Marcello Federico

Statistical cross-language information retrieval using n-best query translations

This paper presents a novel statistical model for cross-language information retrieval. Given a written query in the source language, documents in the target language are ranked by integrating probabilities computed by two statistical models: a query-translation model, which generates most probable term-by-term translations of the query, and a query-document model, which evaluates the likelihood of each document and translation. Integration of the two scores is performed over the set of N most probable translations of the query. Experimental results with values N=1, 5, 10 are presented on the Italian-English bilingual track data used in the CLEF 2000 and 2001 evaluation campaigns.

Efficient Handling of N-gram Language Models for Statistical Machine Translation

Statistical machine translation, as well as other areas of human language processing, have recently pushed toward the use of large scale n-gram language models. This paper presents efficient algorithmic and architectural solutions which have been tested within the Moses decoder, an open source toolkit for statistical machine translation. Experiments are reported with a high performing baseline, trained on the Chinese-English NIST 2006 Evaluation task and running on a standard Linux 64-bit PC architecture. Comparative tests show that our representation halves the memory required by SRI LM Toolkit, at the cost of 44% slower translation speed. However, as it can take advantage of memory mapping on disk, the proposed implementation seems to scale-up much better to very large language models: decoding with a 289-million 5-gram language model runs in 2.1Gb of RAM.

Speech Translation by Confusion Network Decoding

This paper describes advances in the use of confusion networks as interface between automatic speech recognition and machine translation. In particular, it presents an implementation of a confusion network decoder which significantly improves both in efficiency and performance previous work along this direction. The confusion network decoder results as an extension of a state-of-the-art phrase-based text translation system. Experimental results in terms of decoding speed and translation accuracy are reported on a real-data task, namely the translation of plenary speeches at the European Parliament from Spanish to English.

System Combination for Machine Translation of Spoken and Written Language

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.

Language modeling and transcription of the TED corpus lectures

Transcribing lectures is a challenging task, both in acoustic and in language modeling. In this work, we present our first results on the automatic transcription of lectures from the TED corpus, recently released by ELRA and LDC. In particular, we concentrated our effort on language modeling. Baseline acoustic and language models were developed using respectively 8 hours of TED transcripts and various types of texts: conference proceedings, lecture transcripts, and conversational speech transcripts. Then, adaptation of the language model to single speakers was investigated by exploiting different kinds of information: automatic transcripts of the talk, the title of the talk, the abstract and, finally, the paper. In the last case, a 39.2% WER was achieved.

A new decoder for spoken language translation based on confusion networks

A novel approach to spoken language translation is proposed, which more tightly integrates automatic speech recognition (ASR) and statistical machine translation (SMT). SMT is directly applied on an approximation of the word graph produced by the ASR system, namely a confusion network. The decoding algorithm extends a conventional phrase-based decoder in that it can process at once a large number of source sentence hypotheses contained in the confusion network. Experimental results are presented on a Spanish-English large vocabulary task, namely the translation of the European Parliament plenary sessions. With respect to a conventional SMT decoder processing N-best lists, a slight improvement in the BLEU score is reported as well as a significantly lower decoding time

Language model representations for beam-search decoding

This paper presents an efficient way of representing a bigram language model for a beam-search based, continuous speech, large vocabulary HMM recognizer. The tree-based topology considered takes advantage of a factorization of the bigram probability derived from the bigram interpolation scheme, and of a tree organization of all the words that can follow a given one. Moreover, an optimization algorithm is used to considerably reduce the space requirements of the language model. Experimental results are provided for two 10,000-word dictation tasks: radiological reporting (perplexity 27) and newspaper dictation (perplexity 120). In the former domain 93% word accuracy is achieved with real-time response and 23 Mb process space. In the newspaper dictation domain, 88.1% word accuracy is achieved with 1.41 real-time response and 38 Mb process space. All recognition tests were performed on an HP-735 workstation.

Morpho-syntactic Information for Automatic Error Analysis of Statistical Machine Translation Output

Evaluation of machine translation output is an important but difficult task. Over the last years, a variety of automatic evaluation measures have been studied, some of them like Word Error Rate (WER), Position Independent Word Error Rate (PER) and BLEU and NIST scores have become widely used tools for comparing different systems as well as for evaluating improvements within one system. However, these measures do not give any details about the nature of translation errors. Therefore some analysis of the generated output is needed in order to identify the main problems and to focus the research efforts. On the other hand, human evaluation is a time consuming and expensive task. In this paper, we investigate methods for using of morpho-syntactic information for automatic evaluation: standard error measures WER and PER are calculated on distinct word classes and forms in order to get a better idea about the nature of translation errors and possibilities for improvements.

Language modelling for efficient beam-search

Abstract This paper considers the problems of estimating bigram language models and of efficiently representing them by a finite state network, which can be employed by a hidden Markov model based, beam-search, continuous speech recognizer. A review of the best known bigram estimation techniques is given together with a description of the original Stacked model. Language model comparisons in terms of perplexity are given for three text corpora with different data sparseness conditions, while speech recognition accuracy tests are presented for a 10 000-word real-time, speaker independent dictation task. The Stacked estimation method compares favourably with the others, by achieving about 93% of word accuracy. If better language model estimates can improve recognition accuracy, representations better suited to the search algorithm can improve its speed as well. Two static representations of language models are introduced: linear and tree-based. Results show that the latter organization is better exploited by the beam-search algorithm as it provides a five times faster response with same word accuracy. Finally, an off-line reduction algorithm is presented that cuts the space requirements of the tree-based topology to about 40%.The proposed solutions presented here have been successfully employed in a real-time, speaker independent, 10 000-word real-time dictation system for radiological reporting.

Neural versus Phrase-Based Machine Translation Quality: a Case Study

Within the field of Statistical Machine Translation (SMT), the neural approach (NMT) has recently emerged as the first technology able to challenge the long-standing dominance of phrase-based approaches (PBMT). In particular, at the IWSLT 2015 evaluation campaign, NMT outperformed well established state-of-the-art PBMT systems on English-German, a language pair known to be particularly hard because of morphology and syntactic differences. To understand in what respects NMT provides better translation quality than PBMT, we perform a detailed analysis of neural versus phrase-based SMT outputs, leveraging high quality post-edits performed by professional translators on the IWSLT data. For the first time, our analysis provides useful insights on what linguistic phenomena are best modeled by neural models -- such as the reordering of verbs -- while pointing out other aspects that remain to be improved.