Mohammad Pilehvar, Ali Modarressi, Hosein Mohebbi
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.
Several studies have been carried out on revealing linguistic features captured by BERT. This is usually achieved by training a diagnostic classifier on the representations obtained from different layers of BERT. The subsequent classification accuracy is then interpreted as the ability of the model in encoding the corresponding linguistic property. Despite providing insights, these studies have left out the potential role of token representations. In this paper, we provide a more in-depth analysis on the representation space of BERT in search for distinct and meaningful subspaces that can explain the reasons behind these probing results. Based on a set of probing tasks and with the help of attribution methods we show that BERT tends to encode meaningful knowledge in specific token representations (which are often ignored in standard classification setups), allowing the model to detect syntactic and semantic abnormalities, and to distinctively separate grammatical number and tense subspaces. 1
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.01477")
get_code_for_paper("2104.01477")
have("2104.01477")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.01477.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.01477)
Connect an agent — have() is free.