Kai-Wei Chang, Kuan-Hao Huang, James Huang
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.
Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pretrained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive useful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models. ParaBART is trained to perform syntax-guided paraphrasing, based on a source sentence that shares semantics with the target paraphrase, and a parse tree that specifies the target syntax. In this way, ParaBART learns disentangled semantic and syntactic representations from their respective inputs with separate encoders. Experiments in English show that ParaBART outperforms state-of-theart sentence embedding models on unsupervised semantic similarity tasks. Additionally, we show that our approach can effectively remove syntactic information from semantic sentence embeddings, leading to better robustness against syntactic variation on downstream semantic tasks.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2104.05115")
get_code_for_paper("2104.05115")
have("2104.05115")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2104.05115.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2104.05115)
Connect an agent — have() is free.