mlsanityData to 14 Oct 2026

Improving Lexical Choice in Neural Machine Translation

arXiv 1710.01329 ↗First posted 3 Oct 2017cs.CLcited by 17

Not on the map. Why?

Abstract (arXiv)

We explore two solutions to the problem of mistranslating rare words in neural machine translation. First, we argue that the standard output layer, which computes the inner product of a vector representing the context with all possible output word embeddings, rewards frequent words disproportionately, and we propose to fix the norms of both vectors to a constant value. Second, we integrate a simple lexical module which is jointly trained with the rest of the model. We evaluate our approaches on eight language pairs with data sizes ranging from 100k to 8M words, and achieve improvements of up to +4.3 BLEU, surpassing phrase-based translation in nearly all settings.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 9; 2022: 3; 2023: 1; 2024: 4.

17 papers.

Sort:

By area:

  1. 2021Domain Adaptation and Multi-Domain Adaptation for Neural Machine Translation: A Surveycited by 46
  2. 2021Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translationcited by 34
  3. 2021Variational Graph Normalized Auto-Encoderscited by 29
  4. 2021Lexicon Learning for Few-Shot Neural Sequence Modelingcited by 28
  5. 2024Streaming Deep Reinforcement Learning Finally Workscited by 25
  6. 2022Low-Rank Softmax Can Have Unargmaxable Classes in Theory but Rarely in Practicecited by 15
  7. 2021How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?cited by 12
  8. 2024MoRSE: Bridging the Gap in Cybersecurity Expertise with Retrieval Augmented Generationcited by 8
  9. 2024Transformer Normalisation Layers and the Independence of Semantic Subspacescited by 6
  10. 2022Switching to Discriminative Image Captioning by Relieving a Bottleneck of Reinforcement Learningcited by 4
  11. 2021HintedBT: Augmenting Back-Translation with Quality and Transliteration Hintscited by 3
  12. 2021Rule-based Morphological Inflection Improves Neural Terminology Translationcited by 3
5 more
  1. 2021Variance-Aware Machine Translation Test Setscited by 3
  2. 2021Advances in Electron Microscopy with Deep Learningcited by 0
  3. 2022Optimizing Deep Transformers for Chinese-Thai Low-Resource Translationcited by 0
  4. 2023LABO: Towards Learning Optimal Label Regularization via Bi-level Optimizationcited by 0
  5. 2024Massively Multilingual Text Translation For Low-Resource Languagescited by 0