# Semantic Tagging with LSTM-CRF

arXiv: https://arxiv.org/abs/2301.12206 · HTML: https://mlsanity.com/paper/2301.12206/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 16 references that are in the map.
- First posted on arXiv 28 Jan 2023.

## Builds on (most cited first, 13 of 13)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Evaluating Layers of Representation in Neural Machine Translation on Part-of-Speech and Semantic Tagging Tasks](https://mlsanity.com/paper/1801.07772/) (2018)
- [Compositional Generalization via Semantic Tagging](https://mlsanity.com/paper/2010.11818/) (2020)
- [Finding Function in Form: Compositional Character Models for Open Vocabulary Word Representation](https://mlsanity.com/paper/1508.02096/) (2015)
- [Establishing Strong Baselines for the New Decade: Sequence Tagging, Syntactic and Semantic Parsing with BERT](https://mlsanity.com/paper/1908.04943/) (2019)
- [Towards Universal Semantic Tagging](https://mlsanity.com/paper/1709.10381/) (2017)
- [Semantic Tagging with Deep Residual Networks](https://mlsanity.com/paper/1609.07053/) (2016)
- [What can we learn from Semantic Tagging?](https://mlsanity.com/paper/1808.09716/) (2018)
- [Semantic Operator Prediction and Applications](https://mlsanity.com/paper/2301.00399/) (2023)

## Abstract (arXiv)

In the present paper, two models are presented namely LSTM-CRF and BERT-LSTM-CRF for semantic tagging of universal semantic tag dataset. The experiments show that the first model is much easier to converge while the second model that leverages BERT embedding, takes a long time to converge and needs a big dataset for semtagging to be effective.