Pith. sign in

REVIEW

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.04726 v3 pith:UXCFRJKO submitted 2021-09-10 cs.CL cs.IR

AutoTriggER: Label-Efficient and Robust Named Entity Recognition with Auxiliary Trigger Extraction

classification cs.CL cs.IR
keywords entityautotriggerauxiliaryentitiesframeworkgeneralizinginformationleveraging
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Deep neural models for named entity recognition (NER) have shown impressive results in overcoming label scarcity and generalizing to unseen entities by leveraging distant supervision and auxiliary information such as explanations. However, the costs of acquiring such additional information are generally prohibitive. In this paper, we present a novel two-stage framework (AutoTriggER) to improve NER performance by automatically generating and leveraging ``entity triggers'' which are human-readable cues in the text that help guide the model to make better decisions. Our framework leverages post-hoc explanation to generate rationales and strengthens a model's prior knowledge using an embedding interpolation technique. This approach allows models to exploit triggers to infer entity boundaries and types instead of solely memorizing the entity words themselves. Through experiments on three well-studied NER datasets, AutoTriggER shows strong label-efficiency, is capable of generalizing to unseen entities, and outperforms the RoBERTa-CRF baseline by nearly 0.5 F1 points on average.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.