Lingpeng Kong, Yangqiu Song, Kong, Changlong Yu, Wilfred Ng, Tianyi Xiao, Hong Hkust
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.
Though linguistic knowledge emerges during large-scale language model pretraining, recent work attempt to explicitly incorporate humandefined linguistic priors into task-specific finetuning. Infusing language models with syntactic or semantic knowledge from parsers has shown improvements on many language understanding tasks. To further investigate the effectiveness of structural linguistic priors, we conduct empirical study of replacing parsed graphs or trees with trivial ones (rarely carrying linguistic knowledge e.g., balanced tree) for tasks in the GLUE benchmark. Encoding with trivial graphs achieves competitive or even better performance in fully-supervised and few-shot settings. It reveals that the gains might not be significantly attributed to explicit linguistic priors but rather to more feature interactions brought by fusion layers. Hence we call for attention to using trivial graphs as necessary baselines to design advanced knowledge fusion methods in the future.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2210.13002")
get_code_for_paper("2210.13002")
have("2210.13002")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2210.13002.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2210.13002)
Connect an agent — have() is free.