Kay Peterson

Balancing Expressiveness and Simplicity in an Interlingua for Task Based Dialogue

In this paper we compare two interlingua representations for speech translation. The basis of this paper is a distributional analysis of the C-STAR II and NESPOLE databases tagged with interlingua representations. The C-STAR II database has been partially re-tagged with the NESPOLE interlingua, which enables us to make comparisons on the same data with two types of interlinguas and on two types of data (C-STAR II and NESPOLE) with the same interlingua. The distributional information presented in this paper show that the NESPOLE interlingua maintains the language-independence and simplicity of the C-STAR II speech-act-based approach, while increasing semantic expressiveness and scalability.

The NIST 2008 Metrics for machine translation challenge--overview, methodology, metrics, and results

This paper discusses the evaluation of automated metrics developed for the purpose of evaluating machine translation (MT) technology. A general discussion of the usefulness of automated metrics is offered. The NIST MetricsMATR evaluation of MT metrology is described, including its objectives, protocols, participants, and test data. The methodology employed to evaluate the submitted metrics is reviewed. A summary is provided for the general classes of evaluated metrics. Overall results of this evaluation are presented, primarily by means of correlation statistics, showing the degree of agreement between the automated metric scores and the scores of human judgments. Metrics are analyzed at the sentence, document, and system level with results conditioned by various properties of the test data. This paper concludes with some perspective on the improvements that should be incorporated into future evaluations of metrics for MT evaluation.

A Thai speech translation system for medical dialogs

In this paper we present our activities towards a Thai Speech-to-Speech translation system. We investigated in the design and implementation of a prototype system. For this purpose we carried out research on bootstrapping a Thai speech recognition system, developing a translation component, and building an initial Thai synthesis system using our existing tools.

Domain portability in speech-to-speech translation

Speech-to-speech translation has made significant advances over the past decade, with several high-visibility projects (C-STAR, Verb-mobil, the Spoken Language Translator, and others) significantly advancing the state-of-the-art. While speech recognition can currently effectively deal with very large vocabularies and is fairly speaker independent, speech translation is currently still effective only in limited, albeit large, domains. The issue of domain portability is thus of significant importance, with several current research efforts designed to develop speech-translation systems that can be ported to new domains with significantly less time and effort than is currently possible.

Spoken Language Parsing Using Phrase-Level Grammars and Trainable Classifiers

In this paper, we describe a novel approach to spoken language analysis for translation, which uses a combination of grammar-based phrase-level parsing and automatic classification. The job of the analyzer is to produce a shallow semantic interlingua representation for spoken task-oriented utterances. The goal of our hybrid approach is to provide accurate real-time analyses while improving robustness and portability to new domains and languages.

Speech-to-Speech translation services for the olympic games 2008

In 2008 the Olympics Games will be held in Beijing. For this purpose the city government of Beijing has launched the Special Programme for Construction of Digital Olympics. One of the objectives of the program is the use of artificial intelligence technology to overcome language barriers during the games. In order to demonstrate the contribution that speech-to-speech translation technology (SST) can make to solving this problem and in order to prove the feasibility of deploying such technology in the environment of the Olympic Games 2008 in Beijing, we have developed the Digital Olympics Speech-to-Speech Translation System that addresses a general touristic domain with a special focus on pre-arrival hotel reservation. The system allows for rapid development of SST prototypes, the study of different user-interfaces and the on-the-fly comparison of alternative approaches to the individual problems involved in this task.

A Speech-to-Speech Translation System for Catalan, Spanish, and English

In this paper we describe the FAME interlingual speech-to- speech translation System for Spanish, Catalan and English which is intended to assist users in the reservation of a hotel room when calling or visiting abroad. The System has been developed as an extension of the existing NESPOLE! translation system [4] which translates between English, German, Italian and French. After a brief introduction we describe the Spanish and Catalan System components including speech recognition, transcription to IF mapping, IF to text generation and speech synthesis. We also present a task-oriented evaluation method used to inform about system development and some preliminary results.

Overview of the NIST 2016 LoReHLT Evaluation

Initiated in conjunction with DARPA’s low resource languages for emergent incidents (LORELEI) Program, the NIST LoReHLT (Low Resource Human Language Technology) evaluation series seeks to incubate research on fundamental natural language processing tasks in under-resourced languages. While part of the LORELEI program, LoReHLT is an open evaluation workshop that anyone may participate in, with its first evaluation taking place in July 2016. Eight teams, out of the 21 teams that registered, participated in the evaluation over three tasks—machine translation, named entity recognition, and situation frame—in the surprise language Uyghur.