Structured Prediction in NLP -- A survey
arXiv:2110.02057
Abstract
Over the last several years, the field of Structured prediction in NLP has had seen huge advancements with sophisticated probabilistic graphical models, energy-based networks, and its combination with deep learning-based approaches. This survey provides a brief of major techniques in structured prediction and its applications in the NLP domains like parsing, sequence labeling, text generation, and sequence to sequence tasks. We also deep-dived into energy-based and attention-based techniques in structured prediction, identified some relevant open issues and gaps in the current state-of-the-art research, and have come up with some detailed ideas for future research in these fields.
arXiv comment6 pages, 0 figures
References in corpus (13)
- On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
- Harnessing Deep Neural Networks with Logic Rules
- Input Convex Neural Networks
- Sequence-to-Sequence Learning as Beam-Search Optimization
- Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs
- End-to-End Learning for Structured Prediction Energy Networks
- An enhanced Tree-LSTM architecture for sentence semantic modeling using typed dependencies
- Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT
- Cascaded Text Generation with Markov Transformers
- Structured variable selection in support vector machines
- Deep Structured Prediction with Nonlinear Output Transformations
- Syntax-driven Iterative Expansion Language Models for Controllable Text Generation
- Generalizing with perceptrons in case of structured phase- and pattern-spaces