Articles

We compare two pivot strategies for phrase-based statistical machine transla- tion (SMT), namely phrase translation and sentence translation. The phrase translation strategy means that we di- rectly construct a phrase translation ta- ble (phrase-table) of the source and tar- get language pair from two phrase-tables; one constructed from the source …...

This paper introduces the use of speech translation technology for a new type of voice-interactive Computer Aided Lan- guage Learning (CALL) application. We describe a computer game we have devel- oped, in which the system presents sen- tences in a student’s native language to elicit spoken translations in the target …...

This work evaluates a system that uses in- terpolated predictions of reading difficulty that are based on both vocabulary and grammatical features. The combined ap- proach is compared to individual gram- mar- and language modeling-based approaches. While the vocabulary-based language modeling approach outper- formed the grammar-based approach, grammar-based predictions can …...

This paper explores the potential for an- notating and enriching data for low-density languages via the alignment and projec- tion of syntactic structure from parsed data for resource-rich languages such as English. We seek to develop enriched resources for a large number of the world’s languages, most of which have …...

We propose to use a statistical phrase- based machine translation system in a post-editing task: the system takes as in- put raw machine translation output (from a commercial rule-based MT system), and produces post-edited target-language text. We report on experiments that were per- formed on data collected in precisely such …...

The task of selecting and ordering infor- mation appears in multiple contexts in text generation and summarization. For in- stance, methods for title generation con- struct a headline by selecting and order- ing words from the input text. In this pa- per, we investigate decoding methods that simultaneously optimize selection …...

We present a model for discourse co- herence which combines the local entity- based approach of (Barzilay and Lapata, 2005) and the HMM-based content model of (Barzilay and Lee, 2004). Unlike the mixture model of (Soricut and Marcu, 2006), we learn local and global features jointly, providing a better theoretical …...

Assessing learning progress is a critical step in language learning applications and experiments. In word learning, for exam- ple, one important type of assessment is a definition production test, in which sub- jects are asked to produce a short defini- tion of the word being learned. In current practice, each …...

We report results of experiments which build and refine models of rhetorical- semantic relations such as Cause and Con- trast. We adopt the approach of Marcu and Echihabi (2002), using a small set of patterns to build relation models, and ex- tend their work by refining the training and classification …...

A new architecture for identifying and in- terpreting temporal expressions is intro- duced, in which the large set of com- plex hand-crafted rules standard in sys- tems for this task is replaced by a series of machine learned classifiers and a much smaller set of context-independent seman- tic composition rules. …...

We present a novel method for creating A∗ esti- mates for structured search problems. In our ap- proach, we project a complex model onto multiple simpler models for which exact inference is effi- cient. We use an optimization framework to es- timate parameters for these projections in a way which …...

We present several improvements to unlexicalized parsing with hierarchically state-split PCFGs. First, we present a novel coarse-to-fine method in which a grammar’s own hierarchical projections are used for incremental pruning, including a method for ef- ficiently computing projections of a grammar with- out a treebank. In our experiments, hierarchical pruning …...

We analyze subword-based language models (LMs) in large-vocabulary continuous speech recognition across four “morphologically rich” languages: Finnish, Estonian, Turkish, and Egyptian Colloquial Arabic. By estimating n-gram LMs over sequences of morphs instead of words, better vocabulary coverage and reduced data sparsity is obtained. Standard word LMs suffer from high out-of-vocabulary …...

We present a revision learning model for improving the accuracy of a dependency parser. The revision stage corrects the out- put of the base parser by means of revi- sion rules learned from the mistakes of the base parser itself. Revision learning is performed with a discriminative classi- fier. The …...

We propose a novel HMM-based framework to accurately transliterate unseen named entities. The framework leverages features in letter- alignment and letter n-gram pairs learned from available bilingual dictionaries. Letter-classes, such as vowels/non-vowels, are integrated to further improve transliteration accuracy. The proposed transliteration system is applied to out-of-vocabulary named-entities in statistical …...

An intelligent thesaurus assists a writer with alternative choices of words and or- ders them by their suitability in the writ- ing context. In this paper we focus on methods for automatically choosing near- synonyms by their semantic coherence with the context. Our statistical method uses the Web as a …...

In word sense disambiguation, choosing the most frequent sense for an ambigu- ous word is a powerful heuristic. However, its usefulness is restricted by the availabil- ity of sense-annotated data. In this paper, we propose an information retrieval-based method for sense ranking that does not re- quire annotated data. The …...

An open issue in data-driven dependency parsing is how to handle non-projective dependencies, which seem to be required by linguistically adequate representations, but which pose problems in parsing with respect to both accuracy and efficiency. Using data from five different languages, we evaluate an incremental deterministic parser that derives non-projective …...

Previous multi-document relationship ex- traction and fusion research has focused on single relationships. Shifting the fo- cus to multiple relationships allows for the use of mutual constraints to aid extrac- tion. This paper presents a fusion method which uses a probabilistic database model to pick relationships which violate few constraints. …...

Measuring semantic similarity between words is vital for various applications in natural language processing, such as language modeling, information retrieval, and document clustering. We propose a method that utilizes the information avail- able on the Web to measure semantic sim- ilarity between a pair of words or entities. We integrate …...