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.

In this paper, we describe NICT’s participation in the IWSLT 2011 evaluation campaign for the ASR Track. To recognize spontaneous speech, we prepared an acoustic model trained by more spontaneous speech corpora and a language model constructed with text corpora distributed by the organizer. We built the multi-pass ASR system by adapting the acoustic and language models with previous ASR results. The target speech was selected from talks on the TED (Technology, Entertainment, Design) program. Here, a large reduction in word error rate was obtained by the speaker adaptation of the acoustic model with MLLR. Additional improvement was achieved not only by adaptation of the language model but also by parallel usage of the baseline and speaker-dependent acoustic models. Accordingly, the final WER was reduced by 30% from the baseline ASR for the distributed test set.

This paper describes the MIT-LL/AFRL statistical MT system and the improvements that were developed during the IWSLT 2011 evaluation campaign. As part of these efforts, we experimented with a number of extensions to the standard phrase-based model that improve performance on the Arabic to English and English to French TED-talk translation tasks. We also applied our existing ASR system to the TED-talk lecture ASR task. We discuss the architecture of the MIT-LL/AFRL MT system, improvements over our 2010 system, and experiments we ran during the IWSLT-2011 evaluation. Specifically, we focus on 1) speech recognition for lecture-like data, 2) cross-domain translation using MAP adaptation, and 3) improved Arabic morphology for MT preprocessing.

In this paper, we provide a description of the Dublin City University’s (DCU) submissions in the IWSLT 2011 evaluationcampaign.1 WeparticipatedintheArabic-Englishand Chinese-English Machine Translation(MT) track translation tasks. We use phrase-based statistical machine translation (PBSMT) models to create the baseline system. Due to the open-domain nature of the data to be translated, we use domain adaptation techniques to improve the quality of translation. Furthermore, we explore target-side syntactic augmentation for an Hierarchical Phrase-Based (HPB) SMT model. Combinatory Categorial Grammar (CCG) is used to extract labels for target-side phrases and non-terminals in the HPB system. Combining the domain adapted language models with the CCG-augmented HPB system gave us the best translations for both language pairs providing statistically significant improvements of 6.09 absolute BLEU points (25.94% relative) and 1.69 absolute BLEU points (15.89% relative) over the unadapted PBSMT baselines for the Arabic-English and Chinese-English language pairs, respectively.

This paper describes NICT’s participation in the IWSLT 2011 evaluation campaign for the TED speech translation ChineseEnglish shared-task. Our approach was based on a phrasebased statistical machine translation system that was augmented in two ways. Firstly we introduced rule-based re-ordering constraints on the decoding. This consisted of a set of rules that were used to segment the input utterances into segments that could be decoded almost independently. This idea here being that constraining the decoding process in this manner would greatly reduce the search space of the decoder, and cut out many possibilities for error while at the same time allowing for a correct output to be generated. The rules we used exploit punctuation and spacing in the input utterances, and we use these positions to delimit our segments. Not all punctuation/spacing positions were used as segment boundaries, and the set of used positions were determined by a set of linguistically-based heuristics. Secondly we used two heterogeneous methods to build the translation model, and lexical reordering model for our systems. The first method employed the popular method of using GIZA++ for alignment in combination with phraseextraction heuristics. The second method used a recentlydeveloped Bayesian alignment technique that is able to perform both phrase-to-phrase alignment and phrase pair extraction within a single unsupervised process. The models produced by this type of alignment technique are typically very compact whilst at the same time maintaining a high level of translation quality. We evaluated both of these methods of translation model construction in isolation, and our results show their performance is comparable. We also integrated both models by linear interpolation to obtain a model that outperforms either component. Finally, we added an indicator feature into the log-linear model to indicate those phrases that were in the intersection of the two translation models. The addition of this feature was also able to provide a small improvement in performance.

This paper describes the Microsoft Research (MSR) system for the evaluation campaign of the 2011 international workshop on spoken language translation. The evaluation task is to translate TED talks (www.ted.com). This task presents two unique challenges: First, the underlying topic switches sharply from talk to talk. Therefore, the translation system needs to adapt to the current topic quickly and dynamically. Second, only a very small amount of relevant parallel data (transcripts of TED talks) is available. Therefore, it is necessary to perform accurate translation model estimation with limited data. In the preparation for the evaluation, we developed two new methods to attack these problems. Specifically, we developed an unsupervised topic modeling based adaption method for machine translation models. We also developed a discriminative training method to estimate parameters in the generative components of the translation models with limited data. Experimental results show that both methods improve the translation quality. Among all the submissions, ours achieves the best BLEU score in the machine translation Chinese-to-English track (MT_CE) of the IWSLT 2011 evaluation that we participated.

