LINEAiGE
AI HISTORY

Deep Contextualized Word Representations

Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer submitted 'Deep contextualized word representations' on February 15, 2018, introducing deep contextualized word representations learned as functions of the internal states of a pretrained deep bidirectional language model.

15 February 2018AI HISTORYVERIFIED

Historical classification

This verified record belongs to LINEAiGE's artificial-intelligence history layer beginning in 1956.

Why it matters

A documented natural-language-processing research milestone for contextual word representation, demonstrating representations that vary with linguistic context and can be added to downstream models across multiple NLP tasks.

People, organizations & technologies

PEOPLE
Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer

TECHNOLOGIES
Deep contextualized word representations, Bidirectional language model, Contextual word representations

Evidence & verification

STATE
verified

CONFIDENCE
high

LAST VERIFIED
2026-09-10T04:08:14+08:00

The original arXiv record establishes the February 15, 2018 first-submission date, authors, and the introduction of deep contextualized word representations learned from internal states of a pretrained deep bidirectional language model. The ACL Anthology independently corroborates the paper, authors, 2018 NAACL publication context, and technical abstract. This record uses the arXiv submission date strictly as a research-publication milestone. It does not infer an exact software-release date, geography, institutional affiliation, ancestry, influence, causality, or relationships.

Sources

SOURCE 1 · PRIMARY · CLAIM-EVIDENCE

Deep contextualized word representations

arXiv

PUBLISHED
2018-02-15

SOURCE 2 · PRIMARY · CORROBORATION

Deep Contextualized Word Representations

Association for Computational Linguistics

Trace the chronology

Record identity

LINEAiGE ID
elmo-2018