6 papers
Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?
HyoJung Han, Akiko Eriguchi, Haoran Xu +3
Vocabulary adaptation, which integrates new vocabulary into pre-trained language models, enables expansion to new languages and mitigates token over-fragmentation. However, existin…
X-ALMA: Plug & Play Modules and Adaptive Rejection for Quality Translation at Scale
Haoran Xu, Kenton Murray, Philipp Koehn +3
Large language models (LLMs) have achieved remarkable success across various NLP tasks with a focus on English due to English-centric pre-training and limited multilingual data. In…
Paradigm Completion for Derivational Morphology
Ryan Cotterell, Ekaterina Vylomova, Huda Khayrallah +2
The generation of complex derived word forms has been an overlooked problem in NLP; we fill this gap by applying neural sequence-to-sequence models to the task. We overview the the…
How to Choose How to Choose Your Chatbot: A Massively Multi-System MultiReference Data Set for Dialog Metric Evaluation
Huda Khayrallah, Zuhaib Akhtar, Edward Cohen +2
We release MMSMR, a Massively Multi-System MultiReference dataset to enable future work on metrics and evaluation for dialog. Automatic metrics for dialogue evaluation should be ro…
Improving Statistical Significance in Human Evaluation of Automatic Metrics via Soft Pairwise Accuracy
Brian Thompson, Nitika Mathur, Daniel Deutsch +1
Selecting an automatic metric that best emulates human annotators is often non-trivial, because there is no clear definition of "best emulates." A meta-metric is required to compar…
On-the-Fly Fusion of Large Language Models and Machine Translation
Hieu Hoang, Huda Khayrallah, Marcin Junczys-Dowmunt
We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) w…