Pith. sign in

REVIEW 1 cited by

Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER

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 1910.02586 v2 pith:2W2ZY64G submitted 2019-10-07 cs.CL

classification cs.CL
keywords bilstmcross-contextimprovementsmentionsmodelingmulti-tokenachievedacross
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

State-of-the-art approaches of NER have used sequence-labeling BiLSTM as a core module. This paper formally shows the limitation of BiLSTM in modeling cross-context patterns. Two types of simple cross-structures -- self-attention and Cross-BiLSTM -- are shown to effectively remedy the problem. On both OntoNotes 5.0 and WNUT 2017, clear and consistent improvements are achieved over bare-bone models, up to 8.7% on some of the multi-token mentions. In-depth analyses across several aspects of the improvements, especially the identification of multi-token mentions, are further given.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Enhancing Speech Instruction Understanding and Disambiguation in Robotics via Speech Prosody

    cs.RO 2025-06 conditional novelty 6.0 of 10

    Prosody-based token-level goal/detail classification, combined with in-context LLM prompting, disambiguates robot instructions better than text-only processing.

Pith tools