Anonymized BERT: An Augmentation Approach to the Gendered Pronoun Resolution Challenge
By Bo Liu. 2019
8 citations recorded by the source corpus.
We present our 7th place solution to the Gendered Pronoun Resolution challenge, which uses BERT without fine-tuning and a novel augmentation strategy designed for contextual embedding token-level tasks. Our method anonymizes the referent by replacing candidate names with a set of common placeholder names. Besides the usual benefits of effectively increasing training data size, this approach diversifies idiosyncratic information embedded in names. Using same set of common first names can also help the model recognize names better, shorten token length, and remove gender and regional biases associated with names. The system scored 0.1947 log loss in stage 2, where the augmentation contributed to an improvements of 0.04. Post-competition analysis shows that, when using different embedding layers, the system scores 0.1799 which would be third place.
Subfields: Artificial Intelligence, Natural Language Processing, Alignment & RLHF
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Hal Daumé Iii
- Marta Ruiz Costa-jussà
- Su Lin Blodgett
- Kellie Webster
- Hanna M. Wallach
- Solon Barocas
- Will Radford
- Christian Hardmeier
In Natural Language Processing
- Hal Daumé Iii
- Marta Ruiz Costa-jussà
- Su Lin Blodgett
- Kellie Webster
- Christian Hardmeier
- Will Radford
- Hanna M. Wallach
- Solon Barocas
In Alignment & RLHF
- Marta Ruiz Costa-jussà
- Will Radford
- Hal Daumé Iii
- Hanna M. Wallach
- Kellie Webster
- Christian Hardmeier
- Solon Barocas
- Su Lin Blodgett
Citations in the corpus
- Language (Technology) is Power: A Critical Survey of “Bias” in NLP (2020, methodology): “…here; most propose techniques we would have categorized as “Questionable correlations,” with a few as “Other representational harms” (Abzaliev, 2019; Attree, 2019; Bao and Qiao, 2019; Chada, 2019; Ionita et al., 2019; Liu, 2019; Lois et al., 2019; Wang, 2019; Xu and Yang, 2019; Yang et al., 2019).”
- Gendered Ambiguous Pronoun (GAP) Shared Task at the Gender Bias in NLP Workshop 2019 (2019, methodology): “Two teams augmented the GAP data by using name substitutions (Liu, 2019; Lois et al., 2019) and two automatically created extra examples of the minority label Neither (Attree, 2019; Bao and Qiao, 2019).”