TransQuest at WMT2020: Sentence-Level Direct Assessment

• URL: http://arxiv.org/abs/2010.05318v1
• Date: Sun, 11 Oct 2020 18:53:05 GMT
• Title: TransQuest at WMT2020: Sentence-Level Direct Assessment
• Authors: Tharindu Ranasinghe, Constantin Orasan, Ruslan Mitkov
• Abstract summary: We introduce a simple QE framework based on cross-lingual transformers. We use it to implement and evaluate two different neural architectures. Our approach is the winning solution in all of the language pairs according to the WMT 2020 official results.
• Score: 14.403165053223395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents the team TransQuest's participation in Sentence-Level Direct Assessment shared task in WMT 2020. We introduce a simple QE framework based on cross-lingual transformers, and we use it to implement and evaluate two different neural architectures. The proposed methods achieve state-of-the-art results surpassing the results obtained by OpenKiwi, the baseline used in the shared task. We further fine tune the QE framework by performing ensemble and data augmentation. Our approach is the winning solution in all of the language pairs according to the WMT 2020 official results.

Related papers

• Unify word-level and span-level tasks: NJUNLP's Participation for the WMT2023 Quality Estimation Shared Task [59.46906545506715]
  We introduce the NJUNLP team to the WMT 2023 Quality Estimation (QE) shared task. Our team submitted predictions for the English-German language pair on all two sub-tasks. Our models achieved the best results in English-German for both word-level and fine-grained error span detection sub-tasks.
  arXiv  Detail & Related papers  (2023-09-23T01:52:14Z)
• BJTU-WeChat's Systems for the WMT22 Chat Translation Task [66.81525961469494]
  This paper introduces the joint submission of the Beijing Jiaotong University and WeChat AI to the WMT'22 chat translation task for English-German. Based on the Transformer, we apply several effective variants. Our systems achieve 0.810 and 0.946 COMET scores.
  arXiv  Detail & Related papers  (2022-11-28T02:35:04Z)
• Alibaba-Translate China's Submission for WMT 2022 Quality Estimation Shared Task [80.22825549235556]
  We present our submission to the sentence-level MQM benchmark at Quality Estimation Shared Task, named UniTE. Specifically, our systems employ the framework of UniTE, which combined three types of input formats during training with a pre-trained language model. Results show that our models reach 1st overall ranking in the Multilingual and English-Russian settings, and 2nd overall ranking in English-German and Chinese-English settings.
  arXiv  Detail & Related papers  (2022-10-18T08:55:27Z)
• Alibaba-Translate China's Submission for WMT 2022 Metrics Shared Task [61.34108034582074]
  We build our system based on the core idea of UNITE (Unified Translation Evaluation) During the model pre-training phase, we first apply the pseudo-labeled data examples to continuously pre-train UNITE. During the fine-tuning phase, we use both Direct Assessment (DA) and Multidimensional Quality Metrics (MQM) data from past years' WMT competitions.
  arXiv  Detail & Related papers  (2022-10-18T08:51:25Z)
• UniTE: Unified Translation Evaluation [63.58868113074476]
  UniTE is the first unified framework engaged with abilities to handle all three evaluation tasks. We testify our framework on WMT 2019 Metrics and WMT 2020 Quality Estimation benchmarks.
  arXiv  Detail & Related papers  (2022-04-28T08:35:26Z)
• QEMind: Alibaba's Submission to the WMT21 Quality Estimation Shared Task [24.668012925628968]
  We present our submissions to the WMT 2021 QE shared task. We propose several useful features to evaluate the uncertainty of the translations to build our QE system, named textitQEMind. We show that our multilingual systems outperform the best system in the Direct Assessment QE task of WMT 2020.
  arXiv  Detail & Related papers  (2021-12-30T02:27:29Z)
• The JHU-Microsoft Submission for WMT21 Quality Estimation Shared Task [14.629380601429956]
  This paper presents the JHU-Microsoft joint submission for WMT 2021 quality estimation shared task. We only participate in Task 2 (post-editing effort estimation) of the shared task, focusing on the target-side word-level quality estimation. We demonstrate the competitiveness of our system compared to the widely adopted OpenKiwi-XLM baseline.
  arXiv  Detail & Related papers  (2021-09-17T19:13:31Z)
• TransQuest: Translation Quality Estimation with Cross-lingual Transformers [14.403165053223395]
  We propose a simple QE framework based on cross-lingual transformers. We use it to implement and evaluate two different neural architectures. Our evaluation shows that the proposed methods achieve state-of-the-art results.
  arXiv  Detail & Related papers  (2020-11-01T16:34:44Z)
• Unbabel's Participation in the WMT20 Metrics Shared Task [8.621669980568822]
  We present the contribution of the Unbabel team to the WMT 2020 Shared Task on Metrics. We intend to participate on the segment-level, document-level and system-level tracks on all language pairs. We illustrate results of our models in these tracks with reference to test sets from the previous year.
  arXiv  Detail & Related papers  (2020-10-29T12:59:44Z)
• Learning to Evaluate Translation Beyond English: BLEURT Submissions to the WMT Metrics 2020 Shared Task [30.889496911261677]
  This paper describes our contribution to the WMT 2020 Metrics Shared Task. We make several submissions based on BLEURT, a metric based on transfer learning. We show how to combine BLEURT's predictions with those of YiSi and use alternative reference translations to enhance the performance.
  arXiv  Detail & Related papers  (2020-10-08T23:16:26Z)
• WeChat Neural Machine Translation Systems for WMT20 [61.03013964996131]
  Our system is based on the Transformer with effective variants and the DTMT architecture. In our experiments, we employ data selection, several synthetic data generation approaches, advanced finetuning approaches and self-bleu based model ensemble. Our constrained Chinese to English system achieves 36.9 case-sensitive BLEU score, which is the highest among all submissions.
  arXiv  Detail & Related papers  (2020-10-01T08:15:09Z)

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.