Articles

A purely functional implementation of LR-parsers is given, together with a simple correctness proof. It is presented as a generalization of the recursive descent parser. For non-LR grammars the time-complexity of our parser is cubic if the functions that constitute the parser are implemented as memo-functions, i.e. func- tions that …...

This paper describes a computational model of human sentence processing based on the principles and pa- rameters paradigm of current linguistic theory. The syntactic processing model posits four modules, re- covering phrase structure, long-distance dependencies, coreference, and thematic structure. These four mod- ules are implemented as recta-interpreters over their relevant …...

of seven types of structural ambiguity. In addition, it ap- ~ ~ ~ ~ f i ~ ~ t ~ have shown that prosody is used by human ]is- peared that the relative size and location of prosodic phrase teners to disambiguate spoken language and, in particular, that boundaries provided …...

Relating the intonational characteristics of an utter- ance to other features inferable from its text is impor- tant both for speech recognition and for speech syn- thesis. This work investigates techniques for predicting the location of intonational phrase boundaries in natural speech, through analyzing a utterances from the DARPA Air …...

Prosodic structure and syntactic structure are not identical; neither are they unrelated. Knowing when and how the two eorrespoud could yield better quality speech synthesis, could aid in the disambiguation of com- peting syntactic hypotheses in speech understanding, and could lead to a more comprehensive view of human speech processing. …...

As part of our development of a spoken language system in the ATIS domain, we have begun a smail-scale effort in collecting spontaneous speech data. Our procedure differs from the one used at 'i~xas Instruments (TI) in many respects, the most important being the reliance on an existing system, rather …...

This paper describes the present status of the discourse and dialogue models within the MIT ATIS system, extended to sup- port the notion of booking a flight. The discourse model includes not only the resolution of explicit anaphoric references, but also indirect and direct references to information mentioned earlier in …...

This paper describes an implemented program that takes a tagged text corpus and generates a partial list of the subcategorization frames in wtfich each verb occurs. The completeness of the out- put list increases monotonically with the total occurrences of each verb in the training corpus. False positive rates are …...

Ordinarily, one thinks of the problem of natural language un- derstanding as one of making a single, left-to-right pass through an input, producing a progressively refined and detailed interpre- tation. In text interpretation, however, the constraints of strict left-to-right processing are an encumbrance. Multi-pass meth- ods, especially by interpreting words …...

In a natural dialog, a considerable proportion of the utterances actually relate to the maintenance of the dialog itself rather than to furthering the task or goals motivating the conversation. For example, many utterances serve to acknowledge, clarify, correct a previous utterance rather than pursue some goal in the domain. …...

The SIS community has made progress recently toward evaluating SLS systems that deal with dialogue, but there is still considerable work that needs to be done in this area. Our goal is to develop incremental ways to evaluate dialogue processing, not just going from Class D1 (dialogue pairs) to Class …...

While certain standard procedures are widely used for evalu- ating text retrieval systems and algorithms, the sarne is not true for text categorization. Omission of important data from reports is common and methods of measuring effectiveness vary widely. This ]'ms m~de judging the relative merits of techniques for text categorization …...

We report here on our experiments with POST (Part of Speech Tagger) to address problems of ambiguity and of understanding unknown words. Part of speech tagging, per se, is a well understood problem. Our paper reports experiments in three important areas: handling unknown words, limiting the size of the training …...

A probabilistic approach to lexieal access from a recognized phone sequence is presented. Lexical access is seen as finding the word se- quence that maximizes the lexical likelihood of a sequence of phones and durations as recognized by a phone recognizer. This is theoretically correct for minimum error rate recognition …...

In the case of a trlgr~m language model, the proba- bility of the next word conditioned on the previous two words is estimated from a large corpus of text. The re- sulting static trigram language model (STLM) has fixed probabilities that are independent of the document being dictated. To improve …...

Speaker-independent system is desirable in many applications where speaker-specific data do not exist. However, if speaker- dependent data are available, the system could be adapted to the specific speaker such that the error rate could be signifi- cantly reduced. In this paper, DARPA Resource Management task is used as the …...

An investigation into the use of Bayesian learning of the parame- ters of a multivariate Gaassian mixture density has been carried out. In a continuous density hidden Markov model (CDHMM) framework, Bayesian learning serves as a unified approach for parameter smooth- ing, speaker adaptation, speaker clustering, and corrective training. The …...

In a continuous speech recognition system it is impor- tant to model the context dependent variations in the pro- nunciations of words. In this paper we present an automatic method for modeling phonological variation using decision trees. For each phone we construct a decision tree that spec- ifies the acoustic …...

This paper reports recent efforts to improve the performance of CMU's robust vocabulary-independent (VI) speech recog- nition systems on the DARPA speaker-independent resource management task. The improvements are evaluated on 320 sentences that randomly selected from the DARPA June 88, February 89 and October 89 test sets. Our first improvement …...

We present the concept of a "Segmental Neural Net" (SNN) for phonetic modeling in continuous speech recognition. The SNN takes as input all the frames of a phonetic segment and gives as output an estimate of the probability of each of the phonemes, given the input segment. By tak- ing …...