Wei Wang, Wanyun Cui, Guangyu Zheng
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.
We propose to solve the natural language inference problem without any supervision from the inference labels via task-agnostic multimodal pretraining. Although recent studies of multimodal self-supervised learning also represent the linguistic and visual context, their encoders for different modalities are coupled. Thus they cannot incorporate visual information when encoding plain text alone. In this paper, we propose Multimodal Aligned Contrastive Decoupled learning (MACD) network. MACD forces the decoupled text encoder to represent the visual information via contrastive learning. Therefore, it embeds visual knowledge even for plain text inference. We conducted comprehensive experiments over plain text inference datasets (i.e. SNLI and STS-B). The unsupervised MACD even outperforms the fully-supervised BiLST-M and BiLSTM+ELMO on STS-B.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2010.08200")
get_code_for_paper("2010.08200")
have("2010.08200")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2010.08200.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2010.08200)
Connect an agent — have() is free.