Rachel Rudinger, Christine Herlihy
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Crowdworker-constructed natural language inference (NLI) datasets have been found to contain statistical artifacts associated with the annotation process that allow hypothesis-only classifiers to achieve better-than-random performance (Poliak et al., 2018;Gururangan et al., 2018;Tsuchiya, 2018). We investigate whether MedNLI, a physician-annotated dataset with premises extracted from clinical notes, contains such artifacts (Romanov and Shivade, 2018). We find that entailed hypotheses contain generic versions of specific concepts in the premise, as well as modifiers related to responsiveness, duration, and probability. Neutral hypotheses feature conditions and behaviors that co-occur with, or cause, the condition(s) in the premise. Contradiction hypotheses feature explicit negation of the premise and implicit negation via assertion of good health. Adversarial filtering demonstrates that performance degrades when evaluated on the difficult subset. We provide partition information and recommendations for alternative dataset construction strategies for knowledge-intensive domains.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2106.01491")
get_code_for_paper("2106.01491")
have("2106.01491")
Connect an agent — have() is free.