Articles

We present the first English syllabification system to improve the accuracy of letter-to- phoneme conversion. We propose a novel dis- criminative approach to automatic syllabifica- tion based on structured SVMs. In comparison with a state-of-the-art syllabification system, we reduce the syllabification word error rate for English by 33%. Our approach …...

This paper presents a translation model that is based on tree sequence alignment, where a tree sequence refers to a single sequence of sub- trees that covers a phrase. The model leverages on the strengths of both phrase-based and lin- guistically syntax-based method. It automati- cally learns aligned tree sequence …...

This paper presents an empirical study on the robustness and generalization of two alterna- tive role sets for semantic role labeling: Prop- Bank numbered roles and VerbNet thematic roles. By testing a state–of–the–art SRL sys- tem with the two alternative role annotations, we show that the PropBank role set is …...

In this paper, we present a novel backward transliteration approach which can further as- sist the existing statistical model by mining monolingual web resources. Firstly, we em- ploy the syllable-based search to revise the transliteration candidates from the statistical model. By mapping all of them into existing words, we can …...

People rarely articulate explicitly what a na- tive speaker of a language is already assumed to know. So to acquire the stereotypical knowledge that underpins much of what is said in a given culture, one must look to what is implied by language rather than what is overtly stated. Similes …...

We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a dis- criminative, convex, semi-supervised learning algorithm can be obtained that is applicable to large-scale problems. To demonstrate the benefits of this approach, we apply the …...

We improve the quality of statistical machine translation (SMT) by applying models that predict word forms from their stems using extensive morphological and syntactic infor- mation from both the source and target lan- guages. Our inflection generation models are trained independently of the SMT system. We investigate different ways of …...

We propose a succinct randomized language model which employs a perfect hash func- tion to encode fingerprints of n-grams and their associated probabilities, backoff weights, or other parameters. The scheme can repre- sent any standard n-gram model and is easily combined with existing model reduction tech- niques such as entropy-pruning. …...

This paper presents an innovative, complex approach to semantic verb classification that relies on selectional preferences as verb prop- erties. The probabilistic verb class model un- derlying the semantic classes is trained by a combination of the EM algorithm and the MDL principle, providing soft clusters with two dimensions (verb …...

Statistical machine learning methods are em- ployed to train a Named Entity Recognizer from annotated data. Methods like Maxi- mum Entropy and Conditional Random Fields make use of features for the training purpose. These methods tend to overfit when the avail- able training corpus is limited especially if the number …...

Despite its long history, and a great deal of research producing many useful algo- rithms and observations, research in coop- erative response generation has had little impact on the recent commercialization of dialogue technologies, particularly within the spoken dialogue community. We hy- pothesize that a particular type of cooper- ative …...

We present a simple linguistically-motivated method for characterizing the semantic rela- tions that hold between two nouns. The ap- proach leverages the vast size of the Web in order to build lexically-specific features. The main idea is to look for verbs, preposi- tions, and coordinating conjunctions that can help make …...

Rapid and inexpensive techniques for auto- matic transcription of speech have the po- tential to dramatically expand the types of content to which information retrieval tech- niques can be productively applied, but lim- itations in accuracy and robustness must be overcome before that promise can be fully realized. Combining retrieval …...

Question answering research has only recently started to spread from short factoid questions to more complex ones. One significant chal- lenge is the evaluation: manual evaluation is a difficult, time-consuming process and not ap- plicable within efficient development of sys- tems. Automatic evaluation requires a cor- pus of questions and …...

In this work, we develop and evaluate a wide range of feature spaces for deriving Levin- style verb classifications (Levin, 1993). We perform the classification experiments using Bayesian Multinomial Regression (an effi- cient log-linear modeling framework which we found to outperform SVMs for this task) with the proposed feature spaces. …...

Chinese abbreviations are widely used in modern Chinese texts. Compared with English abbreviations (which are mostly acronyms and truncations), the formation of Chinese abbreviations is much more complex. Due to the richness of Chinese abbreviations, many of them may not appear in available par- allel corpora, in which case current …...

Roget’s Thesaurus has gone through many re- visions since it was first published 150 years ago. But how do these revisions affect Ro- get’s usefulness for NLP? We examine the differences in content between the 1911 and 1987 versions of Roget’s, and we test both ver- sions with each other …...

We propose using large-scale clustering of de- pendency relations between verbs and multi- word nouns (MNs) to construct a gazetteer for named entity recognition (NER). Since depen- dency relations capture the semantics of MNs well, the MN clusters constructed by using dependency relations should serve as a good gazetteer. However, …...

Adaptor grammars (Johnson et al., 2007b) are a non-parametric Bayesian extension of Prob- abilistic Context-Free Grammars (PCFGs) which in effect learn the probabilities of en- tire subtrees. In practice, this means that an adaptor grammar learns the structures useful for generating the training data as well as their probabilities. We …...

We present a method to transliterate names in the framework of end-to-end statistical machine translation. The system is trained to learn when to transliterate. For Arabic to English MT, we developed and trained a transliterator on a bitext of 7 million sen- tences and Google’s English terabyte ngrams and achieved …...