Methods › Natural Language Processing › Language Models › ELMo

ELMo

234 papers tagged archive 2025-07-28

Introduced by Matthew E. Peters et al. in Deep contextualized word representations

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

Embeddings from Language Models, or ELMo, is a type of deep contextualized word representation that models both (1) complex characteristics of word use (e.g., syntax and semantics), and (2) how these uses vary across linguistic contexts (i.e., to model polysemy). Word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pre-trained on a large text corpus.

A biLM combines both a forward and backward LM. ELMo jointly maximizes the log likelihood of the forward and backward directions. To add ELMo to a supervised model, we freeze the weights of the biLM and then concatenate the ELMo vector ELMOᵗᵃˢᵏₖ with xₖ and pass the ELMO enhanced representation [xₖ; ELMOᵗᵃˢᵏₖ] into the task RNN. Here xₖ is a context-independent token representation for each token position.

Image Source: here

PaperSource

Papers archive 2025-07-28

30 shown of 234, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 199 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Word Embeddings71
Sentence48
Language Modelling38
Language Modeling33
Sentiment Analysis26
Named Entity Recognition (NER)22
NER20
Named Entity Recognition20
named-entity-recognition20
Transfer Learning18
text-classification16
General Classification15
Text Classification15
Question Answering14
Natural Language Inference12
POS11
Word Sense Disambiguation11
Natural Language Understanding10
Dependency Parsing8
Machine Translation8

Usage over time archive 2025-07-28

Papers per year tagged with ELMo: 2018 to 2025, peak 94 94 0 2018: 25 papers 2018 2019: 94 papers 2019 2020: 59 papers 2020 2021: 36 papers 2021 2022: 7 papers 2022 2023: 6 papers 2023 2024: 5 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (234 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Language ModelsContextualized Word EmbeddingsWord Embeddings

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections