mlsanityData to 7 Oct 2026

Dynamic Meta-Embeddings for Improved Sentence Representations

arXiv 1804.07983 ↗First posted 21 Apr 2018cs.CLcited by 15

Not on the map. Why?

Abstract (arXiv)

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic meta-embeddings, a simple yet effective method for the supervised learning of embedding ensembles, which leads to state-of-the-art performance within the same model class on a variety of tasks. We subsequently show how the technique can be used to shed new light on the usage of word embeddings in NLP systems.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). First posted on arXiv 21 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 4; 2023: 3; 2024: 0; 2025: 1.

15 papers.

Sort:

By area:

  1. 2022A General Survey on Attention Mechanisms in Deep Learningcited by 64
  2. 2021Are Multilingual Models Effective in Code-Switching?cited by 56
  3. 2021How Transferable Are Self-supervised Features in Medical Image Classification Tasks?cited by 32
  4. 2021Attentive Neural Controlled Differential Equations for Time-series Classification and Forecastingcited by 28
  5. 2021ACE-NODE: Attentive Co-Evolving Neural Ordinary Differential Equationscited by 15
  6. 2021Learning Graph Meta Embeddings for Cold-Start Ads in Click-Through Rate Predictioncited by 13
  7. 2022A Survey on Word Meta-Embedding Learningcited by 7
  8. 2023TADA: Efficient Task-Agnostic Domain Adaptation for Transformerscited by 6
  9. 2022Learning Meta Word Embeddings by Unsupervised Weighted Concatenation of Source Embeddingscited by 5
  10. 2022Unsupervised Attention-based Sentence-Level Meta-Embeddings from Contextualised Language Modelscited by 4
  11. 2021A Meta-embedding-based Ensemble Approach for ICD Coding Predictioncited by 2
  12. 2021Denoising Word Embeddings by Averaging in a Shared Spacecited by 2
3 more
  1. 2025Looking to Learn: Token-wise Dynamic Gating for Low-Resource Vision-Language Modellingcited by 2
  2. 2023Together We Make Sense -- Learning Meta-Sense Embeddings from Pretrained Static Sense Embeddingscited by 1
  3. 2023Dual-Query Multiple Instance Learning for Dynamic Meta-Embedding based Tumor Classificationcited by 1