Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
Recent impressive improvements in NLP, largely based on the success of contextual neural
language models, have been mostly demonstrated on at most a couple dozen high-resource …
language models, have been mostly demonstrated on at most a couple dozen high-resource …
The impact of indirect machine translation on sentiment classification
Sentiment classification has been crucial for many natural language processing (NLP)
applications, such as the analysis of movie reviews, tweets, or customer feedback. A …
applications, such as the analysis of movie reviews, tweets, or customer feedback. A …
Comparing statistical and neural machine translation performance on hindi-to-tamil and english-to-tamil
Phrase-based statistical machine translation (PB-SMT) has been the dominant paradigm in
machine translation (MT) research for more than two decades. Deep neural MT models have …
machine translation (MT) research for more than two decades. Deep neural MT models have …
RoCS-MT: Robustness Challenge Set for Machine Translation
RoCS-MT, a Robust Challenge Set for Machine Translation (MT), is designed to test MT
systems' ability to translate user-generated content (UGC) that displays non-standard …
systems' ability to translate user-generated content (UGC) that displays non-standard …
Limsi@ wmt 2020
This paper describes LIMSI's submissions to the translation shared tasks at WMT'20. This
year we have focused our efforts on the biomedical translation task, developing a resource …
year we have focused our efforts on the biomedical translation task, developing a resource …
Understanding the impact of UGC specificities on translation quality
This work takes a critical look at the evaluation of user-generated content automatic
translation, the well-known specificities of which raise many challenges for MT. Our analyses …
translation, the well-known specificities of which raise many challenges for MT. Our analyses …
An error-based investigation of statistical and neural machine translation performance on Hindi-to-Tamil and English-to-Tamil
Statistical machine translation (SMT) was the state-of-the-art in machine translation (MT)
research for more than two decades, but has since been superseded by neural MT (NMT) …
research for more than two decades, but has since been superseded by neural MT (NMT) …
Effects of different types of noise in user-generated reviews on human and machine translations including ChatGPT
M Popović, E Lapshinova-Koltunski… - Proceedings of the …, 2024 - aclanthology.org
This paper investigates effects of noisy source texts (containing spelling and grammar
errors, informal words or expressions, etc.) on human and machine translations, namely …
errors, informal words or expressions, etc.) on human and machine translations, namely …
Phonetic normalization for machine translation of user generated content
We present an approach to correct noisy User Generated Content (UGC) in French aiming to
produce a pretreatement pipeline to improve Machine Translation for this kind of non …
produce a pretreatement pipeline to improve Machine Translation for this kind of non …
Multi-way Variational NMT for UGC: Improving Robustness in Zero-shot Scenarios via Mixture Density Networks
This work presents a novel Variational Neural Machine Translation (VNMT) architecture with
enhanced robustness properties, which we investigate through a detailed case-study …
enhanced robustness properties, which we investigate through a detailed case-study …