No full-text available
To read the full-text of this research,
you can request a copy directly from the author.
Application 2: Machine Translation
Abstract
Throughout the previous chapters, we have demonstrated that MWEs are a source of errors for machine translation (MT) systems and for human non-native speakers of a language. As Manning and Schütze (1999, p. 184) point out, “a nice way to test whether a combination is a collocation [MWE] is to translate it into another language. If we cannot translate the combination word by word, then there is evidence that we are dealing with a collocation”. In Sect. 2. 3. 2, we argue that the fact that MWEs cannot be translated word-for-word is a consequence of their limited syntactic and semantic compositionality. Adequate solutions for the variable syntactic/semantic fixedness of MWEs are not easy to find, especially in the context of statistical MT models. However, for high quality MT, it is important to detect MWEs, to disambiguate them semantically and to treat them appropriately in order to avoid generating unnatural translations or losing information.
ResearchGate has not been able to resolve any citations for this publication.
The placement of the particle before or after an object in the English verb-particle construction is influenced by a variety of factors. We argue that many of them can be subsumed under a single simple principle, motivated by considerations of processing efficiency: to the extent that the domains of syntactic and semantic dependencies can be minimized, processing is facilitated. We use a more precise formulationof this idea to make several predictions about the distributionof particles based on the size of the object NP and the semantic dependencies among the verb, the particle, and the object. Corpus studies confirm the predictions, providing evidence for the princi- ple of domain minimization.*
We present two methods that merge ideas from statistical machine translation (SMT) and translation memories (TM). We use a TM to retrieve matches for source segments, and replace the mismatched parts with instructions to an SMT system to fill in the gap. We show that for fuzzy matches of over 70%, one method outperforms both SMT and TM base-lines.
We examine a new, intuitive measure for evaluating machine-translation output that avoids the knowledge intensiveness of more meaning-based approaches, and the labor-intensiveness of human judg-ments. Translation Edit Rate (TER) mea-sures the amount of editing that a hu-man would have to perform to change a system output so it exactly matches a reference translation. We show that the single-reference variant of TER correlates as well with human judgments of MT quality as the four-reference variant of BLEU. We also define a human-targeted TER (or HTER) and show that it yields higher correlations with human judgments than BLEU—even when BLEU is given human-targeted references. Our results in-dicate that HTER correlates with human judgments better than HMETEOR and that the four-reference variants of TER and HTER correlate with human judg-ments as well as—or better than—a sec-ond human judgment does.
Abstract We describe the new release of the RASP (robust accurate statistical parsing) system, designed for syntactic annotation of free text. The new,version includes a revised and more semantically-motivated output representation, an enhanced grammar and part-of-speech tagger lexicon, and a more fl exible and semi-supervised training method for the structural parse ranking model. We evaluate the released version on the WSJ using a relational evaluation scheme, and describe how the new release allows users to enhance performance using (in-domain) lexical information.
We describe an open-source toolkit for sta- tistical machine translation whose novel contributions are (a) support for linguisti- cally motivated factors, (b) confusion net- work decoding, and (c) efficient data for- mats for translation models and language models. In addition to the SMT decoder, the toolkit also includes a wide variety of tools for training, tuning and applying the system to many translation tasks.
Researchers in both machine translation (e.g., Brown ., 1990) and bilingual lexicography (e.g., Klavans and Tzoukermann, 1990) have recently become interested in studying parallel texts, texts such as the Canadian Hansards (parliamentary proceedings) which are available in multiple languages (French and English). This paper describes a method for aligning sentences in these parallel texts, based on a simple statistical model of character lengths. The method was developed and tested on a small trilingual sample of Swiss economic reports. A much larger sample of 90 million words of Canadian Hansards has been aligned and donated to the ACL/DCI.
