With increasing globalization, communication across language and cultural boundaries is becoming an essential requirement of doing business, delivering education, and providing public services. Due to the considerable cost of human translation services, only a small fraction of text documents and an even smaller percentage of spoken encounters, such as international meetings and conferences, are translated, with most resorting to the use of a common language (e.g. English) or not taking place at all. Technology may provide a potentially revolutionary way out if real-time, domain-independent, simultaneous speech translation can be realized. In this paper, we present a simultaneous speech translation system based on statistical recognition and translation technology. We discuss the technology, various system improvements and propose mechanisms for user-friendly delivery of the result. Over extensive component and end-to-end system evaluations and comparisons with human translation performance, we conclude that machines can already deliver comprehensible simultaneous translation output. Moreover, while machine performance is affected by recognition errors (and thus can be improved), human performance is limited by the cognitive challenge of performing the task in real time.

/pdf/simultaneous-translation-of-lectures-and-speeches-7h65gw4uk4.pdf

Simultaneous translation of lectures and speeches

Punctuation prediction is an important task in Spoken Language Translation. The output of speech recognition systems does not typically contain punctuation marks. In this paper we analyze different methods for punctuation prediction and show improvements in the quality of the final translation output. In our experiments we compare the different approaches and show improvements of up to 0.8 BLEU points on the IWSLT 2011 English French Speech Translation of Talks task using a translation system to translate from unpunctuated to punctuated text instead of a language model based punctuation prediction method. Furthermore, we do a system combination of the hypotheses of all our different approaches and get an additional improvement of 0.4 points in BLEU.

/pdf/modeling-punctuation-prediction-as-machine-translation-3ciboq3tqe.pdf

Modeling punctuation prediction as machine translation.

We report here on the eighth Evaluation Campaign organized by the IWSLT workshop. This year, the IWSLT evaluation focused on the automatic translation of public talks and included tracks for speech recognition, speech translation, text translation, and system combination. Unlike previous years, all data supplied for the evaluation has been publicly released on the workshop website, and is at the disposal of researchers interested in working on our benchmarks and in comparing their results with those published at the workshop. This paper provides an overview of the IWSLT 2011 Evaluation Campaign, which includes: descriptions of the supplied data and evaluation specifications of each track, the list of participants specifying their submitted runs, a detailed description of the subjective evaluation carried out, the main findings of each exercise drawn from the results and the system descriptions prepared by the participants, and, finally, several detailed tables reporting all the evaluation results.

Overview of the IWSLT 2011 evaluation campaign.

Machine translation systems can be classified into rule-based and corpus-based approaches, in terms of their core methodology. Since both paradigms have been largely used during the last years, one of the aims in the research community is to know how these systems differ in terms of translation quality. To this end, this paper reports a study and comparison of several specific Catalan-Spanish machine translation systems: two rule-based and two corpus-based (particularly, statistical-based) systems, all of them freely available on the web. The translation quality analysis is performed under two different domains: journalistic and medical. The systems are evaluated by using standard automatic measures, as well as by native human evaluators. In addition to these traditional evaluation procedures, this paper reports a novel linguistic evaluation, which provides information about the errors encountered at the orthographic, morphological, lexical, semantic and syntactic levels. Results show that while rule-based systems provide a better performance at orthographic and morphological levels, statistical systems tend to commit less semantic errors. Furthermore, results show all the evaluations performed are characterised by some degree of correlation, and human evaluators tend to be specially critical with semantic and syntactic errors.

/pdf/study-and-comparison-of-rule-based-and-statistical-catalan-1yxy5t9j3x.pdf

Study and comparison of rule-based and statistical catalan-spanish machine translation systems

In this paper the statistical machine translation (SMT) systems of RWTH Aachen University developed for the evaluation campaign of the International Workshop on Spoken Language Translation (IWSLT) 2011 is presented. We participated in the MT (English-French, Arabic-English, ChineseEnglish) and SLT (English-French) tracks. Both hierarchical and phrase-based SMT decoders are applied. A number of different techniques are evaluated, including domain adaptation via monolingual and bilingual data selection, phrase training, different lexical smoothing methods, additional reordering models for the hierarchical system, various Arabic and Chinese segmentation methods, punctuation prediction for speech recognition output, and system combination. By application of these methods we can show considerable improvements over the respective baseline systems.

The RWTH Aachen Machine Translation Systems for IWSLT 2017

This paper describes an approach for computing a consensus translation from the outputs of multiple machine translation (MT) systems. The consensus translation is computed by weighted majority voting on a confusion network, similarly to the well-established ROVER approach of Fiscus for combining speech recognition hypotheses. To create the confusion network, pairwise word alignments of the original MT hypotheses are learned using an enhanced statistical alignment algorithm that explicitly models word reordering. The context of a whole corpus of automatic translations rather than a single sentence is taken into account in order to achieve high alignment quality. The confusion network is rescored with a special language model, and the consensus translation is extracted as the best path. The proposed system combination approach was evaluated in the framework of the TC-STAR speech translation project. Up to six state-of-the-art statistical phrase-based translation systems from different project partners were combined in the experiments. Significant improvements in translation quality from Spanish to English and from English to Spanish in comparison with the best of the individual MT systems were achieved under official evaluation conditions.

/pdf/system-combination-for-machine-translation-of-spoken-and-3f7flpstw0.pdf

M. Kolss

Papers

System Combination for Machine Translation of Spoken and Written Language