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.

We develop two techniques for analyzing the effect of porting a machine translation system to a new domain. One is a macro-level analysis that measures how domain shift affects corpus-level evaluation; the second is a micro-level analysis for word-level errors. We apply these methods to understand what happens when a Parliament-trained phrase-based machine translation system is applied in four very different domains: news, medical texts, scientific articles and movie subtitles. We present quantitative and qualitative experiments that highlight opportunities for future research in domain adaptation for machine translation.

We present a novel method for extracting parallel sub-sentential fragments from comparable, non-parallel bilingual corpora. By analyzing potentially similar sentence pairs using a signal processing-inspired approach, we detect which segments of the source sentence are translated into segments in the target sentence, and which are not. This method enables us to extract useful machine translation training data even from very non-parallel corpora, which contain no parallel sentence pairs. 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.

One of the major bottlenecks in the development of Statistical Machine Translation systems for most language pairs is the lack of bilingual parallel training data. Currently available parallel corpora span relatively few language pairs and very few domains; building new ones of sufficiently large size and high quality is time-consuming and expensive. In this thesis, I propose methods that enable automatic creation of parallel corpora by exploiting a rich, diverse, and readily available resource: comparable corpora. Comparable corpora are bilingual texts that, while not parallel in the strict sense, are somewhat related and convey overlapping information. Such texts exist in large quantities on the Web; a good example are the multilingual news feeds produced by news agencies such as Agence France Presse, CNN, and BBC. I present novel methods for extracting parallel data of good quality from such comparable collections. I show how to detect parallelism at various granularity levels, and thus find parallel documents (if there are any in the collection), parallel sentences, and parallel sub-sentential fragments. In order to demonstrate the validity of this approach, I use my method to extract data from large-scale comparable corpora for various language pairs, and show that the extracted data helps improve the end-to-end performance of a state-of-the art machine translation system.

ParaEval is an automated evaluation method for comparing reference and peer summaries. It facilitates a tiered-comparison strategy where recall-oriented global optimal and local greedy searches for paraphrase matching are enabled in the top tiers. We utilize a domain-independent paraphrase table extracted from a large bilingual parallel corpus using methods from Machine Translation (MT). We show that the quality of ParaEval's evaluations, measured by correlating with human judgments, closely resembles that of ROUGE's.

The ISI/USC machine translation system is a statistical system based on a phrase translation model that is trained on bilingual parallel data. This translation model is combined with several other knowledge sources in a log-linear manner. The weights of the individual components in the log-linear model are set by an automatic parameter-tuning method. The system described here has been developed for translating news text, and is a simplified version of the one we participated with in the NIST 2004 MT evaluation. We give a brief overview of the components of the system and discuss its performance at IWSLT. 1. The ISI/USC Machine Translation System Our machine translation system uses a log-linear model to combine several different knowledge sources into a direct model of translation. The 12 different models used to score hypothesized translations are given in Table 1. We also give more in-depth descriptions of the major components. 1.1. Translation Model At the core of the system is the alignment template translation model, which learns many-to-many mappings between word sequences from parallel bilingual data. A sentence is translated by segmenting a source-language sentence into phrases, translating these phrases with the ones observed in the training data, and reordering the target-language phrases. More details about the alignment template approach to machine translation used here are given in [1], [2]. For the IWSLT evaluation for Chineseand Japanese-toEnglish, we trained the alignment template system on the 20,000 lines of bilingual basic travel expressions provided by the organizers. For the “additional” evaluation condition for Chinese, we used 6 of the allowed corpora provided by LDC. For the “unrestricted” evaluation condition for Chinese, we used 167M words of parallel news and political data obtained from LDC in addition to the provided data. When mixing the provided in-domain data with out-of-domain data, the in-domain data was weighted by a factor of 5, and was resegmented with the LDC segmenter. 1Now at Google, Inc. 1.2. Language Model A smoothed trigram model was also used to score hypothesized translations. We used the SRI Language Modelling Toolkit to train a language model smoothed with Kneser-Ney discounting. For all of the evaluation conditions, a language model was trained on the English half of the parallel corpus used for alignment-template training. For the “additional” and “unrestricted” evaluation conditions, an additional language model was used that was trained on 800M words of monolingual news text. Each language model is considered an independent information source, and is weighted separately in the global log-linear model. 1.3. Minimum Error Rate Training The individual model weights of the log-linear model are set using a parameter tuning procedure that minimizes the error rate of a given evaluation function (such as the BLEU score) on a held-out test corpus. Setting model weights in order to minimize the error of the function used for testing has been shown to provide better results than maximumlikelihood training [3]. For this evaluation, we optimize parameters to achieve the best performance with respect to the BLEU score. We split the provided development data into two equally sized corpora that were used separately for minimum error training and testing.

We present a novel method for discovering parallel sentences in comparable 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, Gigaword, Arabic and English newspaper corpora. We evaluate the quality of the extracted data by showing it improves the performance of a baseline statistical machine translation system.

L'invention concerne un systeme de traduction automatique pouvant utiliser des corpus monolingues non paralleles pour produire un lexique de traduction. Le systeme peut identifier des mots s'epelant de maniere identique dans les deux corpus et il peut les utiliser comme lexique de depart. Le systeme peut utiliser divers criteres, par exemple, le contexte et la frequence, pour identifier et evaluer d'autres paires de traductions possibles, au moyen du lexique depart utilise comme base. Un systeme selon un autre mode de realisation peut utiliser un petit lexique bilingue conjointement avec des corpus non paralleles, aux fins d'apprentissage de traductions de mots inconnus et de production d'un corpus parallele.

We describe GLEANS, a summarization system that uses four novel techniques for summarizating document collections. (i) GLEANS first maps all documents in a collection into a canonical, database-like representation that makes explicit the main entities and relations in a document collection. (ii) GLEANS also classifies each document collection into one of four categories: collections about a single person, single event, multiple event, and natural disaster. (iii) For each type of document...

Generator Postprocessor ABSTRACT WITH HEADLINE o j n u j n € j z y u y  y l jWITH HEADLINE o j n u j n € j z y u y  y l j

We introduce Bilingual Suffix Trees (BST), a data structure that is suitable for exploiting comparable corpora. We discuss algorithms that use BSTs in order to create parallel corpora and learn translations of unseen words from comparable corpora. Starting with a small bilingual dictionary that was derived automatically from a corpus of 5.000 parallel sentences, we have automatically extracted a corpus of 33.926 parallel phrases of size greater than 3, and learned 9 new word translations from a comparable corpus of 1.3M words (100.000 sentences).