We propose a new phrase-based translation model and decoding algorithm that enables us to evaluate and compare several, previously proposed phrase-based translation models. Within our framework, we carry out a large number of experiments to understand better and explain why phrase-based models out-perform word-based models. Our empirical results, which hold for all examined language pairs, suggest that the highest levels of performance can be obtained through relatively simple means: heuristic learning of phrase translations from word-based alignments and lexical weighting of phrase translations. Surprisingly, learning phrases longer than three words and learning phrases from high-accuracy word-level alignment models does not have a strong impact on performance. Learning only syntactically motivated phrases degrades the performance of our systems.
Automatic translation from one human language to another using computers, better known as machine translation (MT), is a long-standing goal of computer science. Accurate translation requires a great deal of knowledge about the usage and meaning of words, the structure of phrases, the meaning of sentences, and which real-life situations are plausible. For general-purpose translation, the amount of required knowledge is staggering, and it is not clear how to prioritize knowledge acquisition efforts.Recently, there has been a fair amount of research into extracting translation-relevant knowledge automatically from bilingual texts. In the early 1990s, IBM pioneered automatic bilingual-text analysis. A 1999 workshop at Johns Hopkins University saw a re-implementation of many of the core components of this work, aimed at attracting more researchers into the field. Over the past years, several statistical MT projects have appeared in North America, Europe, and Asia, and the literature is growing substantially. We will provide a technical overview of the state-of-the-art.
A phrase-based statistical machine translation approach — the alignment template approach — is described. This translation approach allows for general many-to-many relations between words. Thereby, the context of words is taken into account in the translation model, and local changes in word order from source to target language can be learned explicitly. The model is described using a log-linear modeling approach, which is a generalization of the often used source-channel approach. Thereby, the model is easier to extend than classical statistical machine translation systems. We describe in detail the process for learning phrasal translations, the feature functions used, and the search algorithm. The evaluation of this approach is performed on three different tasks. For the German-English speech Verbmobil task, we analyze the effect of various sys- tem components. On the French-English Canadian Hansards task, the alignment template system obtains significantly better results than a single-word-based translation model. In the Chinese-English 2002 National Institute of Standards and Technology (NIST) machine transla- tion evaluation it yields statistically significantly better NIST scores than all competing research and commercial translation systems.
In this article, we describe an efficient beam search algorithm for statistical machine translation based on dynamic programming (DP). The search algorithm uses the translation model presented in Brown et al. (1993). Starting from a DP-based solution to the traveling-salesman problem, we present a novel technique to restrict the possible word reorderings between source and target language in order to achieve an efficient search algorithm. Word reordering restrictions especially useful for the translation direction German to English are presented. The restrictions are generalized, and a set of four parameters to control the word reordering is introduced, which then can easily be adopted to new translation directions. The beam search procedure has been successfully tested on the Verbmobil task (German to English, 8,000-word vocabulary) and on the Canadian Hansards task (French to English, 100,000-word vocabulary). For the medium-sized Verbmobil task, a sentence can be translated in a few seconds, only a small number of search errors occur, and there is no performance degradation as measured by the word error criterion used in this article.
this article the problem of finding the word alignment of a bilingual sentence-aligned corpus by using language-independent statistical methods. There is a vast literature on this topic, and many different systems have been suggested to solve this problem. Our work follows and extends the methods introduced by Brown, Della Pietra, Della Pietra, and Mercer (1993) by using refined statistical models for the translation process. The basic idea of this approach is to develop a model of the translation process with the word alignment as a hidden variable of this process, to apply statistical estimation theory to compute the "optimal" model parameters, and to perform alignment search to compute the best word alignment
Human evaluations of machine translation are extensive but expensive. Human evaluations can take months to finish and involve human labor that can not be reused.
In this paper, we present and compare various single-word based alignment models for statistical machine translation. We discuss the five IBM alignment models, the Hidden-Markov alignment model, smoothing techniques and various modifications.
