Position-Aware Self-Attention based Neural Sequence Labeling

Abstract

Sequence labeling is a fundamental task in natural language processing and has been widely studied. Recently, RNN-based sequence labeling models have increasingly gained attentions. Despite superior performance achieved by learning the long short-term (i.e., successive) dependencies, the way of sequentially processing inputs might limit the ability to capture the non-continuous relations over tokens within a sentence. To tackle the problem, we focus on how to effectively model successive and discrete dependencies of each token for enhancing the sequence labeling performance. Specifically, we propose an innovative attention-based model (called position-aware selfattention, i.e., PSA) as well as a well-designed self-attentional context fusion layer within a neural network architecture, to explore the positional information of an input sequence for capturing the latent relations among tokens. Extensive experiments on three classical tasks in sequence labeling domain, i.e., partof-speech (POS) tagging, named entity recognition (NER) and phrase chunking, demonstrate our proposed model outperforms the state-of-the-arts without any external knowledge, in terms of various metrics.

12 pages, 6 figures

References in corpus (8)

• Natural Language Processing (almost) from Scratch
• On the difficulty of training Recurrent Neural Networks
• A Structured Self-attentive Sentence Embedding
• Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
• Empower Sequence Labeling with Task-Aware Neural Language Model
• Robust Multilingual Part-of-Speech Tagging via Adversarial Training
• A New Recurrent Neural CRF for Learning Non-linear Edge Features
• Does Higher Order LSTM Have Better Accuracy for Segmenting and Labeling Sequence Data?

Cited by in corpus (2)

• A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
• Convolutions and Self-Attention: Re-interpreting Relative Positions in Pre-trained Language Models