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

• URL: http://arxiv.org/abs/2006.04050v1
• Date: Sun, 7 Jun 2020 05:46:15 GMT
• Title: Growing Together: Modeling Human Language Learning With n-Best Multi-Checkpoint Machine Translation
• Authors: El Moatez Billah Nagoudi, Muhammad Abdul-Mageed, Hasan Cavusoglu
• Abstract summary: We view MT models at various training stages as human learners at different levels. We employ an ensemble of multi-checkpoints from the same model to generate translation sequences with various levels of fluency. We achieve 37.57 macro F1 with a 6 checkpoint model ensemble on the official English to Portuguese shared task test data.
• Score: 8.9379057739817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Enhancing Translation for Indigenous Languages: Experiments with Multilingual Models [57.10972566048735]
  We present the system descriptions for three methods. We used two multilingual models, namely M2M-100 and mBART50, and one bilingual (one-to-one) -- Helsinki NLP Spanish-English translation model. We experimented with 11 languages from America and report the setups we used as well as the results we achieved.
  arXiv  Detail & Related papers  (2023-05-27T08:10:40Z)
• An Open Dataset and Model for Language Identification [84.15194457400253]
  We present a LID model which achieves a macro-average F1 score of 0.93 and a false positive rate of 0.033 across 201 languages. We make both the model and the dataset available to the research community.
  arXiv  Detail & Related papers  (2023-05-23T08:43:42Z)
• UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining [92.3702056505905]
  We propose a new sampling method, UniMax, that delivers more uniform coverage of head languages while mitigating overfitting on tail languages. We find that UniMax outperforms standard temperature-based sampling, and the benefits persist as scale increases.
  arXiv  Detail & Related papers  (2023-04-18T17:45:50Z)
• Towards the Next 1000 Languages in Multilingual Machine Translation: Exploring the Synergy Between Supervised and Self-Supervised Learning [48.15259834021655]
  We present a pragmatic approach towards building a multilingual machine translation model that covers hundreds of languages. We use a mixture of supervised and self-supervised objectives, depending on the data availability for different language pairs. We demonstrate that the synergy between these two training paradigms enables the model to produce high-quality translations in the zero-resource setting.
  arXiv  Detail & Related papers  (2022-01-09T23:36:44Z)
• Few-shot Learning with Multilingual Language Models [66.49496434282564]
  We train multilingual autoregressive language models on a balanced corpus covering a diverse set of languages. Our largest model sets new state of the art in few-shot learning in more than 20 representative languages. We present a detailed analysis of where the model succeeds and fails, showing in particular that it enables cross-lingual in-context learning.
  arXiv  Detail & Related papers  (2021-12-20T16:52:35Z)
• Handshakes AI Research at CASE 2021 Task 1: Exploring different approaches for multilingual tasks [0.22940141855172036]
  The aim of the CASE 2021 Shared Task 1 was to detect and classify socio-political and crisis event information in a multilingual setting. Our submission contained entries in all of the subtasks, and the scores obtained validated our research finding.
  arXiv  Detail & Related papers  (2021-10-29T07:58:49Z)
• Beyond English-Centric Multilingual Machine Translation [74.21727842163068]
  We create a true Many-to-Many multilingual translation model that can translate directly between any pair of 100 languages. We build and open source a training dataset that covers thousands of language directions with supervised data, created through large-scale mining. Our focus on non-English-Centric models brings gains of more than 10 BLEU when directly translating between non-English directions while performing competitively to the best single systems of WMT.
  arXiv  Detail & Related papers  (2020-10-21T17:01:23Z)
• ANDES at SemEval-2020 Task 12: A jointly-trained BERT multilingual model for offensive language detection [0.6445605125467572]
  We jointly-trained a single model by fine-tuning Multilingual BERT to tackle the task across all the proposed languages. Our single model had competitive results, with a performance close to top-performing systems.
  arXiv  Detail & Related papers  (2020-08-13T16:07:00Z)
• Automatic Machine Translation Evaluation in Many Languages via Zero-Shot Paraphrasing [11.564158965143418]
  We frame the task of machine translation evaluation as one of scoring machine translation output with a sequence-to-sequence paraphraser. We propose training the paraphraser as a multilingual NMT system, treating paraphrasing as a zero-shot translation task. Our method is simple and intuitive, and does not require human judgements for training.
  arXiv  Detail & Related papers  (2020-04-30T03:32:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.