In this work we revise the application of discriminative learning to the problem of phrase selection in Statistical Machine Translation. Inspired by common techniques used in Word Sense Disambiguation, we train classifiers based on local context to predict possible phrase translations. Our work extends that of Vickrey et al. (2005) in two main aspects. First, we move from word translation to phrase translation. Second, we move from the ‘blank-filling ’ task to the ‘full translation ’ task. We report results on a set of highly frequent source phrases, obtaining a significant improvement, specially with respect to adequacy, according to a rigorous process of manual evaluation. 1

Evaluation results recently reported by Callison-Burch et al. (2006) and Koehn and Monz (2006), revealed that, in certain cases, the BLEU metric may not be a reliable MT quality indicator. This happens, for instance, when the systems under evaluation are based on different paradigms, and therefore, do not share the same lexicon. The reason is that, while MT quality aspects are diverse, BLEU limits its scope to the lexical dimension. In this work, we suggest using metrics which take into account linguistic features at more abstract levels. We provide experimental results showing that metrics based on deeper linguistic information (syntactic/shallow-semantic) are able to produce more reliable system rankings than metrics based on lexical matching alone, specially when the systems under evaluation are of a different nature. 1

This work reports on research conducted on the domain of multi-document summarization using background knowledge. The research focuses on summary evaluation and the implementation of a set of generic use tools for NLP tasks and especially for automatic summarization. Within this work we formalize the n-gram graph representation and its use in NLP tasks. We present the use of n-gram graphs for the tasks of summary evaluation, content selection, novelty detection and redundancy removal. Furthermore, we present a set of algorithmic constructs and methodologies, based on the notion of n-gram graphs, that aim to support meaning extraction and textual quality quantification.

This work studies the viability of performing heterogeneous automatic MT error analyses. Error analysis is, undoubtly, one of the most crucial stages in the development cycle of an MT system. However, often not enough attention is paid to this process. The reason is that performing an accurate error analysis requires intensive human labor. In order to speed up the error analysis process, we suggest partially automatizing it by having automatic evaluation metrics play a more active role. For that purpose, we have compiled a large and heterogeneous set of features at different linguistic levels and at different levels of granularity. Through a practical case study, we show how these features provide an effective means of ellaborating interpretable and detailed automatic reports of translation quality. 1.

Combining different metrics into a single measure of quality seems the most direct and natural way to improve over the quality of individual metrics. Recently, several approaches have been suggested (Kulesza and

This paper presents the automatic summarization problem and specifies a generic process for the automatic construction of summaries. Most recent approaches to summarization are exposed as contributions to the various steps of this process. The paper elaborates on the grounds of multi-document automatic summarization and examines the use of background knowledge, indicating related, ongoing and recent efforts. Finally it discusses open problems, proposing further research directions in this field of research. 1 1