User:Mirceat/Compositional distributional semantics

This is not a Wikipedia article: It is an individual user's work-in-progress page, and may be incomplete and/or unreliable. For guidance on developing this draft, see Wikipedia:So you made a userspace draft.

Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL
Easy tools: Citation bot (help) | Advanced: Fix bare URLs
This page was last edited by Bearcat (talk | contribs) 6 years ago. (Update timer)

Finished writing a draft article? Are you ready to request an experienced editor review it for possible inclusion in Wikipedia? Submit your draft for review!

Compositional distributional semantics

Compositional distributional semantic models are an extension of distributional semantic models that characterize the semantics of entire phrases or sentences. This is achieved by composing the distributional representations of the words that sentences contain. Different approaches to composition have been explored, and are under discussion at established workshops such as SemEval.^[1]

Simpler non-compositional models fail to capture the semantics of larger linguistic units as they ignore grammatical structure and logical words, which are crucial for their understanding.

^[2] ^[3]

Approaches

category theory
deep learning
Hadamard?

Applications

Multiple choice
Semantic Text Similarity
Word Sense disambiguation

Corpora

SICK corpus
https://github.com/brmson/dataset-sts

References

External links

Semantic Text Similarity Dataset Hub [1]

[1] "SemEval-2014, Task 1".

[2] "Deep Learning for Semantic Similarity" (PDF).

[3] "Sentence Pair Scoring: Towards Unified Framework for Text Comprehension" (PDF).

[1]

[2]

[3]