mlsanityData to 7 Oct 2026

Input Combination Strategies for Multi-Source Transformer Decoder

arXiv 1811.04716 ↗First posted 12 Nov 2018cs.CLcited by 22

Not on the map. Why?

Abstract (arXiv)

In multi-source sequence-to-sequence tasks, the attention mechanism can be modeled in several ways. This topic has been thoroughly studied on recurrent architectures. In this paper, we extend the previous work to the encoder-decoder attention in the Transformer architecture. We propose four different input combination strategies for the encoder-decoder attention: serial, parallel, flat, and hierarchical. We evaluate our methods on tasks of multimodal translation and translation with multiple source languages. The experiments show that the models are able to use multiple sources and improve over single source baselines.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 7; 2022: 6; 2023: 6; 2024: 2; 2025: 1.

22 papers.

Sort:

By area:

  1. 2022Causal Transformer for Estimating Counterfactual Outcomescited by 121
  2. 2022Improving Chest X-Ray Report Generation by Leveraging Warm Startingcited by 93
  3. 2021Attention, please! A survey of Neural Attention Models in Deep Learningcited by 50
  4. 2021Good for Misconceived Reasons: An Empirical Revisiting on the Need for Visual Context in Multimodal Machine Translationcited by 44
  5. 2023Exploring Better Text Image Translation with Multimodal Codebookcited by 23
  6. 2021Alternative Input Signals Ease Transfer in Multilingual Machine Translationcited by 14
  7. 2023From Interpolation to Extrapolation: Complete Length Generalization for Arithmetic Transformerscited by 10
  8. 2022HierarchyNet: Learning to Summarize Source Code with Heterogeneous Representationscited by 9
  9. 2024AnyTrans: Translate AnyText in the Image with Large Scale Modelscited by 8
  10. 2022Unsupervised domain adaptation for speech recognition with unsupervised error correctioncited by 5
  11. 2021Visual Cues and Error Correction for Translation Robustnesscited by 2
  12. 2021AlloST: Low-resource Speech Translation without Source Transcriptioncited by 2
10 more
  1. 2021Transfer Learning for Sequence Generation: from Single-source to Multi-sourcecited by 2
  2. 2022Supervised Visual Attention for Simultaneous Multimodal Machine Translationcited by 2
  3. 2023MTCue: Learning Zero-Shot Control of Extra-Textual Attributes by Leveraging Unstructured Context in Neural Machine Translationcited by 2
  4. 2023Enhancing conversational quality in language learning chatbots: An evaluation of GPT4 for ASR error correctioncited by 2
  5. 2021Predicting Opioid Use Disorder from Longitudinal Healthcare Data using Multi-stream Transformercited by 1
  6. 2023A Case Study on Context Encoding in Multi-Encoder based Document-Level Neural Machine Translationcited by 1
  7. 2023Heterogeneous Encoders Scaling In The Transformer For Neural Machine Translationcited by 1
  8. 2022Multi-Source Transformer Architectures for Audiovisual Scene Classificationcited by 0
  9. 2024Cross-Attention Based Influence Model for Manual and Nonmanual Sign Language Analysiscited by 0
  10. 2025Contextual Cues in Machine Translation: Investigating the Potential of Multi-Source Input Strategies in LLMs and NMT Systemscited by 0