Methods › Natural Language Processing › Contextualized Word Embeddings › CoVe

Contextual Word Vectors

CoVe

13 papers tagged archive 2025-07-28

Introduced by Bryan McCann et al. in Learned in Translation: Contextualized Word Vectors

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

CoVe, or Contextualized Word Vectors, uses a deep LSTM encoder from an attentional sequence-to-sequence model trained for machine translation to contextualize word vectors. CoVe word embeddings are therefore a function of the entire input sequence. These word embeddings can then be used in downstream tasks by concatenating them with GloVe embeddings:

v = [GloVe(x), CoVe(x)]

and then feeding these in as features for the task-specific models.

PaperSource

In Syntology about another paper, arXiv:2603.01940: no code under this exact name (no_code; paper_only). About another paper: this answer is about arXiv:2603.01940, while the archive credits arXiv:1708.00107, so it does not say whether this method has code.

From the lookup's note on this name: The same name also belongs to “COVE”, a method in the paper “COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing” (arXiv:2406.08850, 72 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name. For arXiv:2406.08850: its page on this site · ask the lookup about it.

Origin paper of this answer, arXiv:2603.01940 (its page on Syntology).

Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.

Papers archive 2025-07-28

archive papers tagged: 13 · with a code link: 9 · where Syntology ran a sample: 3 (2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran (3 of 13 tagged: 2 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)

Page 1 of 1: papers 1 to 13 of 13, newest first by the archive's date (ties by slug), in archive order.

Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.

Tasks archive 2025-07-28

20 shown of 38 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
Retrieval3
Translation3
Hallucination2
Language Modeling2
Language Modelling2
Machine Translation2
Question Answering2
Reading Comprehension2
Recommendation Systems2
Text Generation2
Transfer Learning2
CCG Supertagging1
Causal Inference1
Click-Through Rate Prediction1
Collaborative Filtering1
Conformal Prediction1
Decoder1
Denoising1
Dialogue Generation1
Entity Embeddings1

Usage over time archive 2025-07-28

Papers per year tagged with CoVe: 2017 to 2025, peak 4 4 0 2017: 1 paper 2017 2018: 4 papers 2018 2019: 1 paper 2019 2020: 0 papers 2020 2021: 0 papers 2021 2022: 0 papers 2022 2023: 2 papers 2023 2024: 3 papers 2024 2025: 2 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (13 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

Contextualized 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