LIMSI took part in the IWSLT 2011 TED task in the MT track for English to French using the in-house n-code system, which implements the n-gram based approach to Machine Translation. This framework not only allows to achieve state-of-the-art results for this language pair, but is also appealing due to its conceptual simplicity and its use of well understood statistical language models. Using this approach, we compare several ways to adapt our existing systems and resources to the TED task with mixture of language models and try to provide an analysis of the modest gains obtained by training a log linear combination of inand out-of-domain models.

This paper describes the system developed by the LIG laboratory for the 2011 IWSLT evaluation. We participated to the English-French MT and SLT tasks. The development of a reference translation system (MT task), as well as an ASR output translation system (SLT task) are presented. We focus this year on the SLT task and on the use of multiple 1-best ASR outputs to improve overall translation quality. The main experiment presented here compares the performance of a SLT system where multiple ASR 1-best are combined before translation (source combination), with a SLT system where multiple ASR 1-best are translated, the system combination being conducted afterwards on the target side (target combination). The experimental results show that the second approach (target combination) overpasses the first one, when the performance is measured with BLEU.

This paper presents the KIT system participating in the English→French TALK Translation tasks in the framework of the IWSLT 2011 machine translation evaluation. Our system is a phrase-based translation system using POS-based reordering extended with many additional features. First of all, a special preprocessing is devoted to the Giga corpus in order to minimize the effect of the great amount of noise it contains. In addition, the system gives more importance to the in-domain data by adapting the translation and the language models as well as by using a wordcluster language model. Furthermore, the system is extended by a bilingual language model and a discriminative word lexicon. The automatic speech transcription input usually has no or wrong punctuation marks, therefore these marks were especially removed from the source training data for the SLT system training.

This paper describes the three systems developed by the LIUM for the IWSLT 2011 evaluation campaign. We participated in three of the proposed tasks, namely the Automatic Speech Recognition task (ASR), the ASR system combination task (ASR_SC) and the Spoken Language Translation task (SLT), since these tasks are all related to speech translation. We present the approaches and specificities we developed on each task.

This paper reports on the participation of FBK at the IWSLT 2011 Evaluation: namely in the English ASR track, the Arabic-English MT track and the English-French MT and SLT tracks. Our ASR system features acoustic models trained on a portion of the TED talk recordings that was automatically selected according to the fidelity of the provided transcriptions. Three decoding steps are performed interleaved by acoustic feature normalization and acoustic model adaptation. Concerning the MT and SLT systems, besides language specific pre-processing and the automatic introduction of punctuation in the ASR output, two major improvements are reported over our last year baselines. First, we applied a fill-up method for phrase-table adaptation; second, we explored the use of hybrid class-based language models to better capture the language style of public speeches.

This paper describes our English Speech-to-Text (STT) system for the 2011 IWSLT ASR track. The system consists of 2 subsystems with different front-ends—one MVDR based, one MFCC based—which are combined using confusion network combination to provide a base for a second pass speaker adapted MVDR system. We demonstrate that this set-up produces competitive results on the IWSLT 2010 dev and test sets.

We describe DFKI’s submission to the System Combination and Machine Translation tracks of the 2011 IWSLT Evaluation Campaign. We focus on a sentence selection mechanism which chooses the (hopefully) best sentence among a set of candidates. The rationale behind it is to take advantage of the strengths of each system, especially given an heterogeneous dataset like the one in this evaluation campaign, composed of TED Talks of very different topics. We focus on using features that correlate well with human judgement and, while our primary system still focus on optimizing the BLEU score on the development set, our goal is to move towards optimizing directly the correlation with human judgement. This kind of system is still under development and was used as a secondary submission.

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 Quaero program is an international project promoting research and industrial innovation on technologies for automatic analysis and classification of multimedia and multilingual documents. Within the program framework, research organizations and industrial partners collaborate to develop prototypes of innovating applications and services for access and usage of multimedia data. One of the topics addressed is the translation of spoken language. Each year, a project-internal evaluation is conducted by DGA to monitor the technological advances. This work describes the design and results of the 2011 evaluation campaign. The participating partners were RWTH, KIT, LIMSI and SYSTRAN. Their approaches are compared on both ASR output and reference transcripts of speech data for the translation between French and German. The results show that the developed techniques further the state of the art and improve translation quality.

This paper describes the speech-to-text systems used to provide automatic transcriptions used in the Quaero 2010 evaluation of Machine Translation from speech. Quaero (www.quaero.org) is a large research and industrial innovation program focusing on technologies for automatic analysis and classification of multimedia and multilingual documents. The ASR transcript is the result of a Rover combination of systems from three teams ( KIT, RWTH, LIMSI+VR) for the French and German languages. The casesensitive word error rates (WER) of the combined systems were respectively 20.8% and 18.1% on the 2010 evaluation data, relative WER reductions of 14.6% and 17.4% respectively over the best component system.

