papers AI Learner
The Github is limit! Click to go to the new site.

Sentence Embedding Alignment for Lifelong Relation Extraction

2019-03-06
Hong Wang, Wenhan Xiong, Mo Yu, Xiaoxiao Guo, Shiyu Chang, William Yang Wang

Abstract

Conventional approaches to relation extraction usually require a fixed set of pre-defined relations. Such requirement is hard to meet in many real applications, especially when new data and relations are emerging incessantly and it is computationally expensive to store all data and re-train the whole model every time new data and relations come in. We formulate such a challenging problem as lifelong relation extraction and investigate memory-efficient incremental learning methods without catastrophically forgetting knowledge learned from previous tasks. We first investigate a modified version of the stochastic gradient methods with a replay memory, which surprisingly outperforms recent state-of-the-art lifelong learning methods. We further propose to improve this approach to alleviate the forgetting problem by anchoring the sentence embedding space. Specifically, we utilize an explicit alignment model to mitigate the sentence embedding distortion of the learned model when training on new data and new relations. Experiment results on multiple benchmarks show that our proposed method significantly outperforms the state-of-the-art lifelong learning approaches.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.02588

PDF

http://arxiv.org/pdf/1903.02588


Similar Posts

Comments