Mark E. Epstein

Statistical natural language understanding using hidden clumpings

We present a new approach to natural language understanding (NLU) based on the source-channel paradigm, and apply it to ARPAs Air Travel Information Service (ATIS) domain. The model uses techniques similar to those used by IBM in statistical machine translation. The parameters are trained using the exact match algorithm; a hierarchy of models is used to facilitate the bootstrapping of more complex models from simpler models.

Automatic phonetic baseform determination

The authors describe a series of experiments in which the phonetic baseform is deduced automatically for new words by utilizing actual utterances of the new word in conjunction with a set of automatically derived spelling-to-sound rules. Recognition performance was evaluated on new words spoken by two different speakers when the phonetic baseforms were extracted via the above approach. The error rates on these new words were found to be comparable to or better than when the phonetic baseforms were derived by hand, thus validating the basic approach.<<ETX>>

Intertask communications in an integrated multirobot system

An integrated multirobot system (IMRS) consists of two or more robots, machinery, and sensors and is capable of executing almost all industrial processes with efficiency, flexibility, and reliability. Although the IMRS is motivated by an interesting application, it is essentially a distributed real-time processing system with various heterogeneous processes. To support a distributed modular architecture of the IMRS, low-level communication primitives are proposed along with their supporting language syntax which are typical of real-time concurrent programming languages. This is done by 1) carefully examining the generic structure and interactions of IMRS processes, 2) comparing and analyzing the primitives and syntax developed/proposed for general concurrent programming, and 3) using port-directed communications.

Method and apparatus for translating natural-language speech using multiple output phrases

A multi-lingual translation system that provides multiple output sentences for a given word or phrase. Each output sentence for a given word or phrase reflects, for example, a different emotional emphasis, dialect, accents, loudness or rates of speech. A given output sentence could be selected automatically, or manually as desired, to create a desired effect. For example, the same output sentence for a given word or phrase can be recorded three times, to selectively reflect excitement, sadness or fear. The multi-lingual translation system includes a phrase-spotting mechanism, a translation mechanism, a speech output mechanism and optionally, a language understanding mechanism or an event measuring mechanism or both. The phrase-spotting mechanism identifies a spoken phrase from a restricted domain of phrases. The language understanding mechanism, if present, maps the identified phrase onto a small set of formal phrases. The translation mechanism maps the formal phrase onto a well-formed phrase in one or more target languages. The speech output mechanism produces high-quality output speech. The speech output may be time synchronized to the spoken phrase using the output of the event measuring mechanism.

Fertility Models for Statistical Natural Language Understanding

Several recent efforts in statistical natural language understanding (NLU) have focused on generating clumps of English words from semantic meaning concepts (Miller et al., 1995; Levin and Pieracini, 1995; Epstein et al., 1996; Epstein, 1996). This paper extends the IBM Machine Translation Groups concept of fertility (Brown et al., 1993) to the generation of clumps for natural language understanding. The basic underlying intuition is that a single concept may be expressed in English as many disjoint clump of words. We present two fertility models which attempt to capture this phenomenon. The first is a Poisson model which leads to appealing computational simplicity. The second is a general nonparametric fertility model. The general models parameters are boot-strapped from the Poisson model and updated by the EM algorithm. These fertility models can be used to impose clump fertility structure on top of preexisting clump generation models. Here, we present results for adding fertility structure to unigram, bigram, and headword clump generation models on ARPAs Air Travel Information Service (ATIS) domain.

Communication primitives for a distributed multi-robot system

An integrated multi-robot system (IMRS) consists of two or more robots, machinery and sensors, and is capable of executing almost all industrial processes with efficiency, flexibility and reliability. In order to support a distributed, modular architecture of an IMRS in [SHIN84], we propose in this paper low-level communication and synchronization primitives for the IMRS. This is done by comparing and analyzing the primitives developed/proposed for general concurrent programming, and carefully examining the generic structure and interactions of IMRS processes.

Processing dual tone multi-frequency signals for use with a natural language understanding system

A method for processing dual tone multi-frequency signals for use with a natural language understanding system can include several steps. The step of determining whether a audio input signal is a dual tone multi-frequency signal or a human speech signal can be included. If the audio input signal is determined to be a dual tone multi-frequency signal, the audio input signal can be converted to at least one text equivalent. Also, the step of providing the at least one text equivalent to a natural language understanding system can be included. The natural language understanding system can determine a meaning from the text equivalent.

Improved language modeling for conversational applications using sentence quality

In this paper, we propose a new approach to build language models for conversationals system using a a corpus of text as a opposed to a live or a Wizard-of-Oz collection. Each sentence in the corpus is assigned a “quality” that reflects the developers intuition for how likely that sentence is to be spoken by a real user to the live system. Language Models (LM) are built for each sentence quality and these are subsequently interpolated to produce the final model. We also have built a classifier that assigns sentence qualities to the data, and whose subsequent language models achive similar improvements in word and turn error rate.