Machine translation evaluation campaigns require the production of reference corpora to automatically measure system output. This paper describes recent efforts to create such data with the objective of measuring the quality of the systems participating in the Quaero evaluations. In particular, we focus on the protocols behind such production as well as all the issues raised by the complexity of the transcription data handled.

This paper compares techniques to combine diverse parallel corpora for domain-specific phrase-based SMT system training. We address a common scenario where little in-domain data is available for the task, but where large background models exist for the same language pair. In particular, we focus on phrase table fill-up: a method that effectively exploits background knowledge to improve model coverage, while preserving the more reliable information coming from the in-domain corpus. We present experiments on an emerging transcribed speech translation task – the TED talks. While performing similarly in terms of BLEU and NIST scores to the popular log-linear and linear interpolation techniques, filled-up translation models are more compact and easy to tune by minimum error training.

In statistical machine translation systems, phrases with similar meanings often have similar but not identical distributions of translations. This paper proposes a new soft clustering method to smooth the conditional translation probabilities for a given phrase with those of semantically similar phrases. We call this semantic smoothing (SS). Moreover, we fabricate new phrase pairs that were not observed in training data, but which may be used for decoding. In learning curve experiments against a strong baseline, we obtain a consistent pattern of modest improvement from semantic smoothing, and further modest improvement from phrase pair fabrication.

We discuss learning latent annotations for synchronous context-free grammars (SCFG) for the purpose of improving machine translation. We show that learning annotations for nonterminals results in not only more accurate translation, but also faster SCFG decoding.

In this paper, we propose structure transformation rules for statistical machine translation which are lexicalized by only function words. Although such rules can be extracted from an aligned parallel corpus simply as original phrase pairs, their structure is hierarchical and thus can be used in a hierarchical translation system. In addition, structure transformation rules can take into account long-distance reordering, allowing for more than two phrases to be moved simultaneously. The rule set is used as a core module in our hierarchical model together with two other modules, namely, a basic reordering module and an optional gap phrase module. Our model is considerably more compact and produces slightly higher BLEU scores than the original hierarchical phrase-based model in Japanese-English translation on the parallel corpus of the NTCIR-7 patent translation task.

In this paper we describe some of our recent investigations into ASR and SMT coupling issues from an ASR perspective. Our study was motivated by several areas: Firstly, to understand how standard ASR tuning procedures effect the SMT performance and whether it is safe to perform this tuning in isolation. Secondly, to investigate how vocabulary and segmentation mismatches between the ASR and SMT system effect the performance. Thirdly, to uncover any practical issues that arise when using a WFST based speech decoder for tight coupling as opposed to a more traditional tree-search decoding architecture. On the IWSLT07 Japanese-English task we found that larger language model weights only helped the SMT performance when the ASR decoder was tuned in a sub-optimal manner. When we considered the performance with suitable wide beams that ensured the ASR accuracy had converged we observed the language model weight had little influence on the SMT BLEU scores. After the construction of the phrase table the actual SMT vocabulary can be less than the training data vocabulary. By reducing the ASR lexicon to only cover the words the SMT system could accept, we found this lead to an increase in the ASR error rates, however the SMT BLEU scores were nearly unchanged. From a practical point of view this is a useful result as it means we can significantly reduce the memory footprint of the ASR system. We also investigated coupling WFST based ASR to a simple WFST based translation decoder and found it was crucial to perform phrase table expansion to avoid OOV problems. For the WFST translation decoder we describe a semiring based approach for optimizing the log-linear weights.

Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over the sentence pair [1]. The boundaries of the target phrase are chosen such that the overall sentence alignment probability is optimal. Viterbi alignment information is also added in the extended model with a view of improving phrase alignment. We extract phrase pairs using a relatively larger number of features which are discriminatively trained using a large-margin online learning algorithm, i.e., Margin Infused Relaxed Algorithm (MIRA) and integrate it in our approach. Initial experiments show improvements in both phrase alignment and translation quality for Arabic-English on a moderate-size translation task.

Many syntactic machine translation decoders, including Moses, cdec, and Joshua, implement bottom-up dynamic programming to integrate N-gram language model probabilities into hypothesis scoring. These decoders concatenate hypotheses according to grammar rules, yielding larger hypotheses and eventually complete translations. When hypotheses are concatenated, the language model score is adjusted to account for boundary-crossing n-grams. Words on the boundary of each hypothesis are encoded in state, consisting of left state (the first few words) and right state (the last few words). We speed concatenation by encoding left state using data structure pointers in lieu of vocabulary indices and by avoiding unnecessary queries. To increase the decoder’s opportunities to recombine hypothesis, we minimize the number of words encoded by left state. This has the effect of reducing search errors made by the decoder. The resulting gain in model score is smaller than for right state minimization, which we explain by observing a relationship between state minimization and language model probability. With a fixed cube pruning pop limit, we show a 3-6% reduction in CPU time and improved model scores. Reducing the pop limit to the point where model scores tie the baseline yields a net 11% reduction in CPU time.