Predicting Human Translation Difficulty with Neural Machine Translation
Not on the map. Why?
Abstract (arXiv)
Human translators linger on some words and phrases more than others, and predicting this variation is a step towards explaining the underlying cognitive processes. Using data from the CRITT Translation Process Research Database, we evaluate the extent to which surprisal and attentional features derived from a Neural Machine Translation (NMT) model account for reading and production times of human translators. We find that surprisal and attention are complementary predictors of translation difficulty, and that surprisal derived from a NMT model is the single most successful predictor of production duration. Our analyses draw on data from hundreds of translators operating across 13 language pairs, and represent the most comprehensive investigation of human translation difficulty to date.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 29 of its 99 references that are in the map. First posted on arXiv 19 Dec 2023.
Builds on
29 of 99 references.
References · 29
- 2017Attention Is All You Needcited by 59,932
- 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,290
- 2020A Survey on Neural Network Interpretabilitycited by 291
- 2019Massively Multilingual Neural Machine Translationcited by 246
- 2021Post-hoc Interpretability for Neural NLP: A Surveycited by 155
- 2022mGPT: Few-Shot Learners Go Multilingualcited by 141
- 2023SeamlessM4T: Massively Multilingual & Multimodal Machine Translationcited by 124
- 2020On the Predictive Power of Neural Language Models for Human Real-Time Comprehension Behaviorcited by 115
- 2016Modeling Coverage for Neural Machine Translationcited by 110
- 2023Testing the Predictions of Surprisal Theory in 11 Languagescited by 75
- 2019Attention Interpretability Across NLP Taskscited by 71
- 2019Investigating Multilingual NMT Representations at Scalecited by 68
17 more
- 2019Domain Robustness in Neural Machine Translationcited by 64
- 2021Revisiting the Uniform Information Density Hypothesiscited by 63
- 2023Adaptive Machine Translation with Large Language Modelscited by 58
- 2021Lower Perplexity is Not Always Human-Likecited by 52
- 2018Recurrent Stacking of Layers for Compact Neural Machine Translation Modelscited by 38
- 2021A Targeted Assessment of Incremental Processing in Neural LanguageModels and Humanscited by 32
- 2022Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translationcited by 28
- 2021Accounting for Agreement Phenomena in Sentence Comprehension with Transformer Language Models: Effects of Similarity-based Interference on Surprisal and Attentioncited by 26
- 2021A surprisal--duration trade-off across and within the world's languagescited by 22
- 2021Do Context-Aware Translation Models Pay the Right Attention?cited by 21
- 2019Towards Understanding Neural Machine Translation with Word Importancecited by 19
- 2021Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Modelcited by 18
- 2018On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translationcited by 17
- 2022Entropy- and Distance-Based Predictors From GPT-2 Attention Patterns Predict Reading Times Over and Above GPT-2 Surprisalcited by 14
- 2020On the Sub-Layer Functionalities of Transformer Decodercited by 12
- 2021Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictionscited by 11
- 2019Encoders Help You Disambiguate Word Senses in Neural Machine Translationcited by 6
Built on by
Citing papers per year: 2025: 1.
1 paper.