A Survey on Recent Advances in Sequence Labeling from Deep Learning Models
arXiv:2011.06727
Abstract
Sequence labeling (SL) is a fundamental research problem encompassing a variety of tasks, e.g., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc. Though prevalent and effective in many downstream applications (e.g., information retrieval, question answering, and knowledge graph embedding), conventional sequence labeling approaches heavily rely on hand-crafted or language-specific features. Recently, deep learning has been employed for sequence labeling tasks due to its powerful capability in automatically learning complex features of instances and effectively yielding the stat-of-the-art performances. In this paper, we aim to present a comprehensive review of existing deep learning-based sequence labeling models, which consists of three related tasks, e.g., part-of-speech tagging, named entity recognition, and text chunking. Then, we systematically present the existing approaches base on a scientific taxonomy, as well as the widely-used experimental datasets and popularly-adopted evaluation metrics in the SL domain. Furthermore, we also present an in-depth analysis of different SL models on the factors that may affect the performance and future directions in the SL domain.
16 pages
References in corpus (17)
- Natural Language Processing (almost) from Scratch
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- SummaRuNNer: A Recurrent Neural Network based Sequence Model for Extractive Summarization of Documents
- A Survey on Recent Advances in Named Entity Recognition from Deep Learning models
- TENER: Adapting Transformer Encoder for Named Entity Recognition
- Transfer Learning for Sequence Tagging with Hierarchical Recurrent Networks
- Empower Sequence Labeling with Task-Aware Neural Language Model
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
- Attending to Characters in Neural Sequence Labeling Models
- Named Entity Recognition with stack residual LSTM and trainable bias decoding
- Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering
- Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
- GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
- GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
- A New Recurrent Neural CRF for Learning Non-linear Edge Features
- Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks