Methods › Natural Language Processing › Word Embeddings › Cross-View Training

Cross-View Training

8 papers tagged archive 2025-07-28

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

Cross View Training, or CVT, is a semi-supervised algorithm for training distributed word representations that makes use of unlabelled and labelled examples.

CVT adds k auxiliary prediction modules to the model, a Bi-LSTM encoder, which are used when learning on unlabeled examples. A prediction module is usually a small neural network (e.g., a hidden layer followed by a softmax layer). Each one takes as input an intermediate representation hʲ(xᵢ) produced by the model (e.g., the outputs of one of the LSTMs in a Bi-LSTM model). It outputs a distribution over labels pⱼ^θ(y|xᵢ).

Each hʲ is chosen such that it only uses a part of the input xᵢ; the particular choice can depend on the task and model architecture. The auxiliary prediction modules are only used during training; the test-time prediction come from the primary prediction module that produces p_θ.

Source: Semi-Supervised Sequence Modeling with Cross-View Training

Papers archive 2025-07-28

8 shown of 8, 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 34 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
Sentence4
Representation Learning3
Dependency Parsing2
Named Entity Recognition (NER)2
Attribute1
CCG Supertagging1
Contrastive Learning1
Data Augmentation1
Feature Engineering1
Graph Representation Learning1
Intent Classification1
Knowledge Distillation1
Language Modeling1
Language Modelling1
Link Prediction1
Machine Translation1
Multi-Task Learning1
NER1
Named Entity Recognition1
Natural Language Understanding1

Usage over time archive 2025-07-28

Papers per year tagged with Cross-View Training: 2018 to 2023, peak 2 2 0 2018: 1 paper 2018 2019: 2 papers 2019 2020: 1 paper 2020 2021: 1 paper 2021 2022: 1 paper 2022 2023: 2 papers 2023
Papers per year the archive tags with this method, by the paper's archive date (8 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

Word 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