TY - JOUR AU - Lin, Peiqin AU - Yang, Meng PY - 2020/04/03 Y2 - 2024/03/29 TI - Hierarchical Attention Network with Pairwise Loss for Chinese Zero Pronoun Resolution JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 34 IS - 05 SE - AAAI Technical Track: Natural Language Processing DO - 10.1609/aaai.v34i05.6352 UR - https://ojs.aaai.org/index.php/AAAI/article/view/6352 SP - 8352-8359 AB - <p>Recent neural network methods for Chinese zero pronoun resolution didn't take bidirectional attention between zero pronouns and candidate antecedents into consideration, and simply treated the task as a classification task, ignoring the relationship between different candidates of a zero pronoun. To solve these problems, we propose a Hierarchical Attention Network with Pairwise Loss (HAN-PL), for Chinese zero pronoun resolution. In the proposed HAN-PL, we design a two-layer attention model to generate more powerful representations for zero pronouns and candidate antecedents. Furthermore, we propose a novel pairwise loss by introducing the correct-antecedent similarity constraint and the pairwise-margin loss, making the learned model more discriminative. Extensive experiments have been conducted on OntoNotes 5.0 dataset, and our model achieves state-of-the-art performance in the task of Chinese zero pronoun resolution.</p> ER -