arXiv subjects

David Carter

Publications and source records attributed to David Carter.

41 records · Page 3Linked to original sources

arXiv1994

CLARE: A Contextual Reasoning and Cooperative Response Framework for the Core Language Engine

This report describes the research, design and implementation work carried out in building the CLARE system at SRI International, Cambridge, England. CLARE was designed as a natural language processing system with facilities for reasoning and understanding in context and for generating cooperative responses. The project involved both further development of SRI's Core Language Engine (Alshawi, 1992, MIT Press) natural language processor and the design and implementation of new components for reasoning and response generation. The CLARE system has advanced the state of the art in a wide variety of areas, both through the use of novel techniques developed on the project, and by extending the coverage or scale of known techniques. The language components are application-independent and provide interfaces for the development of new types of application.

cmp-lg↗

arXiv1994

Improving Language Models by Clustering Training Sentences

Many of the kinds of language model used in speech understanding suffer from imperfect modeling of intra-sentential contextual influences. I argue that this problem can be addressed by clustering the sentences in a training corpus automatically into subcorpora on the criterion of entropy reduction, and calculating separate language model parameters for each cluster. This kind of clustering offers a way to represent important contextual effects and can therefore significantly improve the performance of a model. It also offers a reasonably automatic means to gather evidence on whether a more complex, context-sensitive model using the same general kind of linguistic information is likely to reward the effort that would be required to develop it: if clustering improves the performance of a model, this proves the existence of further context dependencies, not exploited by the unclustered model. As evidence for these claims, I present results showing that clustering improves some models but not others for the ATIS domain. These results are consistent with other findings for such models, suggesting that the existence or otherwise of an improvement brought about by clustering is indeed a good pointer to whether it is worth developing further the unclustered model.

cmp-lg↗

arXiv1994

Training and Scaling Preference Functions for Disambiguation

We present an automatic method for weighting the contributions of preference functions used in disambiguation. Initial scaling factors are derived as the solution to a least-squares minimization problem, and improvements are then made by hill-climbing. The method is applied to disambiguating sentences in the ATIS (Air Travel Information System) corpus, and the performance of the resulting scaling factors is compared with hand-tuned factors. We then focus on one class of preference function, those based on semantic lexical collocations. Experimental results are presented showing that such functions vary considerably in selecting correct analyses. In particular we define a function that performs significantly better than ones based on mutual information and likelihood ratios of lexical associations.

cmp-lg↗

arXiv1994

Estimating Performance of Pipelined Spoken Language Translation Systems

Most spoken language translation systems developed to date rely on a pipelined architecture, in which the main stages are speech recognition, linguistic analysis, transfer, generation and speech synthesis. When making projections of error rates for systems of this kind, it is natural to assume that the error rates for the individual components are independent, making the system accuracy the product of the component accuracies. The paper reports experiments carried out using the SRI-SICS-Telia Research Spoken Language Translator and a 1000-utterance sample of unseen data. The results suggest that the naive performance model leads to serious overestimates of system error rates, since there are in fact strong dependencies between the components. Predicting the system error rate on the independence assumption by simple multiplication resulted in a 16\% proportional overestimate for all utterances, and a 19\% overestimate when only utterances of length 1-10 words were considered.

cmp-lg↗

arXiv1994

Combining Knowledge Sources to Reorder N-Best Speech Hypothesis Lists

A simple and general method is described that can combine different knowledge sources to reorder N-best lists of hypotheses produced by a speech recognizer. The method is automatically trainable, acquiring information from both positive and negative examples. Experiments are described in which it was tested on a 1000-utterance sample of unseen ATIS data.

cmp-lg↗