Machine Translation

Machine translation (MT) aims to automatically translate text between languages, with current research heavily focused on leveraging large language models (LLMs) and exploring various architectures like encoder-decoder and decoder-only models. Key areas of investigation include improving translation quality, particularly for low-resource languages and specialized domains like medicine, mitigating biases (e.g., gender bias), and enhancing evaluation methods beyond simple correlation with human judgments. These advancements have significant implications for cross-cultural communication, information access, and the development of more equitable and effective multilingual technologies.

Papers

May 25, 2023

Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities
Sina Ahmadi, Antonios Anastasopoulos
Machine Translation Transformer Based Model Language Identification Text Normalization Resourced Language

May 23, 2023

Benchmarking Machine Translation with Cultural Awareness
Binwei Yao, Ming Jiang, Tara Bobinac, Diyi Yang, Junjie Hu
Machine Translation Benchmark Platform Parallel Corpus Cultural Background
Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration
Daniel Deutsch, George Foster, Markus Freitag
Machine Translation Calibration Performance Evaluation Metric Pairwise Comparison Pairwise Learning Fair Ranking Tie KD
Revisiting Machine Translation for Cross-lingual Classification
Mikel Artetxe, Vedanuj Goswami, Shruti Bhosale, Angela Fan, Luke Zettlemoyer
Machine Translation Multilingual Model Cross Lingual Classification
Accessing Higher Dimensions for Unsupervised Word Translation
Sida I. Wang
Machine Translation Co Occurrence Information Access Word Vector Higher Dimension
CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation
Aswanth Kumar, Ratish Puduppully, Raj Dabre, Anoop Kunchukuttan
Large Language Model Language Model Context Learning Machine Translation Translation Quality Context Example Multiple Feature
TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation
Yiming Ai, Zhiwei He, Kai Yu, Rui Wang
Data Set New Benchmark Machine Translation Metric Prediction
CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models
Aitor Ormazabal, Mikel Artetxe, Eneko Agirre
Language Model Machine Translation Model Weight Black Box Language Model Black Box Large Language Model

May 22, 2023

Syntactic Knowledge via Graph Attention with BERT in Machine Translation
Yuqian Dai, Serge Sharoff, Marc de Kamps
Machine Translation Ticket BERT Graph Attention Network Graph Attention Syntactic Dependency Meta Representation Syntactic Knowledge
Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters
Proyag Pal, Brian Thompson, Yogesh Virkar, Prashant Mathur, Alexandra Chronopoulou, Marcello Federico
Machine Translation Translation Model Utterance Length Automatic Dubbing Target Identification Phoneme Sequence
Extrapolating Multilingual Understanding Models as Multilingual Generators
Bohong Wu, Fei Yuan, Hai Zhao, Lei Li, Jingjing Xu
Machine Translation Spoken Language Understanding Multilingual Encoders Cross Lingual Generation
Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models
Ratish Puduppully, Anoop Kunchukuttan, Raj Dabre, Ai Ti Aw, Nancy F. Chen
Machine Translation Language Pair Shot Prompting Chunk Wise Different Language
Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models
Hao Wang, Hirofumi Shimizu, Daisuke Kawahara
Language Model Natural Language Processing Machine Translation Chinese Character Knowledge Comprehension Capability Read V Complex Instruction Ancient Text

Machine Translation

Papers

RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation

TranSFormer: Slow-Fast Transformer for Machine Translation

Do GPTs Produce Less Literal Translations?

Script Normalization for Unconventional Writing of Under-Resourced Languages in Bilingual Communities

Textless Speech-to-Speech Translation With Limited Parallel Data

MuLER: Detailed and Scalable Reference-based Evaluation

Leveraging GPT-4 for Automatic Translation Post-Editing

CMOT: Cross-modal Mixup via Optimal Transport for Speech Translation

Benchmarking Machine Translation with Cultural Awareness

Ties Matter: Meta-Evaluating Modern Metrics with Pairwise Accuracy and Tie Calibration

Revisiting Machine Translation for Cross-lingual Classification

Accessing Higher Dimensions for Unsupervised Word Translation

CTQScorer: Combining Multiple Features for In-context Example Selection for Machine Translation

TeCS: A Dataset and Benchmark for Tense Consistency of Machine Translation

CombLM: Adapting Black-Box Language Models through Small Fine-Tuned Models

Syntactic Knowledge via Graph Attention with BERT in Machine Translation

Improving Isochronous Machine Translation with Target Factors and Auxiliary Counters

Extrapolating Multilingual Understanding Models as Multilingual Generators

Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models

Kanbun-LM: Reading and Translating Classical Chinese in Japanese Methods by Language Models