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

Broad coverage, high quality parsers are available for only a handful of languages. A prerequisite for developing broad coverage parsers for more languages is the annotation of text with the desired linguistic representations (also known as “treebanking”). However, syntactic annotation is a labor intensive and time-consuming process, and it is difficult to find linguistically annotated text in sufficient quantities. In this article, we explore using parallel text to help solving the problem of creating syntactic annotation in more languages. The central idea is to annotate the English side of a parallel corpus, project the analysis to the second language, and then train a stochastic analyzer on the resulting noisy annotations. We discuss our background assumptions, describe an initial study on the “projectability ” of syntactic relations, and then present two experiments in which stochastic parsers are developed with minimal human intervention via projection from English. 1

We present a novel method for discovering parallel sentences in comparable, non-parallel corpora. We train a maximum entropy classifier that, given a pair of sentences, can reliably determine whether or not they are translations of each other. Using this approach, we extract parallel data from large Chinese, Arabic, and English non-parallel newspaper corpora. We evaluate the quality of the extracted data by showing that it improves the performance of a state-of-the-art statistical machine translation system. We also show that a good-quality MT system can be built from scratch by starting with a very small parallel corpus (100,000 words) and exploiting a large non-parallel corpus. Thus, our method can be applied with great benefit to language pairs for which only scarce resources are available. 1.

We propose methods to exploit contemporary news articles in a resource rich language, together with cross-language information retrieval and machine translation, to sharpen language models for a news story in a language with fewer linguistic resources. We report experimental results on storyspecific Chinese language models that use cues from a parallel corpus of English news stories. We demonstrate that even with fairly crude cross-language information retrieval, level-1 machine translation and simple linear interpolation, a significant (18%) reduction in perplexity may be obtained over a Chinese trigram model. We also demonstrate that this method of sharpening the Chinese language model is complementary to other techniques like topic dependent modeling, and the two in combination result in an even greater reduction in perplexity (28%).

In-domain texts for estimating statistical language models are not easily found for most languages of the world. We present two techniques to take advantage of in-domain text resources in other languages. First, we extend the notion of lexical triggers, which have been used monolingually for language model adaptation, to the cross-lingual problem, permitting the construction of sharper language models for a target-language document by drawing statistics from related documents in a resource-rich language. Next, we show that cross-lingual latent semantic analysis is similarly capable of extracting useful statistics for language modeling. Neither technique requires explicit translation capabilities between the two languages! We demonstrate significant reductions in both perplexity and word error rate on a Mandarin speech recognition task by using these techniques.

As the demand for global information increases significantly, multilingual corpora has become a valuable linguistic resource for applications to cross-lingual information retrieval and natural language processing. In order to cross the boundaries that exist between different languages, dictionaries are the most typical tools. However, the general-purpose dictionary is less sensitive in both genre and domain. It is also impractical to manually construct tailored bilingual dictionaries or sophisticated multilingual thesauri for large applications. Corpusbased approaches, which do not have the limitation of dictionaries, provide a statistical translation model with which to cross the language boundary. There are many domain-specific parallel or comparable corpora that are employed in machine translation and cross-lingual information

The continuously growing MT market faces the challenge of translating new languages, diverse genres, and di#erent domains using a variety of available linguistic resources.

ISBN 951-22-8210-0 (printed version) ISBN 951-22-8211-9 (electronic version)

In this paper we illustrate an approach to the creation of high quality linguistically annotated resources based on the exploitation of aligned parallel corpora. This approach is based on the key notion that translating a text can be seen as a linguistic annotation task which is easier than manual annotation with formal schemes. After translation, formal annotations can be automatically derived from aligned translated texts. We will show that translations can be exploited in various interesting ways to speed up and automate the linguistic annotation of texts. If none of the texts is already annotated, information from aligned texts can be exploited to carry out the annotation from scratch. On the contrary, if the texts in one language have been annotated and the others have not, annotations can be transferred from one language to the other. The transferbased method allows for the exploitation of existing (mostly English) annotated resources to bootstrap the creation of annotated corpora in new languages with highly reduced human effort.

The last decade has taught computational linguists that high performance on broad-coverage natural language processing tasks is best obtained using supervised learning techniques, which require annotation of large quantities of training data. But annotated text is hard to obtain.