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.
arXiv comment16 pages
References in corpus (27)
- 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
- Multi-Task Cross-Lingual Sequence Tagging from Scratch
- Empower Sequence Labeling with Task-Aware Neural Language Model
- Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme
- Compositional Sequence Labeling Models for Error Detection in Learner Writing
- Hierarchically-Refined Label Attention Network for Sequence Labeling
- Dataset and Neural Recurrent Sequence Labeling Model for Open-Domain Factoid Question Answering
- CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition
- Attending to Characters in Neural Sequence Labeling Models
- Position-Aware Self-Attention based Neural Sequence Labeling
- Answer Sequence Learning with Neural Networks for Answer Selection in Community Question Answering
- Named Entity Recognition with stack residual LSTM and trainable bias decoding
- Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach
- Robust Lexical Features for Improved Neural Network Named-Entity Recognition
- GCDT: A Global Context Enhanced Deep Transition Architecture for Sequence Labeling
- GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
- Learning Better Internal Structure of Words for Sequence Labeling
- A New Recurrent Neural CRF for Learning Non-linear Edge Features
- Jointly Trained Sequential Labeling and Classification by Sparse Attention Neural Networks
- Evaluating the Utility of Hand-crafted Features in Sequence Labelling
- Neural Semi-Markov Conditional Random Fields for Robust Character-Based Part-of-Speech Tagging