Abstract | ||
---|---|---|
We present an unsupervised phrase relatedness function f that has been applied in a Semantic Textual Similarity system TrWP of SemEval-2015. The best run of TrWP was ranked 33 among 73 runs. f finds the relatedness strength between two phrases using overlapping bi-gram context extracted from the Google-n-gram corpus. The relatedness strength is the strength of association capturing how similar or dissimilar two phrases are. In order to find the relatedness strength, f applies a sum-ratio SR technique based on the statistics of the overlapping n-grams associated with two input phrases. The experimental result from f demonstrates improvement over existing phrase relatedness methods on two standard datasets of 216 phrase-pairs. f does not require any human annotated resource and is independent of the syntactic structure of phrases. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1007/978-3-319-34111-8_19 | Canadian Conference on AI |
Keywords | Field | DocType |
Phrase relatedness,Google-n-gram,Unsupervised,Overlapping bi-gram context | Ranking,Pattern recognition,Computer science,Phrase,Speech recognition,Natural language processing,Artificial intelligence,Gram,Syntactic structure | Conference |
Volume | ISSN | Citations |
9673 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 19 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Md. Rashadul Hasan Rakib | 1 | 1 | 0.70 |
Aminul Islam | 2 | 328 | 31.16 |
Evangelos E. Milios | 3 | 290 | 41.22 |