Is N-Best Dead?

Is N-Best Dead? Long Nguyen, Richard Schwartz, Ying Zhao, George Zavaliagkos t BBN Systems and Technologies Cambridge, MA 02138 tNortheastern University ABSTRACT We developed a faster search algorithm that avoids the use of the N-Best paradigm until after more powerful knowledge sources have been used. We found, however, that there was little or no decrease in word errors. We then showed that the use of the N-Best paradigm is still essential for the use of still more powerful knowledge sources, and for several other purposes that are outlined in the paper. 1. INTRODUCTION The N-Best Paradigm [1] was introduced originally as a means for integrating the speech recognition and language understanding components of a spoken language system. Since then, we have generalized its use for integrating into the recognition search other expensive knowledge sources (such as higher-order n-gram language models, between- word co-articulation models, and segmental models) with- out increasing the search space [2]. The basic idea is that we use inexpensive knowledge sources to find N alternative sentence hypotheses. Then we rescore each of these hy- potheses with the more expensive and more accurate knowl- edge sources in order to determine the most likely utterance. The N-Best Paradigm specifically, and multi-pass search al- gofithms in general, are now used widely by the speech recognition research community. Besides its use as an efficient search strategy, the N-Best Paradigm has been used extensively in several other ways [2]. Its simplicity has made it ideal as a means for coop- eration between research sites. For example, we regularly send the N-Best lists of alternatives to research sites that do not have an advanced speech recognition capability (e.g., Paramax and NYU) in order that they can apply their own linguistic components for understanding or for research into alternative language modeling techniques. Another related use of the N-Best lists is for evaluation of alternative knowledge sources. New knowledge sources can be evaluated without having to integrate them into the search strategy. For example, we can determine whether a new prosodic module or linguistic knowledge source reduces the error rate when used to reorder the N-Best list. This is particularly important for knowledge sources that are not easily formulated in a left-to-ddght incremental manner. Finally, we have presented techniques for optimizing the weights for different knowledge sources, and for discrimi- native training [2]. In this paper we attempt to determine whether the N-Best Paradigm results in substantial search errors. If it does, then its use for the other purposes mentioned above would also be questionable. First we describe briefly how we used the N-Best paradigm in previous versions of BYBLOS. Then, we descfibe our attempts to avoid the errors that might be a result of using the N-Best paradigm. Finally, we argue that there will always be cases where the N-Best paradigm will make it possible to use some knowledge sources that would likely never be used otherwise. 2. 3-PASS N-BEST SEARCH STRATEGY The BYBLOS system has been described previously (e.g., [3]). We reiterate here …

Content truncated to 500 words