Articles

In a linguistically-motivated syntax-based trans- lation system, the entire translation process is normally carried out in two steps, translation rule matching and target sentence decoding us- ing the matched rules. Both steps are very time- consuming due to the tremendous number of translation rules, the exhaustive search in trans- lation …...

We present a new phrase-based con- ditional exponential family translation model for statistical machine translation. The model operates on a feature repre- sentation in which sentence level transla- tions are represented by enumerating all the known phrase level translations that occur inside them. This makes the model a good match …...

Current statistical machine translation sys- tems usually extract rules from bilingual corpora annotated with 1-best alignments. They are prone to learn noisy rules due to alignment mistakes. We propose a new structure called weighted alignment matrix to encode all possible alignments for a par- allel text compactly. The key idea …...

We present a discriminative substring de- coder for transliteration. This decoder extends recent approaches for discrimi- native character transduction by allow- ing for a list of known target-language words, an important resource for translit- eration. Our approach improves upon Sherif and Kondrak’s (2007b) state-of-the- art decoder, creating a 28.5% relative …...

A large body of recent research has been investigating the acquisition and applica- tion of applied inference knowledge. Such knowledge may be typically captured as entailment rules, applied over syntactic representations. Efficient inference with such knowledge then becomes a funda- mental problem. Starting out from a for- malism for entailment-rule …...

We apply machine learning to the Lin- ear Ordering Problem in order to learn sentence-specific reordering models for machine translation. We demonstrate that even when these models are used as a mere preprocessing step for German-English translation, they significantly outperform Moses’ integrated lexicalized reordering model. Our models are trained on …...

The Person Cross Document Coreference sys- tems depend on the context for making deci- sions on the possible coreferences between person name mentions. The amount of context required is a parameter that varies from cor- pora to corpora, which makes it difficult for usual disambiguation methods. In this paper we …...

In this paper, we employ the centering the- ory in pronoun resolution from the seman- tic perspective. First, diverse semantic role features with regard to different predicates in a sentence are explored. Moreover, given a pronominal anaphor, its relative ranking among all the pronouns in a sentence, ac- cording to …...

Knowledge of noun phrase anaphoricity might be profitably exploited in coreference resolu- tion to bypass the resolution of non-anaphoric noun phrases. However, it is surprising to no- tice that recent attempts to incorporate auto- matically acquired anaphoricity information into coreference resolution have been some- what disappointing. This paper employs a …...

Traditional learning-based coreference re- solvers operate by training a mention- pair classifier for determining whether two mentions are coreferent or not. Two in- dependent lines of recent research have attempted to improve these mention-pair classifiers, one by learning a mention- ranking model to rank preceding men- tions for a given …...

s Jacob Eisenstein∗ James Clarke† Dan Goldwasser† Dan Roth∗† ∗Beckman Institute for Advanced Science and Technology, †Department of Computer Science University of Illinois Urbana, IL 61801 {jacobe,clarkeje,goldwas1,danr}@illinois.edu Abstract Machine learning offers a range of tools for training systems from data, but these methods are only as good as the underly- …...

Computing the pairwise semantic similarity between all words on the Web is a compu- tationally challenging task. Parallelization and optimizations are necessary. We pro- pose a highly scalable implementation based on distributional similarity, imple- mented in the MapReduce framework and deployed over a 200 billion word crawl of the Web. …...

This paper presents a new method of devel- oping a large-scale hyponymy relation data- base by combining Wikipedia and other Web documents. We attach new words to the hy- ponymy database extracted from Wikipedia by using distributional similarity calculated from documents on the Web. For a given tar- get word, …...

Models of language learning play a cen- tral role in a wide range of applica- tions: from psycholinguistic theories of how people acquire new word knowledge, to information systems that can automati- cally match content to users’ reading abil- ity. We present a novel statistical ap- proach that can infer …...

We have designed, implemented and eval- uated an end-to-end system spellcheck- ing and autocorrection system that does not require any manually annotated train- ing data. The World Wide Web is used as a large noisy corpus from which we infer knowledge about misspellings and word usage. This is used to …...

Topic models are a useful tool for analyz- ing large text collections, but have previ- ously been applied in only monolingual, or at most bilingual, contexts. Mean- while, massive collections of interlinked documents in dozens of languages, such as Wikipedia, are now widely available, calling for tools that can characterize …...

We present a novel approach for multilin- gual document clustering using only com- parable corpora to achieve cross-lingual semantic interoperability. The method models document collections as weighted graph, and supervisory information is given as sets of must-linked constraints for documents in different languages. Recur- sive k-nearest neighbor similarity propa- gation …...

Applying statistical parsers developed for English to languages with freer word- order has turned out to be harder than expected. This paper investigates the adequacy of different statistical parsing models for dealing with a (relatively) free word-order language. We show that the recently proposed Relational- Realizational (RR) model consistently outperforms …...

We investigate the effectiveness of self- training PCFG grammars with latent anno- tations (PCFG-LA) for parsing languages with different amounts of labeled training data. Compared to Charniak’s lexicalized parser, the PCFG-LA parser was more ef- fectively adapted to a language for which parsing has been less well developed (i.e., Chinese) …...

We connect two scenarios in structured learning: adapting a parser trained on one corpus to another annotation style, and projecting syntactic annotations from one language to another. We propose quasi- synchronous grammar (QG) features for these structured learning tasks. That is, we score a aligned pair of source and target …...