paper-with-me

Papers

Machine Translation Reference-less Evaluation using YiSi-2 with Bilingual Mappings of Massive Multilingual Language Model

2020-11-01 · WMT (EMNLP) 2020 11 · Chi-kiu Lo, Samuel Larkin

We present a study on using YiSi-2 with massive multilingual pretrained language models for machine translation (MT) reference-less evaluation. Aiming at finding better semantic representation for semantic MT evaluation, we first test YiSi-2 with contextual embed- dings extracted from different layers of two different pretrained models, multilingual BERT and XLM-RoBERTa. We also experiment with learning bilingual mappings that trans- form the vector subspace of the source language to be closer to that of the target language in the pretrained model to obtain more accurate cross-lingual semantic similarity representations. Our results show that YiSi-2’s correlation with human direct assessment on translation quality is greatly improved by replacing multilingual BERT with XLM-RoBERTa and projecting the source embeddings into the tar- get embedding space using a cross-lingual lin- ear projection (CLP) matrix learnt from a small development set.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingMachine TranslationSemantic SimilaritySemantic Textual SimilarityTARTranslation

Similar Papers 제목 키워드 기반

Extended Study on Using Pretrained Language Models and YiSi-1 for Machine Translation Evaluation

2020-11-01 · WMT (EMNLP) 2020 11 · Chi-kiu Lo

We present an extended study on using pretrained language models and YiSi-1 for machine translation evaluation. Although the recently proposed contextual embedding based metrics, YiSi-1, significantly outperform BLEU and…

Language ModelingLanguage ModellingMachine TranslationTranslation

YiSi - a Unified Semantic MT Quality Evaluation and Estimation Metric for Languages with Different Levels of Available Resources

2019-08-01 · WS 2019 8 · Chi-kiu Lo

We present YiSi, a unified automatic semantic machine translation quality evaluation and estimation metric for languages with different levels of available resources. Underneath the interface with different language reso…

Machine TranslationSemantic SimilaritySemantic Textual SimilarityTranslation

PePe: Personalized Post-editing Model utilizing User-generated Post-edits

2022-09-21 · Jihyeon Lee, Taehee Kim, Yunwon Tae, Cheonbok Park 외

Incorporating personal preference is crucial in advanced machine translation tasks. Despite the recent advancement of machine translation, it remains a demanding task to properly reflect personal style. In this paper, we…

Automatic Post-EditingMachine TranslationTranslation

Accurate semantic textual similarity for cleaning noisy parallel corpora using semantic machine translation evaluation metric: The NRC supervised submissions to the Parallel Corpus Filtering task

2018-10-01 · WS 2018 10 · Chi-kiu Lo, Michel Simard, Darlene Stewart, Samuel Larkin 외

We present our semantic textual similarity approach in filtering a noisy web crawled parallel corpus using YiSi{---}a novel semantic machine translation evaluation metric. The systems mainly based on this supervised appr…

Machine TranslationSemantic Textual SimilarityTranslation

Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task

2020-10-08 · WMT (EMNLP) 2020 11 · Thibault Sellam, Amy Pu, Hyung Won Chung, Sebastian Gehrmann 외

The quality of machine translation systems has dramatically improved over the last decade, and as a result, evaluation has become an increasingly challenging problem. This paper describes our contribution to the WMT 2020…

Machine TranslationTransfer LearningTranslation