paper-with-me

Papers

Data Processing Matters: SRPH-Konvergen AI's Machine Translation System for WMT'21

2021-11-20 · Lintang Sutawika, Jan Christian Blaise Cruz

In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT'21 Large Scale Multilingual Translation Task - Small Track 2. We submit a standard Seq2Seq Transformer model to the shared task without any training or architecture tricks, relying mainly on the strength of our data preprocessing techniques to boost performance. Our final submission model scored 22.92 average BLEU on the FLORES-101 devtest set, and scored 22.97 average BLEU on the contest's hidden test set, ranking us sixth overall. Despite using only a standard Transformer, our model ranked first in Indonesian to Javanese, showing that data preprocessing matters equally, if not more, than cutting edge model architectures and training techniques.

📄 PDF Abstract BibTeX arXiv:2111.10513

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationTranslation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Tanh Activation 설명 없음
Adam 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

Similar Papers 제목 키워드 기반

Data Processing Matters: SRPH-Konvergen AI’s Machine Translation System for WMT’21

2021-11-01 · WMT (EMNLP) 2021 11 · Lintang Sutawika, Jan Christian Blaise Cruz

In this paper, we describe the submission of the joint Samsung Research Philippines-Konvergen AI team for the WMT’21 Large Scale Multilingual Translation Task - Small Track 2. We submit a standard Seq2Seq Transformer mod…

Machine TranslationTranslation

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

2025-11-03 · Andrew M. Bean, Ryan Othniel Kearns, Angelika Romanou, Franziska Sofia Hafner 외 arxiv

Evaluating large language models (LLMs) is crucial for both assessing their capabilities and identifying safety or robustness issues prior to deployment. Reliably measuring abstract and complex phenomena such as 'safety'…

Cross-lingual Dependency Transfer : What Matters? Assessing the Impact of Pre- and Post-processing

2016-06-01 · WS 2016 6 · Oph{\'e}lie Lacroix, Guillaume Wisniewski, Fran{\c{c}}ois Yvon

Enforcing Fairness Where It Matters: An Approach Based on Difference-of-Convex Constraints

2025-05-18 · Yutian He, Yankun Huang, Yao Yao, Qihang Lin

Fairness in machine learning has become a critical concern, particularly in high-stakes applications. Existing approaches often focus on achieving full fairness across all score ranges generated by predictive models, ens…

Fairness

The choice of scaling technique matters for classification performance

2022-12-23 · Lucas B. V. de Amorim, George D. C. Cavalcanti, Rafael M. O. Cruz

Dataset scaling, also known as normalization, is an essential preprocessing step in a machine learning pipeline. It is aimed at adjusting attributes scales in a way that they all vary within the same range. This transfor…

Classification