Learning to Rank Lexical Substitutions

By György Szarvas, Róbert Istvan Busa-Fekete, Eyke Hüllermeier. 2013

24 citations recorded by the source corpus.

The problem to replace a word with a synonym that fits well in its sentential context is known as the lexical substitution task. In this paper, we tackle this task as a supervised ranking problem. Given a dataset of target words, their sentential contexts and the potential substitutions for the target words, the goal is to train a model that accurately ranks the candidate substitutions based on their contextual fitness. As a key contribution, we customize and evaluate several learning-to-rank models to the lexical substitution task, including classification-based and regression-based approaches. On two datasets widely used for lexical substitution, our best models significantly advance the state-of-the-art.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Modeling Word Meaning in Context with Substitute Vectors (2015, methodology): “However, we note that both Szarvas et al. (2013b) and Szarvas et al. (2013a) follow a supervised approach, training on the LS07 gold standard with 10-fold cross validation, as well as incorporate features from WordNet.”
A Simple Word Embedding Model for Lexical Substitution (2015, methodology): “In comparison to previous works our results are slightly better than state-of-the-art, with the exception of Szarvas et al. (2013).”
What Substitutes Tell Us - Analysis of an “All-Words” Lexical Substitution Corpus (2014, background): “Recently, supervised models have emerged (Biemann 2013; Szarvas et al., 2013a,b).”