Snajder, J.; Almic, P.: Modeling semantic compositionality of Croatian multiword expressions (2015)
0.01
0.005875363 = product of:
0.04112754 = sum of:
0.02056377 = weight(_text_:classification in 2920) [ClassicSimilarity], result of:
0.02056377 = score(doc=2920,freq=2.0), product of:
0.097404055 = queryWeight, product of:
3.1847067 = idf(docFreq=4974, maxDocs=44218)
0.030584937 = queryNorm
0.21111822 = fieldWeight in 2920, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1847067 = idf(docFreq=4974, maxDocs=44218)
0.046875 = fieldNorm(doc=2920)
0.02056377 = weight(_text_:classification in 2920) [ClassicSimilarity], result of:
0.02056377 = score(doc=2920,freq=2.0), product of:
0.097404055 = queryWeight, product of:
3.1847067 = idf(docFreq=4974, maxDocs=44218)
0.030584937 = queryNorm
0.21111822 = fieldWeight in 2920, product of:
1.4142135 = tf(freq=2.0), with freq of:
2.0 = termFreq=2.0
3.1847067 = idf(docFreq=4974, maxDocs=44218)
0.046875 = fieldNorm(doc=2920)
0.14285715 = coord(2/14)
- Abstract
- A distinguishing feature of many multiword expressions (MWEs) is their semantic non-compositionality. Determining the semantic compositionality of MWEs is important for many natural language processing tasks. We address the task of modeling semantic compositionality of Croatian MWEs. We adopt a composition-based approach within the distributional semantics framework. We build and evaluate models based on Latent Semantic Analysis and the recently proposed neural network-based Skip-gram model, and experiment with different composition functions. We show that the compositionality scores predicted by the Skip-gram additive models correlate well with human judgments (=0.50). When framed as a classification task, the model achieves an accuracy of 0.64.