Articles

We propose a Name-aware Machine Translation (MT) approach which can tightly integrate name processing into MT model, by jointly annotating parallel cor- pora, extracting name-aware translation grammar and rules, adding name phrase table and name translation driven decod- ing. Additionally, we also propose a new MT metric to appropriately evaluate …...

This paper demonstrates the need and im- pact of subcategorization information for SMT. We combine (i) features on source- side syntactic subcategorization and (ii) an external knowledge base with quantita- tive, dependency-based information about target-side subcategorization frames. A manual evaluation of an English-to- German translation task shows that the subcategorization …...

Developing natural language processing tools for low-resource languages often re- quires creating resources from scratch. While a variety of semi-supervised meth- ods exist for training from incomplete data, there are open questions regarding what types of training data should be used and how much is necessary. We dis- cuss a …...

We consider the problem of grounding the meaning of words in the physical world and focus on the visual modality which we represent by visual attributes. We create a new large-scale taxonomy of visual at- tributes covering more than 500 concepts and their corresponding 688K images. We use this dataset …...

Distributional thesauri are now widely used in a large number of Natural Lan- guage Processing tasks. However, they are far from containing only interesting semantic relations. As a consequence, improving such thesaurus is an impor- tant issue that is mainly tackled indirectly through the improvement of semantic sim- ilarity measures. …...

This paper studies the problem of non- monotonic sentence alignment, motivated by the observation that coupled sentences in real bitexts do not necessarily occur monotonically, and proposes a semisuper- vised learning approach based on two as- sumptions: (1) sentences with high affinity in one language tend to have their counter- …...

Crowdsourcing, which offers new ways of cheaply and quickly gathering large amounts of information contributed by volunteers online, has revolutionised the collection of labelled data. Yet, to create annotated linguistic resources from this data, we face the challenge of having to combine the judgements of a potentially large group of …...

We present GlossBoot, an effective minimally-supervised approach to ac- quiring wide-coverage domain glossaries for many languages. For each language of interest, given a small number of hypernymy relation seeds concerning a target domain, we bootstrap a glossary from the Web for that domain by means of iteratively acquired term/gloss extraction …...

Paratactic syntactic structures are noto- riously difficult to represent in depen- dency formalisms. This has painful con- sequences such as high frequency of pars- ing errors related to coordination. In other words, coordination is a pending prob- lem in dependency analysis of natural lan- guages. This paper tries to shed …...

Techniques that compare short text seg- ments using dependency paths (or simply, paths) appear in a wide range of automated language processing applications including question answering (QA). However, few models in ad hoc information retrieval (IR) use paths for document ranking due to the prohibitive cost of parsing a retrieval …...

This paper proposes a new method for significantly improving the performance of pairwise coreference models. Given a set of indicators, our method learns how to best separate types of mention pairs into equivalence classes for which we con- struct distinct classification models. In ef- fect, our approach finds an optimal …...

We propose a novel approach for develop- ing a two-stage document-level discourse parser. Our parser builds a discourse tree by applying an optimal parsing algorithm to probabilities inferred from two Con- ditional Random Fields: one for intra- sentential parsing and the other for multi- sentential parsing. We present two ap- …...

In spoken dialog systems, statistical state tracking aims to improve robustness to speech recognition errors by tracking a posterior distribution over hidden dialog states. Current approaches based on gener- ative or discriminative models have differ- ent but important shortcomings that limit their accuracy. In this paper we discuss these limitations …...

This paper discusses the construction of a parallel treebank currently involving ten languages from six language families. The treebank is based on deep LFG (Lexical- Functional Grammar) grammars that were developed within the framework of the ParGram (Parallel Grammar) effort. The grammars produce output that is maxi- mally parallelized across …...

Natural language parsing has typically been done with small sets of discrete cat- egories such as NP and VP, but this rep- resentation does not capture the full syn- tactic nor semantic richness of linguistic phrases, and attempts to improve on this by lexicalizing phrases or splitting cate- gories only …...

Many models in NLP involve latent vari- ables, such as unknown parses, tags, or alignments. Finding the optimal model pa- rameters is then usually a difficult noncon- vex optimization problem. The usual prac- tice is to settle for local optimization meth- ods such as EM or gradient ascent. We explore …...

Shift-reduce dependency parsers give comparable accuracies to their chart- based counterparts, yet the best shift- reduce constituent parsers still lag behind the state-of-the-art. One important reason is the existence of unary nodes in phrase structure trees, which leads to different numbers of shift-reduce actions between different outputs for the same …...

Supervised training procedures for seman- tic parsers produce high-quality semantic parsers, but they have difficulty scaling to large databases because of the sheer number of logical constants for which they must see labeled training data. We present a technique for developing seman- tic parsers for large databases based on a …...

To overcome the shortage of labeled data for implicit discourse relation recogni- tion, previous works attempted to auto- matically generate training data by remov- ing explicit discourse connectives from sentences and then built models on these synthetic implicit examples. However, a previous study (Sporleder and Lascarides, 2008) showed that models …...

Expensive feature engineering based on WordNet senses has been shown be useful for document level sentimentto classification. A plausible reason for such a performance improvement is the reduction in data sparsity. However, such a reduction could be achieved with a lesser effort through the means of syntagma based word clustering. …...