Findings of the 2022 conference on machine translation (WMT22)
This paper presents the results of the General Machine Translation Task organised as part
of the Conference on Machine Translation (WMT) 2022. In the general MT task, participants …
of the Conference on Machine Translation (WMT) 2022. In the general MT task, participants …
A survey on zero pronoun translation
Zero pronouns (ZPs) are frequently omitted in pro-drop languages (eg Chinese, Hungarian,
and Hindi), but should be recalled in non-pro-drop languages (eg English). This …
and Hindi), but should be recalled in non-pro-drop languages (eg English). This …
Sentence-Level or Token-Level? A Comprehensive Study on Knowledge Distillation
Knowledge distillation, transferring knowledge from a teacher model to a student model, has
emerged as a powerful technique in neural machine translation for compressing models or …
emerged as a powerful technique in neural machine translation for compressing models or …
Granularity is crucial when applying differential privacy to text: An investigation for neural machine translation
DNL Vu, T Igamberdiev, I Habernal - arXiv preprint arXiv:2407.18789, 2024 - arxiv.org
Applying differential privacy (DP) by means of the DP-SGD algorithm to protect individual
data points during training is becoming increasingly popular in NLP. However, the choice of …
data points during training is becoming increasingly popular in NLP. However, the choice of …
xTower: A Multilingual LLM for Explaining and Correcting Translation Errors
While machine translation (MT) systems are achieving increasingly strong performance on
benchmarks, they often produce translations with errors and anomalies. Understanding …
benchmarks, they often produce translations with errors and anomalies. Understanding …
Can Automatic Metrics Assess High-Quality Translations?
Automatic metrics for evaluating translation quality are typically validated by measuring how
well they correlate with human assessments. However, correlation methods tend to capture …
well they correlate with human assessments. However, correlation methods tend to capture …
Dialogue Quality and Emotion Annotations for Customer Support Conversations
J Mendonça, P Pereira, M Menezes… - arXiv preprint arXiv …, 2023 - arxiv.org
Task-oriented conversational datasets often lack topic variability and linguistic diversity.
However, with the advent of Large Language Models (LLMs) pretrained on extensive …
However, with the advent of Large Language Models (LLMs) pretrained on extensive …
MQM-Chat: Multidimensional Quality Metrics for Chat Translation
The complexities of chats pose significant challenges for machine translation models.
Recognizing the need for a precise evaluation metric to address the issues of chat …
Recognizing the need for a precise evaluation metric to address the issues of chat …
[PDF][PDF] Document-Level Pretraining for Neural Chat Translation
T Kaiser - 2023 - ai4lt.anthropomatik.kit.edu
This study aims to investigate methods for inducing document-level context awareness in
Neural Machine Translation (NMT) models for bilingual chat data. Previous research …
Neural Machine Translation (NMT) models for bilingual chat data. Previous research …