This paper describes our system entered for the *SEM 2013 shared task on Semantic Textual Similarity (STS). We focus on the core task of predicting the semantic textual similarity of sentence pairs. The current system utilizes machine learning techniques trained on semantic similarity ratings from the *SEM 2012 shared task; it achieved rank 20 out of 90 submissions from 35 different teams. Give...

The Semantic Textual Similarity (STS) task aims to exam the degree of semantic equivalence between sentences (Agirre et al., 2012). This paper presents the work of the Hong Kong Polytechnic University (PolyUCOMP) team which has participated in the STS core and typed tasks of SemEval2013. For the STS core task, the PolyUCOMP system disambiguates words senses using contexts and then determine sen...

This paper presents the results of using Roget's International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and applied to Roget's. The experimental evaluation suggests that the traditional edge counting approach does surprisingly well (a correlation of r=0.88 with a benchmark set of human similarity judgements, with...

This paper describes NaDiR (Naive DIstributional Response generation), a corpus-based system that, from a set of word stimuli as an input, generates a response word relying on association strength and distributional similarity. NaDiR participated in the CogALex 2014 shared task on multiword associations (restricted systems track), operationalizing the task as a ranking problem: candidate words ...

We compare four similarity-based estimation methods against back-off and maximum-likelihood estimation methods on a pseudo-word sense disambiguation task in which we controlled for both unigram and bigram frequency. The similarity-based methods perform up to 40% better on this particular task. We also conclude that events that occur only once in the training set have major impact on similarity-...

This paper presents the results of using Roget’s International Thesaurus as the taxonomy in a semantic similarity measurement task. Four similarity metrics were taken from the literature and applied to Roget’s. The experimental evaluation suggests that the traditional edge counting approach does surprisingly well (a correlation of r=0.88 with a benchmark set of human similarity judgements, with...

Prepositions are often considered to have too little semantic content or be too polysemous to warrant a proper semantic description. We first illustrate the suitability of distributional similarity methods for analysing preposition semantics by way of an inter-preposition similarity task, and make the claim that any semantic account of preposition semantics must be partially conditioned on vale...

We describe a set of systems submitted to the SemEval-2016 English Semantic Textual Similarity (STS) task. Given two English sentences, the task is to compute the degree of their semantic similarity. Each of our systems uses the SemEval 2012–2015 STS datasets to train a ridge regression model that combines different measures of similarity. Our best system demonstrates 73.6% correlation with ave...

We investigated the recovery from memory of a primary task after an interruption. If the primary task lacked associative support among its task components, recovery was more difficult following an interruption that overlapped either completely or partially in the amount of information shared with the primary task (an interruption-similarity effect). In addition, memory for completed actions was...