2019/04/17 by Yang Liu, Liu Yang, Yang, Liu +2
Computer Science · #Advanced Text Analysis Techniques #Artificial Intelligence (cs.AI) #Bayesian Modeling and Causal Inference #Computation and Language (cs.CL) #FOS: Computer and information sciences #Topic Modeling #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.1904.08109
arxiv created 2019/04/17 · openalex publication_date 2019/04/17 · arxiv updated 2019/04/18 · openalex created_date 2019/04/25 · openalex updated_date 2026/07/28
In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating these two state-of-the-art architectures, our system tries to extract the contextual word representation at word and character levels, for better comprehension of both question and context and their correlations. We also propose our original joint posterior probability predictor module and its associated loss functions. Our best model so far obtains F1 score of 75.842% and EM score of 72.24% on the test PCE leaderboad.