Growing Together: Modeling Human Language Learning With n-Best Multi-Checkpoint Machine Translation

06/07/2020
by   El Moatez Billah Nagoudi, et al.
0

We describe our submission to the 2020 Duolingo Shared Task on Simultaneous Translation And Paraphrase for Language Education (STAPLE) (Mayhew et al., 2020). We view MT models at various training stages (i.e., checkpoints) as human learners at different levels. Hence, we employ an ensemble of multi-checkpoints from the same model to generate translation sequences with various levels of fluency. From each checkpoint, for our best model, we sample n-Best sequences (n=10) with a beam width =100. We achieve 37.57 macro F1 with a 6 checkpoint model ensemble on the official English to Portuguese shared task test data, outperforming a baseline Amazon translation system of 21.30 macro F1 and ultimately demonstrating the utility of our intuitive method.

READ FULL TEXT
research
06/19/2019

The Effect of Translationese in Machine Translation Test Sets

The effect of translationese has been studied in the field of machine tr...
research
05/17/2021

Ensemble-based Transfer Learning for Low-resource Machine Translation Quality Estimation

Quality Estimation (QE) of Machine Translation (MT) is a task to estimat...
research
07/27/2017

A Shared Task on Bandit Learning for Machine Translation

We introduce and describe the results of a novel shared task on bandit l...
research
08/31/2018

Ensemble Sequence Level Training for Multimodal MT: OSU-Baidu WMT18 Multimodal Machine Translation System Report

This paper describes multimodal machine translation systems developed jo...
research
01/09/2022

An Ensemble Approach to Acronym Extraction using Transformers

Acronyms are abbreviated units of a phrase constructed by using initial ...
research
05/19/2016

Automatic TM Cleaning through MT and POS Tagging: Autodesk's Submission to the NLP4TM 2016 Shared Task

We describe a machine learning based method to identify incorrect entrie...
research
06/03/2023

Span Identification of Epistemic Stance-Taking in Academic Written English

Responding to the increasing need for automated writing evaluation (AWE)...

Please sign up or login with your details

Forgot password? Click here to reset