paper-with-me

Papers

On Compositional Generalization of Neural Machine Translation

2021-05-31 · ACL 2021 5 · