# DEXTER: Deep Encoding of External Knowledge for Named Entity Recognition in Virtual Assistants

arXiv: https://arxiv.org/abs/2108.06633 · HTML: https://mlsanity.com/paper/2108.06633/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 15 Aug 2021.

## Builds on (most cited first, 8 of 8)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Convolutional Neural Networks for Sentence Classification](https://mlsanity.com/paper/1408.5882/) (2014)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [End-to-end Sequence Labeling via Bi-directional LSTM-CNNs-CRF](https://mlsanity.com/paper/1603.01354/) (2016)
- [Named Entity Recognition with Bidirectional LSTM-CNNs](https://mlsanity.com/paper/1511.08308/) (2015)
- [Lexicon Infused Phrase Embeddings for Named Entity Resolution](https://mlsanity.com/paper/1404.5367/) (2014)
- [Self-Attention Gazetteer Embeddings for Named-Entity Recognition](https://mlsanity.com/paper/2004.04060/) (2020)
- [Noise Robust Named Entity Understanding for Voice Assistants](https://mlsanity.com/paper/2005.14408/) (2020)

## Abstract (arXiv)

Named entity recognition (NER) is usually developed and tested on text from well-written sources. However, in intelligent voice assistants, where NER is an important component, input to NER may be noisy because of user or speech recognition error. In applications, entity labels may change frequently, and non-textual properties like topicality or popularity may be needed to choose among alternatives. We describe a NER system intended to address these problems. We test and train this system on a proprietary user-derived dataset. We compare with a baseline text-only NER system; the baseline enhanced with external gazetteers; and the baseline enhanced with the search and indirect labelling techniques we describe below. The final configuration gives around 6% reduction in NER error rate. We also show that this technique improves related tasks, such as semantic parsing, with an improvement of up to 5% in error rate.