Bernier-Colborne, G.: Identifying semantic relations in a specialized corpus through distributional analysis of a cooccurrence tensor (2014)
0.00
0.0016295954 = product of:
0.014666359 = sum of:
0.014666359 = weight(_text_:of in 2153) [ClassicSimilarity], result of:
0.014666359 = score(doc=2153,freq=6.0), product of:
0.061262865 = queryWeight, product of:
1.5637573 = idf(docFreq=25162, maxDocs=44218)
0.03917671 = queryNorm
0.23940048 = fieldWeight in 2153, product of:
2.4494898 = tf(freq=6.0), with freq of:
6.0 = termFreq=6.0
1.5637573 = idf(docFreq=25162, maxDocs=44218)
0.0625 = fieldNorm(doc=2153)
0.11111111 = coord(1/9)
- Abstract
- We describe a method of encoding cooccurrence information in a three-way tensor from which HAL-style word space models can be derived. We use these models to identify semantic relations in a specialized corpus. Results suggest that the tensor-based methods we propose are more robust than the basic HAL model in some respects.
- Source
- Proceedings of the Third Joint Conference on Lexical and Computational Semantics (*SEM 2014), Dublin, Ireland, August 23-24 2014