Articles

In this paper we present a method for extracting bilingual terminologies from comparable corpora. In our approach we treat bilingual term extrac- tion as a classification problem. For classification we use an SVM binary classifier and training data taken from the EUROVOC thesaurus. We test our approach on a held-out …...

The English ’s possessive construction oc- curs frequently in text and can encode several different semantic relations; how- ever, it has received limited attention from the computational linguistics community. This paper describes the creation of a se- mantic relation inventory covering the use of ’s, an inter-annotator agreement study to …...

In this paper, we propose a new Bayesian inference method to train statistical ma- chine translation systems using only non- parallel corpora. Following a probabilis- tic decipherment approach, we first intro- duce a new framework for decipherment training that is flexible enough to incorpo- rate any number/type of features (besides …...

We present two latent variable models for learning character types, or personas, in film, in which a persona is defined as a set of mixtures over latent lexical classes. These lexical classes capture the stereo- typical actions of which a character is the agent and patient, as well as attributes …...

Semi-supervised learning (SSL) methods augment standard machine learning (ML) techniques to leverage unlabeled data. SSL techniques are often effective in text classification, where labeled data is scarce but large unlabeled corpora are readily available. However, existing SSL tech- niques typically require multiple passes over the entirety of the unlabeled data, …...

Most modern machine translation systems use phrase pairs as translation units, al- lowing for accurate modelling of phrase- internal translation and reordering. How- ever phrase-based approaches are much less able to model sentence level effects between different phrase-pairs. We pro- pose a new model to address this im- balance, based …...

Generative probabilistic models have been used for content modelling and template induction, and are typically trained on small corpora in the target domain. In contrast, vector space models of distribu- tional semantics are trained on large cor- pora, but are typically applied to domain- general lexical disambiguation tasks. We introduce …...

This paper presents novel methods for modeling numerical common sense: the ability to infer whether a given number (e.g., three billion) is large, small, or nor- mal for a given context (e.g., number of people facing a water shortage). We first discuss the necessity of numerical com- mon sense in …...

In this paper, we propose a novel re- ordering model based on sequence label- ing techniques. Our model converts the reordering problem into a sequence label- ing problem, i.e. a tagging task. Results on five Chinese-English NIST tasks show that our model improves the baseline sys- tem by 1.32 BLEU …...

We present a fast and scalable online method for tuning statistical machine trans- lation models with large feature sets. The standard tuning algorithm—MERT—only scales to tens of features. Recent discrimi- native algorithms that accommodate sparse features have produced smaller than ex- pected translation quality gains in large systems. Our method, …...

We propose a new variant of Tree- Adjoining Grammar that allows adjunc- tion of full wrapping trees but still bears only context-free expressivity. We provide a transformation to context-free form, and a further reduction in probabilistic model size through factorization and pooling of parameters. This collapsed context-free form is used …...

In this paper, we consider the problem of cross-formalism transfer in parsing. We are interested in parsing constituency- based grammars such as HPSG and CCG using a small amount of data specific for the target formalism, and a large quan- tity of coarse CFG annotations from the Penn Treebank. While …...

Even though the quality of unsupervised dependency parsers grows, they often fail in recognition of very basic dependencies. In this paper, we exploit a prior knowledge of STOP-probabilities (whether a given word has any children in a given direc- tion), which is obtained from a large raw corpus using the …...

We present a corpus analysis of how Ital- ian connectives are translated into LIS, the Italian Sign Language. Since corpus re- sources are scarce, we propose an align- ment method between the syntactic trees of the Italian sentence and of its LIS trans- lation. This method, and clustering ap- plied …...

We propose a computational framework for identifying linguistic aspects of polite- ness. Our starting point is a new corpus of requests annotated for politeness, which we use to evaluate aspects of politeness theory and to uncover new interactions between politeness markers and context. These findings guide our construction of a …...

Many current Natural Language Process- ing [NLP] techniques work well assum- ing a large context of text as input data. However they become ineffective when applied to short texts such as Twitter feeds. To overcome the issue, we want to find a related newswire document to a given tweet to …...

Syntactic structures, by their nature, re- flect first and foremost the formal con- structions used for expressing meanings. This renders them sensitive to formal vari- ation both within and across languages, and limits their value to semantic ap- plications. We present UCCA, a novel multi-layered framework for semantic rep- resentation …...

We adapt discriminative reranking to im- prove the performance of grounded lan- guage acquisition, specifically the task of learning to follow navigation instructions from observation. Unlike conventional reranking used in syntactic and semantic parsing, gold-standard reference trees are not naturally available in a grounded set- ting. Instead, we show how …...

We present a generative probabilistic model, inspired by historical printing pro- cesses, for transcribing images of docu- ments from the printing press era. By jointly modeling the text of the docu- ment and the noisy (but regular) process of rendering glyphs, our unsupervised sys- tem is able to decipher font …...

Recently, researchers have begun explor- ing methods of scoring student essays with respect to particular dimensions of qual- ity such as coherence, technical errors, and relevance to prompt, but there is rel- atively little work on modeling thesis clar- ity. We present a new annotated corpus and propose a learning-based …...