google-research-datasets / gap-coreference Goto Github PK

Super cool work on the GAP dataset! For the page-context setting, would it be possible to get access to the original crawled pages from which the snippets were extracted. I see there a URL field in the tsv data files, but I'm guessing some of the pages have changed since then.

Hi, thanks for your work!
There are some posts saying there could be possible error in the dataset. Would you take a look at this thread?
Error in GAP Coreference Dataset?

If there is such error, would you update the dataset?

As the authors mentioned, the instances in GAP have certain differences between the female and male groups, e.g., the correct candidate is on average further away from the pronoun in the female group than in the male group, the female instances also contains more candidates on average than the male instances. These would incorrectly make unbiased models appear biased.

In our work, we address this issue. Check it out if you are using the GAP test set as a gender bias diagnostic dataset.

@misc{kocijan2020gap,
      title={The Gap on GAP: Tackling the Problem of Differing Data Distributions in Bias-Measuring Datasets}, 
      author={Vid Kocijan and Oana-Maria Camburu and Thomas Lukasiewicz},
      year={2020},
      eprint={2011.01837},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}
 

Hi dear researchers, I have some trouble understanding the following sentences in the original paper.
"To calculate these baselines, we first detect candidate antecedents by finding all mentions of PERSON entity type, NAME mention type (headed by a proper noun), and, for structural cues, that are not in a syntactic position which precludes coreference with the pronoun."

the last part makes me really confused and i cannot get i across.

Under which license is released your dataset?

Thank you.