We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
GloVe learns word embeddings by leveraging statistical information from word co-occurrence matrices. However, word pairs in the matrices are extracted from a predefined local context window, which might lead to limited word pairs and potentially semantic irrelevant word pairs. In this paper, we propose SemGloVe, which distills semantic co-occurrences from BERT into static GloVe word embeddings. Particularly, we propose two models to extract co-occurrence statistics based on either the masked language model or the multi-head attention weights of BERT. Our methods can extract word pairs without limiting by the local window assumption and can define the co-occurrence weights by directly considering the semantic distance between word pairs. Experiments on several word similarity datasets and four external tasks show that SemGloVe can outperform GloVe.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2012.15197")
get_code_for_paper("2012.15197")
have("2012.15197")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2012.15197.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2012.15197)
Connect an agent — have() is free.