Incremental Composition in Distributional Semantics

Composition in Distributional Semantics

Denoising composition in distributional semantics

Since in distributional semantics we derive the embedding from a corpus, and the corpus is just a sample from the entire distribution, it is inevitable that the vectors obtained in the process will be somewhat noisy. In Section 2 we analyze this and other sources of noise, and in Section 3 we turn to the question of how much the considerations of compositionality discussed in Kornai and Kracht ...

DISSECT - DIStributional SEmantics Composition Toolkit

We introduce DISSECT, a toolkit to build and explore computational models of word, phrase and sentence meaning based on the principles of distributional semantics. The toolkit focuses in particular on compositional meaning, and implements a number of composition methods that have been proposed in the literature. Furthermore, DISSECT can be useful to researchers and practitioners who need models...

Separating Disambiguation from Composition in Distributional Semantics

Most compositional-distributional models of meaning are based on ambiguous vector representations, where all the senses of a word are fused into the same vector. This paper provides evidence that the addition of a vector disambiguation step prior to the actual composition would be beneficial to the whole process, producing better composite representations. Furthermore, we relate this issue with...

Composition in Distributional Models of Semantics

Vector-based models of word meaning have become increasingly popular in cognitive science. The appeal of these models lies in their ability to represent meaning simply by using distributional information under the assumption that words occurring within similar contexts are semantically similar. Despite their widespread use, vector-based models are typically directed at representing words in iso...