This paper presents an automatic system for structuring and preparing a news broadcast for applications such as speech summarization, browsing, archiving and information retrieval. This process comprises transcribing the audio using an automatic speech recognizer and subsequently segmenting the text into utterances and topics. A maximum entropy approach is used to build statistical models for both utterance and topic segmentation. The experimental work addresses the effect on performance of the topic boundary detector of three factors: the information sources used, the quality of the ASR transcripts, and the quality of the utterance boundary detector. The results show that the topic segmentation is not affected severely by transcripts errors, whereas errors in the utterance segmentation are more devastating.

We present an approach to dialogue management and interpretation that evaluates and selects amongst candidate dialogue moves based on features at multiple levels. Multiple interpretation methods can be combined, multiple speech recognition and parsing hypotheses tested, and multiple candidate dialogue moves considered to choose the highest scoring hypothesis overall. We integrate hypotheses generated from shallow slot-filling methods and from relatively deep parsing, using pragmatic information. We show that this gives more robust performance than using either approach alone, allowing n-best list reordering to correct errors in speech recognition or parsing. Index Terms: dialogue management, robust interpretation 1.

Abstract — This paper presents a fully automatic news skimming system which takes a broadcast news audio stream and provides the user with the segmented, structured and highlighted transcript. This constitutes a system with three different, cascading stages: converting the audio stream to text using an automatic speech recogniser, segmenting into utterances and stories and finally determining which utterance should be highlighted using a saliency score. Each stage must operate on the erroneous output from the previous stage in the system; an effect which is naturally amplified as the data progresses through the processing stages. We present a large corpus of transcribed broadcast news data enabling us to investigate to which degree information worth highlighting survives this cascading of processes. Both extrinsic and intrinsic experimental results indicate that mistakes in the story boundary detection has a strong impact on the quality of highlights, whereas erroneous utterance boundaries cause only minor problems. Further, the difference in transcription quality does not affect the overall performance greatly. Index Terms — statistical modelling, spoken language processing, speech understanding, information extraction I.

Recent developments in statistical modeling of various linguistic phenomena have shown that additional features give consistent performance improvements. Quite often, improvements are limited by the number of features a system is able to explore. This paper describes a novel progressive training algorithm that selects features from virtually unlimited feature spaces for conditional maximum entropy (CME) modeling. Experimental results in edit region identification demonstrate the benefits of the progressive feature selection (PFS) algorithm: the PFS algorithm maintains the same accuracy performance as previous CME feature selection algorithms (e.g., Zhou et al., 2003) when the same feature spaces are used. When additional features and their combinations are used, the PFS gives 17.66 % relative improvement over the previously reported best result in edit region identification on Switchboard corpus (Kahn et al., 2005), which leads to a 20 % relative error reduction in parsing the Switchboard corpus when gold edits are used as the upper bound. 1

Reversible stochastic attribute-value grammars (de Kok et al., 2011) use one model for parse disambiguation and fluency ranking. Such a model encodes preferences with respect to syntax, fluency, and appropriateness of logical forms, as weighted features. Reversible models are built on the premise that syntactic preferences are shared between parse disambiguation and fluency ranking. Given that reversible models also use features that are specific to parsing or generation, there is the possibility that the model is trained to rely on these directional features. If this is true, the premise that preferences are shared between parse disambiguation and fluency ranking does not hold. In this work, we compare and apply feature selection techniques to extract the most discriminative features from directional and reversible models. We then analyse the contributions of different classes of features, and show that reversible models do rely on task-independent features. 1

The Workshop on Language Generation and Evaluation (UCNLG+EVAL) took place in Edinburgh on