Fei Wang, Muhao Chen, Nan Xu, Bangzheng Li, Mingtao Dong
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.
Entity typing aims at predicting one or more words that describe the type(s) of a specific mention in a sentence. Due to shortcuts from surface patterns to annotated entity labels and biased training, existing entity typing models are subject to the problem of spurious correlations. To comprehensively investigate the faithfulness and reliability of entity typing methods, we first systematically define distinct kinds of model biases that are reflected mainly from spurious correlations. Particularly, we identify six types of existing model biases, including mention-context bias, lexical overlapping bias, named entity bias, pronoun bias, dependency bias, and overgeneralization bias. To mitigate model biases, we then introduce a counterfactual data augmentation method. By augmenting the original training set with their debiased counterparts, models are forced to fully comprehend sentences and discover the fundamental cues for entity typing, rather than relying on spurious correlations for shortcuts. Experimental results on the UFET dataset show our counterfactual data augmentation approach helps improve generalization of different entity typing models with consistently better performance on both the original and debiased test sets 1 . Prompt I: <Mention> is a type of <mask>. S1: fire is a type of <mask>. RoBERTa: energy, heat, explosion, fire, gas S2: the war is a type of <mask>. True labels: war, battle, conflict RoBERTa: war, battle, conflict, violence, warfare T1: A teacher who survived the shooting said he would never forgive the police for taking an hour to arrive after the gunman opened fire.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2205.12640")
get_code_for_paper("2205.12640")
have("2205.12640")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2205.12640.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2205.12640)
Connect an agent — have() is free.