extractive reading comprehension, spatial-temporal information, span mask
Extractive reading comprehension is to extract consecutive subsequences from a given article to answer the given question. Previous work often adopted Byte Pair Encoding (BPE) that could cause semantically correlated words to be separated. Also, previous features extraction strategy cannot effectively capture the global semantic information. In this paper, an extractive summarization model is proposed with enhanced spatial-temporal information and span mask encoding (ESSM) to promote global semantic information. ESSM utilizes Embedding Layer to reduce semantic segmentation of correlated words, and adopts TemporalConvNet Layer to relief the loss of feature information. The model can also deal with unanswerable questions. To verify the effectiveness of the model, experiments on datasets SQuAD1.1 and SQuAD2.0 are conducted. Our model achieved an EM of 86.31% and a F1 score of 92.49% on SQuAD1.1 and the numbers are 80.54% and 83.27% for SQuAD2.0. It was proved that the model is effective for extractive QA task.
Digital Object Identifier (DOI)
Li, Ran; Zheng, Fengbo; Liang, Gongbo; Jiang, Lifen; Wu, Panpan; and Chen, Bowei, "ESSM: An Extractive Summarization Model with Enhanced Spatial-Temporal Information and Span Mask Encoding" (2022). Computer Science Faculty Publications. 29.