We describe METEOR, an automatic metric for machine translation evaluation that is based on a generalized concept of unigram matching between the machine- produced translation and human-produced reference translations. Unigrams can be matched based on their surface forms, stemmed forms, and meanings; further- more, METEOR can be easily extended to include more advanced matching strate- gies. Once all generalized unigram matches between the two strings have been found, METEOR computes a score for this matching using a combination of unigram-precision, unigram-recall, and a measure of fragmentation that is designed to directly capture how well-ordered the matched words in the machine translation are in relation to the reference. We evaluate METEOR by measuring the cor- relation between the metric scores and human judgments of translation quality. We compute the Pearson R correlation value between its scores and human qual- ity assessments of the LDC TIDES 2003 Arabic-to-English and Chinese-to-English datasets. We perform segment-by- segment correlation, and show that METEOR gets an R correlation value of 0.347 on the Arabic data and 0.331 on the Chinese data. This is shown to be an im- provement on using simply unigram- precision, unigram-recall and their har- monic F1 combination. We also perform experiments to show the relative contribu- tions of the various mapping modules.
A new maximum likelihood training algorithm is proposed that compensates for weaknesses of the EM algorithm by using cross-validation likelihood in the expectation step to avoid overtraining. By using a set of sufficient statistics associated with a partitioning of the training data, as in parallel EM, the algorithm has the same order of computational requirements as the original EM algorithm. Another variation uses an approximation of bagging to reduce variance in the E-step but at a somewhat higher cost. Analyses using GMMs with artificial data show the proposed algorithms are more robust to overtraining than the conventional EM algorithm. Large vocabulary recognition experiments on Mandarin broadcast news data show that the methods make better use of more parameters and give lower recognition error rates than standard EM training.
In this article, compound processing for translation into German in a factored sta- tistical MT system is investigated. Com- pounds are handled by splitting them prior to training, and merging the parts after translation. I have explored eight merging strategies using different combinations of external knowledge sources, such as word lists, and internal sources that are carried through the translation process, such as symbols or parts-of-speech. I show that for merging to be successful, some internal knowledge source is needed. I also show that an extra sequence model for part-of- speech is useful in order to improve the order of compound parts in the output. The best merging results are achieved by a matching scheme for part-of-speech tags.
In this thesis proposal I present my thesis work, about pre- and postprocessing for statistical machine translation, mainly into Germanic languages. I focus my work on four areas: compounding, definite noun phrases, reordering, and error correction. Initial results are positive within all four areas, and there are promising possibilities for extending these approaches. In addition I also focus on methods for performing thorough error analysis of machine translation output, which can both motivate and evaluate the studies performed.
We conduct a pilot study for task-oriented evaluation of Multiword Expression (MWE) in Statistical Machine Translation (SMT). We propose two different integration strategies for MWE in SMT, which take advantage of differ- ent degrees of MWE semantic compositional- ity and yield complementary improvements in SMT quality on a large-scale translation task. 1
Statistical machine translation (SMT) treats the translation of natural language as a machine learning problem. By examining many samples of human-produced translation, SMT algorithms automatically learn how to translate. SMT has made tremendous strides in less than two decades, and new ideas are constantly introduced. This survey presents a tutorial overview of the state of the art. We describe the context of the current research and then move to a formal problem description and an overview of the main subproblems: translation modeling, parameter estimation, and decoding. Along the way, we present a taxonomy of some different approaches within these areas. We conclude with an overview of evaluation and a discussion of future directions.
This paper looks at decoding complexity.
SRILM is a collection of C++ libraries, executable programs, and helper scripts designed to allow both production of and experimentation with statistical language models for speech recognition and other applications. SRILM is freely available for noncommercial purposes. The toolkit supports creation and evaluation of a variety of language model types based on N-gram statistics, as well as several related tasks, such as statistical tagging and manipulation of N-best lists and word lattices. This paper summarizes the functionality of the toolkit and discusses its design and implementation, highlighting ease of rapid prototyping, reusability, and combinability of tools.
METEOR: an automatic metric for MT evaluation with improved correlation with human judgments In: Proceedings of the ACL 2005 workshop on intrinsic and extrinsic evaluation measures for MT and/or summarization, Ann Arbor
- S Banerjee
- A Lavie