Larger-Context Tagging: When and Why Does It Work?
arXiv:2104.04434
Abstract
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks. However, a relatively less discussed topic is what if more context information is introduced into current top-scoring tagging systems. Although several existing works have attempted to shift tagging systems from sentence-level to document-level, there is still no consensus conclusion about when and why it works, which limits the applicability of the larger-context approach in tagging tasks. In this paper, instead of pursuing a state-of-the-art tagging system by architectural exploration, we focus on investigating when and why the larger-context training, as a general strategy, can work. To this end, we conduct a thorough comparative study on four proposed aggregators for context information collecting and present an attribute-aided evaluation method to interpret the improvement brought by larger-context training. Experimentally, we set up a testbed based on four tagging tasks and thirteen datasets. Hopefully, our preliminary observations can deepen the understanding of larger-context training and enlighten more follow-up works on the use of contextual information.
arXiv commentAccepted by NAACL 2021
References in corpus (10)
- Semi-Supervised Classification with Graph Convolutional Networks
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- TENER: Adapting Transformer Encoder for Named Entity Recognition
- Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)
- A Unified MRC Framework for Named Entity Recognition
- Robust Lexical Features for Improved Neural Network Named-Entity Recognition
- TriggerNER: Learning with Entity Triggers as Explanations for Named Entity Recognition
- GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
- Instance-Based Learning of Span Representations: A Case Study through Named Entity Recognition
- Towards More Fine-grained and Reliable NLP Performance Prediction