vector-based semantic space models use word co-occurrence counts from large corpora to represent lexical meaning. In this article we present a novel framework for constructing semantic spaces that take syntactic relations into account. We introduce a formalization for this class of models which allows linguistic knowledge to guide the construction process. We evaluate our framework on a range of tasks relevant for cognitive science and natural language processing: semantic priming, synonymy detection and word sense disambiguation. In all cases, our framework obtains results that are comparable or superior to the state of the art. 1.

We consider the task of unsupervised lecture segmentation. We formalize segmentation as a graph-partitioning task that optimizes the normalized cut criterion. Our approach moves beyond localized comparisons and takes into account longrange cohesion dependencies. Our results demonstrate that global analysis improves the segmentation accuracy and is robust in the presence of speech recognition errors. 1

Abstract not found

The Rich News system, that can automatically annotate radio and television news with the aid of resources retrieved from the World Wide Web, is described. Automatic speech recognition gives a temporally precise but conceptually inaccurate annotation model. Information extraction from related web news sites gives the opposite: conceptual accuracy but no temporal data. Our approach combines the two for temporally accurate conceptual semantic annotation of broadcast news. First low quality transcripts of the broadcasts are produced using speech recognition, and these are then automatically divided into sections corresponding to individual news stories. A key phrases extraction component finds key phrases for each story and uses these to search for web pages reporting the same event. The text and meta-data of the web pages is then used to create index documents for the stories in the original broadcasts, which are semantically annotated using the KIM knowledge management platform. A web interface then allows conceptual search and browsing of news stories, and playing of the parts of the media files corresponding to each news story. The use of material from the World Wide Web allows much higher quality textual descriptions and semantic annotations to be produced than would have been possible using the ASR transcript directly. The semantic annotations can form a part of the Semantic Web, and an evaluation shows that the system operates with high precision, and with a moderate level of recall.

Abstract. Large video collections present a unique set of challenges to the search system designer. Text transcripts do not always provide an accurate index to the visual content, and the performance of visually based semantic extraction techniques is often inadequate for search tasks. The searcher must be relied upon to provide detailed judgment of the relevance of specific video segments. We describe a video search system that facilitates this user task by efficiently presenting search results in semantically meaningful units to simplify exploration of query results and query reformulation. We employ a story segmentation system and supporting user interface elements to effectively present query results at the story level. The system was tested in the 2004 TRECVID interactive search evaluations with very positive results. 1

We address the task of unsupervised topic segmentation of speech data operating over raw acoustic information. In contrast to existing algorithms for topic segmentation of speech, our approach does not require input transcripts. Our method predicts topic changes by analyzing the distribution of reoccurring acoustic patterns in the speech signal corresponding to a single speaker. The algorithm robustly handles noise inherent in acoustic matching by intelligently aggregating information about the similarity profile from multiple local comparisons. Our experiments show that audio-based segmentation compares favorably with transcriptbased segmentation computed over noisy transcripts. These results demonstrate the desirability of our method for applications where a speech recognizer is not available, or its output has a high word error rate. 1

In this paper we introduce a dynamic programming algorithm which performs linear text segmentation by global minimization of a segmentation cost function which incorporates two factors: (a) within-segment word similarity and (b) prior information about segment length. We evaluate segmentation accuracy of the algorithm by precision, recall and Beeferman's segmentation metric.

This work concerns automatic topic segmentation of email conversations. We present a corpus of email threads manually annotated with topics, and evaluate annotator reliability. To our knowledge, this is the first such email corpus. We show how the existing topic segmentation models (i.e., Lexical Chain Segmenter (LCSeg) and Latent Dirichlet Allocation (LDA)) which are solely based on lexical information, can be applied to emails. By pointing out where these methods fail and what any desired model should consider, we propose two novel extensions of the models that not only use lexical information but also exploit finer level conversation structure in a principled way. Empirical evaluation shows that LCSeg is a better model than LDA for segmenting an email thread into topical clusters and incorporating conversation structure into these models improves the performance significantly. 1

We investigate the appropriateness of using a technique based on support vector machines for identifying thematic structure of text streams. The thematic segmentation task is modeled as a binaryclassification problem, where the different classes correspond to the presence or the absence of a thematic boundary. Experiments are conducted with this approach by using features based on word distributions through text. We provide empirical evidence that our approach is robust, by showing good performance on three different data sets. In particular, substantial improvement is obtained over previously published results of worddistribution based systems when evaluation is done on a corpus of recorded and transcribed multi-party dialogs. 1

In this paper we describe a novel approach to lexical chain based segmentation of broadcast news stories. Our segmentation system SeLeCT is evaluated with respect to two other lexical cohesion based segmenters TextTiling and C99. Using the Pk and WindowDiff evaluation metrics we show that SeLeCT outperforms both systems on spoken news transcripts (CNN) while the C99 algorithm performs best on the written newswire collection (Reuters). We also examine the differences between spoken and written news styles and how these differences can affect