Interpretese vs. Translationese: The Uniqueness of Human Strategies in Simultaneous Interpretation

By He He, Jordan L. Boyd-Graber, Hal Daumé Iii. 2016

65 citations recorded by the source corpus.

Computational approaches to simultaneous interpretation are stymied by how little we know about the tactics human interpreters use. We produce a parallel corpus of translated and simultaneously interpreted text and study differences between them through a computational approach. Our analysis reveals that human interpreters regularly apply several effective tactics to reduce translation latency, including sentence segmentation and passivization. In addition to these unique, clever strategies, we show that limited human memory also causes other idiosyncratic properties of human interpretation such as generalization and omission of source content.

Subfields: Artificial Intelligence, General Health Professions, Machine Translation, Computational Linguistics & Semantics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Juan Pino
2. Changhan Wang
3. Ann Lee
4. Graham Neubig
5. Emmanuel Dupoux
6. Anne Wu
7. Wei-Ning Hsu
8. Morgane Rivière

In General Health Professions

1. Hal Daumé Iii
2. Changhan Wang

In Machine Translation

1. Juan Pino
2. Changhan Wang
3. Anne Wu
4. Ann Lee
5. Matthias Paulik
6. Jordan L. Boyd-Graber
7. Khanh Nguyen
8. Hal Daumé Iii

In Computational Linguistics & Semantics

1. Haifeng Wang
2. Hal Daumé Iii
3. Emmanuel Dupoux

Citations in the corpus

• VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation (2021, background): “There are differences, however, between translationese and interpretese (Sridhar et al., 2013; He et al., 2016), where interpreters develop a variety of strategies to improve simultaneity.”
• Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback (2017, background): “…to improve the systems or to extend to richer action spaces for problems like simultaneous translation, which requires prediction (Gris-som II et al., 2014) and reordering (He et al., 2015) among other strategies to both minimize delay and effectively translate a sentence (He et al., 2016).”
• STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework (2018, background): “Target side → ited memory forces human interpreters to routinely omit source content (He et al., 2016).”
• Speech Translation and the End-to-End Promise: Taking Stock of Where We Are (2020, background): “Given that human translators and interpreters adapt their translation method depending on factors that include input and output medium (He et al., 2016), more research is needed beyond disfluency removal.”