Resumen: En este art́ıculo presentamos una extensión de una arquitectura integrada diseñada originalmente para Semantic Parsing a WSD. El marco propuesto permitirá que ambas tareas puedan colaborar y llevarse a cabo simultáneamente. Se ha probado la validez y robustez de esta arquitectura contra una tarea de WSD bien definida (el SENSEVAL-II English Lexical Sample) aplicando modelos sintácticose...

We present a theoretically motivated method for creating probabilistic word sense disambiguation (WSD) systems. The method works by composing multiple probabilistic components: such modularity is made possible by an application of Bayesian statistics and Lidstone’s smoothing method. We show that a probabilistic WSD system created along these lines is a strong competitor to state-of-the-art WSD ...

Most word sense disambiguation (WSD) methods require large quantities of manually annotated training data and/or do not exploit fully the semantic relations of thesauri. We propose a new unsupervised WSD algorithm, which is based on generating Spreading Activation Networks (SANs) from the senses of a thesaurus and the relations between them. A new method of assigning weights to the networks’ li...

OBJECTIVE Intravenous immunoglobulin as an adjunctive treatment in sepsis was regarded as promising by a Cochrane meta-analysis of smaller trials. In this phase III multicenter trial, we assessed whether intravenous immunoglobulin G (ivIgG) reduced 28-day mortality and improved morbidity in patients with score-defined severe sepsis. DESIGN Randomized, double-blind, placebo-controlled, multice...

We present a system for for computer-aided WSD mark-up of texts in Spanish. The system is is based on Anaya dictionary, uses a Spanish morphological analyzer and a WSD method based on Lesk algorithm (along with the other standard strategies). This tool reduces time and effort for preparation WSD-marked corpora in Spanish. We also discuss the requirement for such type of systems, which our parti...

We would like to describe the relationship between word sense disambiguation (WSD) and language resources (LR) working with word senses. We discuss the problem of sense division and tagging. Exploiting specific features of the inflectional languages for WSD is encouraged. We present WSD methods for Czech ambiguous nouns. The advantage of these methods consists in reducing the manual work by usi...

BACKGROUND/OBJECTIVES Previous studies have indicated that when compared to young mice, old mice have lower global DNA methylation and higher p16 promoter methylation in colonic mucosa, which is a common finding in colon cancer. It is also known that a Western-style diet (WSD) high in fat and calories, and low in calcium, vitamin D, fiber, methionine and choline (based on the AIN 76A diet) is t...

This paper explores the application of structured learning methods (SLMs) to word sense disambiguation (WSD). On one hand, the semantic dependencies between polysemous words in the sentence can be encoded in SLMs. On the other hand, SLMs obtained significant achievements in natural language processing, and so it is a natural idea to apply them to WSD. However, there are many theoretical and pra...

The Semantic Type Indexing (STI) tool, developed at the National Library of Medicine (NLM), is one of the most accurate unsupervised methods for the word sense disambiguation (WSD) applications. NLM’s Lexical Systems Group (LSG) enhanced the STI tool, achieving an improved precision of 79.05% vs. baseline 73.81% when applied to NLM’s WSD test collection. An ST-based WSD tool, STWSD, has been de...

Recent research presents conflicting evidence on whether word sense disambiguation (WSD) systems can help to improve the performance of statistical machine translation (MT) systems. In this paper, we successfully integrate a state-of-the-art WSD system into a state-of-the-art hierarchical phrase-based MT system, Hiero. We show for the first time that integrating a WSD system improves the perfor...