English

Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition

Computation and Language 2022-04-28 v2

Abstract

Despite impressive results of language models for named entity recognition (NER), their generalization to varied textual genres, a growing entity type set, and new entities remains a challenge. Collecting thousands of annotations in each new case for training or fine-tuning is expensive and time-consuming. In contrast, humans can easily identify named entities given some simple instructions. Inspired by this, we challenge the reliance on large datasets and study pre-trained language models for NER in a meta-learning setup. First, we test named entity typing (NET) in a zero-shot transfer scenario. Then, we perform NER by giving few examples at inference. We propose a method to select seen and rare / unseen names when having access only to the pre-trained model and report results on these groups. The results show: auto-regressive language models as meta-learners can perform NET and NER fairly well especially for regular or seen names; name irregularity when often present for a certain entity type can become an effective exploitable cue; names with words foreign to the model have the most negative impact on results; the model seems to rely more on name than context cues in few-shot NER.

Keywords

Cite

@article{arxiv.2108.11857,
  title  = {Probing Pre-trained Auto-regressive Language Models for Named Entity Typing and Recognition},
  author = {Elena V. Epure and Romain Hennequin},
  journal= {arXiv preprint arXiv:2108.11857},
  year   = {2022}
}

Comments

Accepted for publication in LREC2022

R2 v1 2026-06-24T05:26:45.819Z