Articles

Measuring the relative compositionality of Multi-word Expressions (MWEs) is crucial to Natural Language Processing. Various collocation based measures have been proposed to compute the relative compositionality of MWEs. In this paper, we define novel measures (both colloca- tion based and context based measures) to measure the relative compositionality of MWEs …...

This paper addresses the automatic clas- sification of the semantic relations ex- pressed by the English genitives. A learn- ing model is introduced based on the sta- tistical analysis of the distribution of gen- itives’ semantic relations on a large cor- pus. The semantic and contextual fea- tures of the …...

We develop an unsupervised semantic role labelling system that relies on the direct application of information in a predicate lexicon combined with a simple probabil- ity model. We demonstrate the usefulness of predicate lexicons for role labelling, as well as the feasibility of modifying an existing role-labelled corpus for evaluat- …...

Dictionaries and word translation models are used by a variety of systems, espe- cially in machine translation. We build a multilingual dictionary induction system for a family of related resource-poor lan- guages. We assume only the presence of a single medium-length multitext (the Bible). The techniques rely upon lexical and …...

We present a lexicon-free post-processing method for optical character recognition (OCR), implemented using weighted fi- nite state machines. We evaluate the technique in a number of scenarios rele- vant for natural language processing, in- cluding creation of new OCR capabilities for low density languages, improvement of OCR performance for a …...

The lack of annotated data is an ob- stacle to the development of many natural language processing applica- tions; the problem is especially severe when the data is non-English. Pre- vious studies suggested the possibility of acquiring resources for non-English languages by bootstrapping from high quality English NLP tools and …...

We here propose a new method which sets apart domain-specific terminology from common non-specific noun phrases. is based on the observation that termino-It logical multi-word groups reveal a con- siderably lesser degree of distributional variation than non-specific noun phrases. We define a measure for the observable amount of paradigmatic modifiability …...

Recent work has shown that very large corpora can act as training data for NLP algorithms even without explicit labels. In this paper we show how the use of sur- face features and paraphrases in queries against search engines can be used to infer labels for structural ambiguity resolution tasks. …...

Experimental research in psycholinguis- tics has demonstrated a parallelism effect in coordination: speakers are faster at pro- cessing the second conjunct of a coordi- nate structure if it has the same internal structure as the first conjunct. We show that this phenomenon can be explained by the prevalence of parallel …...

In the REAP system, users are automati- cally provided with texts to read targeted to their individual reading levels. To find ap- propriate texts, the user’s vocabulary knowledge must be assessed. We describe an approach to automatically generating questions for vocabulary assessment. Tra- ditionally, these assessments have been hand-written. Using …...

We present a very efficient statistical in- cremental parser for LTAG-spinal, a vari- ant of LTAG. The parser supports the full adjoining operation, dynamic predi- cate coordination, and non-projective de- pendencies, with a formalism of provably stronger generative capacity as compared to CFG. Using gold standard POS tags as input, …...

This paper considers the problem of auto- matically inducing role-semantic annota- tions in the FrameNet paradigm for new languages. We introduce a general frame- work for semantic projection which ex- ploits parallel texts, is relatively inexpen- sive and can potentially reduce the amount of effort involved in creating semantic re- …...

This paper investigates some computa- tional problems associated with proba- bilistic translation models that have re- cently been adopted in the literature on machine translation. These models can be viewed as pairs of probabilistic context- free grammars working in a ‘synchronous’ way. Two hardness results for the class NP are …...

Hierarchical organization is a well known prop- erty of language, and yet the notion of hierarchi- cal structure has been largely absent from the best performing machine translation systems in recent community-wide evaluations. In this paper, we dis- cuss a new hierarchical phrase-based statistical ma- chine translation system (Chiang, 2005), …...

Confidence measures for machine transla- tion is a method for labeling each word in an automatically generated translation as correct or incorrect. In this paper, we will present a new approach to confidence es- timation which has the advantage that it does not rely on system output such as N- …...

This paper presents a phrase-based statis- tical machine translation method, based on non-contiguous phrases, i.e. phrases with gaps. A method for producing such phrases from a word-aligned corpora is proposed. A statistical translation model is also presented that deals such phrases, as well as a training method based on the …...

In word sense disambiguation, a system attempts to determine the sense of a word from contextual fea- tures. Major barriers to building a high-performing word sense disambiguation system include the dif- ficulty of labeling data for this task and of pre- dicting fine-grained sense distinctions. These is- sues stem partly …...

We address the problem of multi-way re- lation classification, applied to identifica- tion of the interactions between proteins in bioscience text. A major impediment to such work is the acquisition of appro- priately labeled training data; for our ex- periments we have identified a database that serves as a proxy …...

We introduce BLANC, a family of dy- namic, trainable evaluation metrics for ma- chine translation. Flexible, parametrized models can be learned from past data and automatically optimized to correlate well with human judgments for different cri- teria (e.g. adequacy, fluency) using dif- ferent correlation measures. Towards this end, we discuss …...

We present a novel approach to relation extraction, based on the observation that the information required to assert a rela- tionship between two named entities in the same sentence is typically captured by the shortest path between the two en- tities in the dependency graph. Exper- iments on extracting top-level …...