
-
Quality at a Glance: An Audit of Web-Crawled Multilingual Datasets
With the success of large-scale pre-training and multilingual modeling i...
read it
-
MasakhaNER: Named Entity Recognition for African Languages
We take a step towards addressing the under-representation of the Africa...
read it
-
Neural Machine Translation for Extremely Low-Resource African Languages: A Case Study on Bambara
Low-resource languages present unique challenges to (neural) machine tra...
read it
-
Learning from Human Feedback: Challenges for Real-World Reinforcement Learning in NLP
Large volumes of interaction logs can be collected from NLP systems that...
read it
-
KINNEWS and KIRNEWS: Benchmarking Cross-Lingual Text Classification for Kinyarwanda and Kirundi
Recent progress in text classification has been focused on high-resource...
read it
-
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages
Research in NLP lacks geographic diversity, and the question of how NLP ...
read it
-
Inference Strategies for Machine Translation with Conditional Masking
Conditional masked language model (CMLM) training has proven successful ...
read it
-
Correct Me If You Can: Learning from Error Corrections and Markings
Sequence-to-sequence learning involves a trade-off between signal streng...
read it
-
On optimal transformer depth for low-resource language translation
Transformers have shown great promise as an approach to Neural Machine T...
read it
-
Masakhane – Machine Translation For Africa
Africa has over 2000 languages. Despite this, African languages account ...
read it
-
Joey NMT: A Minimalist NMT Toolkit for Novices
We present Joey NMT, a minimalist neural machine translation toolkit bas...
read it
-
Self-Regulated Interactive Sequence-to-Sequence Learning
Not all types of supervision signals are created equal: Different types ...
read it
-
Learning to Segment Inputs for NMT Favors Character-Level Processing
Most modern neural machine translation (NMT) systems rely on presegmente...
read it
-
Optimally Segmenting Inputs for NMT Shows Preference for Character-Level Processing
Most modern neural machine translation (NMT) systems rely on presegmente...
read it
-
Explaining and Generalizing Back-Translation through Wake-Sleep
Back-translation has become a commonly employed heuristic for semi-super...
read it
-
Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning
We present a study on reinforcement learning (RL) from human bandit feed...
read it
-
A Reinforcement Learning Approach to Interactive-Predictive Neural Machine Translation
We present an approach to interactive-predictive neural machine translat...
read it
-
Can Neural Machine Translation be Improved with User Feedback?
We present the first real-world application of methods for improving neu...
read it
-
A Shared Task on Bandit Learning for Machine Translation
We introduce and describe the results of a novel shared task on bandit l...
read it
-
Bandit Structured Prediction for Neural Sequence-to-Sequence Learning
Bandit structured prediction describes a stochastic optimization framewo...
read it
-
Stochastic Structured Prediction under Bandit Feedback
Stochastic structured prediction under bandit feedback follows a learnin...
read it