2019/06/03 by Sandeep Attree, Attree, Sandeep
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Text Readability and Simplification #Topic Modeling
paper · pdf · doi:10.48550/arxiv.1906.00839
openalex publication_date 2019/06/03 · openalex created_date 2022/07/29 · openalex updated_date 2026/07/28
This paper presents a strong set of results for resolving gendered ambiguous\npronouns on the Gendered Ambiguous Pronouns shared task. The model presented\nhere draws upon the strengths of state-of-the-art language and coreference\nresolution models, and introduces a novel evidence-based deep learning\narchitecture. Injecting evidence from the coreference models compliments the\nbase architecture, and analysis shows that the model is not hindered by their\nweaknesses, specifically gender bias. The modularity and simplicity of the\narchitecture make it very easy to extend for further improvement and applicable\nto other NLP problems. Evaluation on GAP test data results in a\nstate-of-the-art performance at 92.5% F1 (gender bias of 0.97), edging closer\nto the human performance of 96.6%. The end-to-end solution presented here\nplaced 1st in the Kaggle competition, winning by a significant lead. The code\nis available at https://github.com/sattree/gap.\n