mlsanityData to 7 Oct 2026

Incorporating Structural Alignment Biases into an Attentional Neural Translation Model

arXiv 1601.01085 ↗First posted 6 Jan 2016cs.CLcited by 16

Not on the map. Why?

Abstract (arXiv)

Neural encoder-decoder models of machine translation have achieved impressive results, rivalling traditional translation models. However their modelling formulation is overly simplistic, and omits several key inductive biases built into traditional models. In this paper we extend the attentional neural translation model to include structural biases from word based alignment models, including positional bias, Markov conditioning, fertility and agreement over translation directions. We show improvements over a baseline attentional model and standard phrase-based model over several language pairs, evaluating on difficult languages in a low resource setting.

Key facts. Cited by 16 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Jan 2016.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 10; 2022: 5; 2023: 1.

16 papers.

Sort:

  1. 2021Word Alignment by Fine-tuning Embeddings on Parallel Corporacited by 186
  2. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  3. 2021Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMTcited by 21
  4. 2021Improving Neural Machine Translation by Bidirectional Trainingcited by 17
  5. 2021Neural OCR Post-Hoc Correction of Historical Corporacited by 12
  6. 2021Lexically Aware Semi-Supervised Learning for OCR Post-Correctioncited by 12
  7. 2021The USYD-JD Speech Translation System for IWSLT 2021cited by 11
  8. 2022Inducing and Using Alignments for Transition-based AMR Parsingcited by 11
  9. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  10. 2021Code to Comment Translation: A Comparative Study on Model Effectiveness & Errorscited by 6
  11. 2022Compositional Generalisation with Structured Reordering and Fertility Layerscited by 6
  12. 2021On Biasing Transformer Attention Towards Monotonicitycited by 5
4 more
  1. 2022Word Alignment in the Era of Deep Learning: A Tutorialcited by 3
  2. 2022DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialoguecited by 1
  3. 2023Noisy Parallel Data Alignmentcited by 1
  4. 2021An empirical analysis of phrase-based and neural machine translationcited by 0