This paper describes the system developed by our team (HLTC-HKUST) for task 1 of SemEval 2015 workshop about paraphrase classification and semantic similarity in Twitter. We trained a neural network classifier over a range of features that includes translation metrics, lexical and syntactic similarity score and semantic features based on semantic roles. The neural network was trained taking int...

This paper briefly reports our submissions to the Semantic Textual Similarity (STS) task in the SemEval 2012 (Task 6). We first use knowledge-based methods to compute word semantic similarity as well as Word Sense Disambiguation (WSD). We also consider word order similarity from the structure of the sentence. Finally we sum up several aspects of similarity with different coefficients and get th...

We present a measure of the similarity of the long-term structure of musical pieces. The system deals with raw polyphonic data. Through unsupervised learning, we generate an abstract representation of music the “texture score”. This “texture score” can be matched to other similar scores using a generalized edit distance, in order to assess structural similarity. We notably apply this algorithm ...

This paper is about adopting the longest common subsequence (LCS) matching for Chinese information retrieval. We re-ranked the retrieved documents by a mixture of the original similarity score and the LCS score obtained by matching the document titles and the query. This LCS-based similarity score is also used in pseudo-relevance feedback in various ways (e.g., selecting terms and filtering doc...

This paper describes our system developed for English Monolingual subtask (STS Core) of SemEval-2016 Task 1: “Semantic Textual Similarity: A Unified Framework for Semantic Processing and Evaluation”. We measure the similarity between two sentences using three different types of features, including word alignment-based similarity, sentence vector-based similarity and sentence constituent similar...

We present a measure of the similarity of the long-term structure of musical pieces. The system deals with raw polyphonic data. Through unsupervised learning, we generate an abstract representation of music the “texture score”. This “texture score” can be matched to other similar scores using a generalized edit distance, in order to assess structural similarity. We notably apply this algorithm ...

In this study, we proposed score fusion technique to improve the performance of remote sensing image retrieval system (RS-IRS) using combination of several features. The representation of each feature is selected based on their performance when used as single feature in RS-IRS. Those features are color moment using L*a*b* color space, edge direction histogram extracted from Saturation channel, ...

How to detect and correct misspelled words in documents is a very important issue for Mandarin and Japanese. This paper uses phonological similarity and orthographic similarity co-occurrence to train linear regression model. Using ACL-SIGHAN 2013 Bake-off Dataset, experimental results indicate that the detection F-score, error location F-score of our proposed method for Subtask 1 is 0.70 and 0....

As with pairwise alignment, multiple sequence alignments (MSAs) are typically scored by assigning a score to each column and summing over the columns. The most common approach to scoring individual columns in a multiple alignment is to calculate a score for each pair of symbols in the column, and then sum over the pair scores. This is called sum-of-pairs or SP-scoring. For global multiple seque...

In this paper we propose a novel approach for contentbased music recommendation. The main innovation of the proposed technique consists of a similarity function that, instead of considering entire songs or their thumbnail representations, analyzes audio similarities between semantic segments from different audio tracks. The rationale of our idea is that a song similarity and recommendation tech...