Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 185–197 November 7–11, 2021. c⃝2021 Association for Computational Linguistics 185 A Partition Filter Network for Joint Entity and Relation Extraction Zhiheng Yan1, Chong Zhang1, Jinlan Fu1,2, Qi Zhang1∗and Zhongyu Wei3 1School of Computer Science, Shanghai Key Laboratory of Intelligent Information Processing, Fudan University, Shanghai, China 2National University of Singapore, Singapore 3School of Data Science, Fudan University, Shanghai, China {zhyan20, chongzhang20, qz, zywei}@fudan.edu.cn jinlanjonna@gmail.com Abstract In joint entity and relation extraction, existing work either sequentially encode task-specific features, leading to an imbalance in inter-task feature interaction where features extracted later have no direct contact with those that come first. Or they encode entity features and relation features in a parallel manner, meaning that feature representation learning for each task is largely independent of each other except for input sharing. We propose a partition filter network to model two-way interaction between tasks properly, where fea- ture encoding is decomposed into two steps: partition and filter. In our encoder, we leverage two gates: entity and relation gate, to segment neurons into two task partitions and one shared partition. The shared partition represents inter-task information valuable to both tasks and is evenly shared across two tasks to ensure proper two-way interaction. The task partitions represent intra-task information and are formed through concerted efforts of both gates, making sure that encoding of task- specific features is dependent upon each other. Experiment results on six public datasets show that our model performs significantly better than previous approaches. In addition, con- trary to what previous work has claimed, our auxiliary experiments suggest that relation prediction is contributory to named entity prediction in a non-negligible way. The source code can be found at https://github.com/ Coopercoppers/PFN. 1 Introduction Joint entity and relation extraction intend to simultaneously extract entity and relation facts in the given text to form relational triples as (s, r, o). The extracted information provides a supplement to many studies, such as knowledge graph construction (Riedel et al., 2013), question ∗ Corresponding author. answering (Diefenbach et al., 2018) and text summarization (Gupta and Lehal, 2010). Cell State NER RE Partition ✂ ✂ RE-Specific Shared NER-Specific Figure 1: Partition process of cell neurons. Entity and relation gate are used to divide neurons into task- related and task-unrelated ones. Neurons relating to both tasks form the shared partition while the rest form two task partitions. Conventionally, Named Entity Recognition (NER) and Relation Extraction (RE) are performed in a pipelined manner (Zelenko et al., 2002; Chan and Roth, 2011). These approaches are flawed in that they do not consider the intimate connection between NER and RE. Also, error propagation is another drawback of pipeline methods. In order to conquer these issues, joint extracting entity and relation is proposed and demonstrates stronger performance on both tasks. In early work, joint methods mainly rely on elaborate feature engineering to establish interaction between NER and RE (Yu and Lam, 2010; Li and Ji, 2014; Miwa and Sasaki, 2014). Recently, end-to-end …

Content truncated to 500 words