# Evaluating the Utility of Hand-crafted Features in Sequence Labelling

arXiv: https://arxiv.org/abs/1808.09075 · HTML: https://mlsanity.com/paper/1808.09075/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 3 of 3)

- [Machine learning and deep learning](https://mlsanity.com/paper/2104.05314/) (2021)
- [Towards Continual Entity Learning in Language Models for Conversational Agents](https://mlsanity.com/paper/2108.00082/) (2021)
- [Semantic Role Labeling of NomBank Partitives](https://mlsanity.com/paper/2412.14328/) (2024)

## Abstract (arXiv)

Conventional wisdom is that hand-crafted features are redundant for deep learning models, as they already learn adequate representations of text automatically from corpora. In this work, we test this claim by proposing a new method for exploiting handcrafted features as part of a novel hybrid learning approach, incorporating a feature auto-encoder loss component. We evaluate on the task of named entity recognition (NER), where we show that including manual features for part-of-speech, word shapes and gazetteers can improve the performance of a neural CRF model. We obtain a F1 of 91.89 for the CoNLL-2003 English shared task, which significantly outperforms a collection of highly competitive baseline models. We also present an ablation study showing the importance of auto-encoding, over using features as either inputs or outputs alone, and moreover, show including the autoencoder components reduces training requirements to 60%, while retaining the same predictive accuracy.