Articles

We address the problem of large-scale auto- matic detection of online reviews without us- ing any human labels. We propose an efficient method that combines two basic ideas: Build- ing a classifier from a large number of noisy examples and using the structure of the web- site to enhance the …...

In (Chen, 2009), we show that for a vari- ety of language models belonging to the ex- ponential family, the test set cross-entropy of a model can be accurately predicted from its training set cross-entropy and its parameter values. In this work, we show how this rela- tionship can be …...

We investigate the task of performance pre- diction for language models belonging to the exponential family. First, we attempt to em- pirically discover a formula for predicting test set cross-entropy for n-gram language mod- els. We build models over varying domains, data set sizes, and n-gram orders, and perform linear …...

This paper presents a new perspective to the language modeling problem by moving the word representations and modeling into the continuous space. In a previous work we in- troduced Gaussian-Mixture Language Model (GMLM) and presented some initial experi- ments. Here, we propose Tied-Mixture Lan- guage Model (TMLM), which does not …...

This paper describes research on automatic as- sessment of the pronunciation quality of spon- taneous non-native adult speech. Since the speaking content is not known prior to the assessment, a two-stage method is developed to first recognize the speaking content based on non-native speech acoustic properties and then forced-align the …...

This paper describes a lattice-based decoder for hierarchical phrase-based translation. The decoder is implemented with standard WFST operations as an alternative to the well-known cube pruning procedure. We find that the use of WFSTs rather than k-best lists requires less pruning in translation search, resulting in fewer search errors, direct …...

This paper presents a semi-supervised learn- ing framework for mining Chinese-English lexicons from large amount of Chinese Web pages. The issue is motivated by the ob- servation that many Chinese neologisms are accompanied by their English translations in the form of parenthesis. We classify par- enthetical translations into bilingual abbrevi- …...

Statistical machine translation (SMT) mod- els need large bilingual corpora for train- ing, which are unavailable for some language pairs. This paper provides the first serious ex- perimental study of active learning for SMT. We use active learning to improve the qual- ity of a phrase-based SMT system, and show …...

Recent work has shown that translating seg- mentation lattices (lattices that encode alterna- tive ways of breaking the input to an MT sys- tem into words), rather than text in any partic- ular segmentation, improves translation qual- ity of languages whose orthography does not mark morpheme boundaries. However, much of …...

In this paper, we show that linguistically mo- tivated pronunciation rules can improve phone and word recognition results for Modern Stan- dard Arabic (MSA). Using these rules and the MADA morphological analysis and dis- ambiguation tool, multiple pronunciations per word are automatically generated to build two pronunciation dictionaries; one for …...

Voice search is increasingly popular, espe- cially for local business directory assistance. However, speech recognition accuracy on business listing names is still low, leading to user frustration. In this paper, we present a new algorithm for geo-centric language model generation for local business voice search for mobile users. Our algorithm …...

We present a novel Bayesian topic model for learning discourse-level document structure. Our model leverages insights from discourse theory to constrain latent topic assignments in a way that reflects the underlying organiza- tion of document topics. We propose a global model in which both topic selection and order- ing are …...

We present an exploration of generative prob- abilistic models for multi-document summa- rization. Beginning with a simple word fre- quency based model (Nenkova and Vander- wende, 2005), we construct a sequence of models each injecting more structure into the representation of document set content and ex- hibiting ROUGE gains along …...

This paper presents a novel unsupervised method for hierarchical topic segmentation. Lexical cohesion – the workhorse of unsu- pervised linear segmentation – is treated as a multi-scale phenomenon, and formalized in a Bayesian setting. Each word token is modeled as a draw from a pyramid of la- tent topic models, …...

Statistical parsing models have recently been proposed that employ a bounded stack in time- series (left-to-right) recognition, using a right- corner transform defined over training trees to minimize stack use (Schuler et al., 2008). Cor- pus results have shown that a vast majority of naturally-occurring sentences can be parsed in …...

The extent to which the organization of nat- ural language grammars reflects a drive to minimize dependency length remains little explored. We present the first algorithm polynomial-time in sentence length for obtain- ing the minimal-length linearization of a de- pendency tree subject to constraints of mild context sensitivity. For the …...

For many language technology applications, such as question answering, the overall sys- tem runs several independent processors over the data (such as a named entity recognizer, a coreference system, and a parser). This eas- ily results in inconsistent annotations, which are harmful to the performance of the aggre- gate system. …...

One of the reasons nonparametric Bayesian inference is attracting attention in computa- tional linguistics is because it provides a prin- cipled way of learning the units of generaliza- tion together with their probabilities. Adaptor grammars are a framework for defining a va- riety of hierarchical nonparametric Bayesian models. This paper …...

In incremental spoken dialogue systems, par- tial hypotheses about what was said are re- quired even while the utterance is still ongo- ing. We define measures for evaluating the quality of incremental ASR components with respect to the relative correctness of the par- tial hypotheses compared to hypotheses that can …...

Syllables play an important role in speech synthesis and recognition. We present sev- eral different approaches to the syllabifica- tion of phonemes. We investigate approaches based on linguistic theories of syllabification, as well as a discriminative learning technique that combines Support Vector Machine and Hidden Markov Model technologies. Our experiments …...