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 investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how priming can be used to study the potential of these models to learn abstract structural information, which is a prerequisite for good performance on tasks that require natural language understanding skills. We introduce a novel metric and release Prime-LM, a large corpus where we control for various linguistic factors which interact with priming strength. We find that Transformer models indeed show evidence of structural priming, but also that the generalisations they learned are to some extent modulated by semantic information. Our experiments also show that the representations acquired by the models may not only encode abstract sequential structure but involve certain level of hierarchical syntactic information. More generally, our study shows that the priming paradigm is a useful, additional tool for gaining insights into the capacities of language models and opens the door to future priming-based investigations that probe the model's internal states.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2109.14989")
get_code_for_paper("2109.14989")
have("2109.14989")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2109.14989.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2109.14989)
Connect an agent — have() is free.