Articles

This paper reports a hybridization experi­ ment, where a baseline ML dependency pars­ er, LingPars, was allowed access to Con­ straint Grammar analyses provided by a rule­ based parser (EngGram) for the same data. Descriptive compatibility issues and their in­ fluence on performance are discussed. The hybrid system performed considerably …...

We describe our experiments using the DeSR parser in the multilingual and do- main adaptation tracks of the CoNLL 2007 shared task. DeSR implements an incre- mental deterministic Shift/Reduce parsing algorithm, using specific rules to handle non-projective dependencies. For the multi- lingual track we adopted a second order averaged perceptron …...

Part of speech tagging is a fundamental component in many NLP systems. When taggers developed in one domain are used in another domain, the performance can degrade considerably. We present a method for developing taggers for new domains without requiring POS annotated text in the new domain. Our method involves …...

We present in this paper methods to improve HMM-based part-of-speech (POS) tagging of Mandarin. We model the emission prob- ability of an unknown word using all the characters in the word, and enrich the stan- dard left-to-right trigram estimation of word emission probabilities with a right-to-left prediction of the word …...

This paper discusses automatic determina- tion of case in Arabic. This task is a ma- jor source of errors in full diacritization of Arabic. We use a gold-standard syntac- tic tree, and obtain an error rate of about 4.2%, with a machine learning based system outperforming a system using hand-written …...

Recognizing polarity requires a list of po- lar words and phrases. For the purpose of building such lexicon automatically, a lot of studies have investigated (semi-) unsuper- vised method of learning polarity of words and phrases. In this paper, we explore to use structural clues that can extract polar sentences …...

Following (Blitzer et al., 2006), we present an application of structural correspondence learning to non-projective dependency pars- ing (McDonald et al., 2005). To induce the correspondences among dependency edges from different domains, we looked at ev- ery two tokens in a sentence and examined whether or not there is a …...

The technology of opinion extraction allows users to retrieve and analyze people’s opin- ions scattered over Web documents. We de- fine an opinion unit as a quadruple consist- ing of the opinion holder, the subject being evaluated, the part or the attribute in which the subject is evaluated, and the …...

In this paper, we present an election predic- tion system (Crystal) based on web users’ opinions posted on an election prediction website. Given a prediction message, Crys- tal first identifies which party the message predicts to win and then aggregates predic- tion analysis results of a large amount of opinions …...

We describe some challenges of adaptation in the 2007 CoNLL Shared Task on Domain Adaptation. Our error analysis for this task suggests that a primary source of error is differences in annotation guidelines between treebanks. Our suspicions are supported by the observation that no team was able to im- prove …...

We present a data-driven variant of the LR algorithm for dependency parsing, and ex- tend it with a best-first search for probabil- istic generalized LR dependency parsing. Parser actions are determined by a classifi- er, based on features that represent the cur- rent state of the parser. We apply this …...

We develop latent Dirichlet allocation with WORDNET (LDAWN), an unsupervised probabilistic topic model that includes word sense as a hidden variable. We develop a probabilistic posterior inference algorithm for simultaneously disambiguating a corpus and learning the domains in which to con- sider each word. Using the WORDNET hi- erarchy, we …...

This paper focuses on the evaluation of meth- ods for the automatic acquisition of Multiword Expressions (MWEs) for robust grammar engi- neering. First we investigate the hypothesis that MWEs can be detected by the distinct statistical properties of their component words, regardless of their type, comparing 3 statistical measures: mutual …...

This paper presents a novel approach for ex- ploiting the global context for the task of word sense disambiguation (WSD). This is done by using topic features constructed us- ing the latent dirichlet allocation (LDA) al- gorithm on unlabeled data. The features are incorporated into a modified na¨ıve Bayes network …...

We present a method for learning to find English to Chinese transliterations on the Web. In our approach, proper nouns are expanded into new queries aimed at maxi- mizing the probability of retrieving trans- literations from existing search engines. The method involves learning the sublexi- cal relationships between names and …...

This paper presents an empirical study on how different selections of input translation systems affect translation quality in system combination. We give empirical evidence that the systems to be combined should be of similar quality and need to be almost uncorrelated in order to be beneficial for sys- tem combination. …...

It has been widely observed that different NLP appli- cations require different sense granularities in order to best exploit word sense distinctions, and that for many applications WordNet senses are too fine-grained. In contrast to previously proposed automatic methods for sense clustering, we formulate sense merging as a su- pervised …...

A major engineering challenge in statistical machine translation systems is the efficient representation of extremely large translation rulesets. In phrase-based models, this prob- lem can be addressed by storing the training data in memory and using a suffix array as an efficient index to quickly lookup and ex- tract rules …...

We present our system used in the CoNLL 2007 shared task on multilingual parsing. The system is composed of three compo- nents: a k-best maximum spanning tree (MST) parser, a tree labeler, and a reranker that orders the k-best labeled trees. We present two techniques for training the MST parser: …...

We present experiments with a dependency parsing model defined on rich factors. Our model represents dependency trees with fac- tors that include three types of relations be- tween the tokens of a dependency and their children. We extend the projective pars- ing algorithm of Eisner (1996) for our case, and …...