A User Study of the Incremental Learning in NMT
In the translation industry, human experts usually supervise and post-edit machine translation hypotheses. Adaptive neural machine translation systems, able to incrementally update the underlying models under an online learning regime, have been proven to be useful to improve the efficiency of this workflow. However, this incremental adaptation is somewhat unstable, and it may lead to undesirable side effects. One of them is the sporadic appearance of made-up words, as a byproduct of an erroneous application of subword segmentation techniques. In this work, we extend previous studies on on-the-fly adaptation of neural machine translation systems. We perform a user study involving professional, experienced post-editors, delving deeper on the aforementioned problems. Results show that adaptive systems were able to learn how to generate the correct translation for task-specific terms, resulting in an improvement of the user’s productivity. We also observed a close similitude, in terms of morphology, between made-up words and the words that were expected.
Code (0)
등록된 구현이 없습니다.
Tasks
Incremental LearningMachine TranslationNMTTranslationSimilar Papers 제목 키워드 기반
Preliminary Study on Incremental Learning for Large Language Model-based Recommender Systems
Adapting Large Language Models for Recommendation (LLM4Rec) has shown promising results. However, the challenges of deploying LLM4Rec in real-world scenarios remain largely unexplored. In particular, recommender models n…
AttributeIncremental LearningLanguage ModelingLanguage Modelling+2Personalizing human activity recognition models using incremental learning
In this study, the aim is to personalize inertial sensor data-based human activity recognition models using incremental learning. At first, the recognition is based on user-independent model. However, when personal strea…
Activity RecognitionGeneral ClassificationHuman Activity RecognitionIncremental LearningIncremental Adaptation of NMT for Professional Post-editors: A User Study
A common use of machine translation in the industry is providing initial translation hypotheses, which are later supervised and post-edited by a human expert. During this revision process, new bilingual data are continuo…
Machine TranslationNMTTranslationFreezing Sub-Models During Incremental Process Discovery: Extended Version
Process discovery aims to learn a process model from observed process behavior. From a user's perspective, most discovery algorithms work like a black box. Besides parameter tuning, there is no interaction between the us…
Semantic Prompting: Agentic Incremental Narrative Refinement through Spatial Semantic Interaction
Interactive spatial layouts empower users to synthesize information and organize findings for sensemaking. While Large Language Models (LLMs) can automate narrative generation from spatial layouts, current collage-based …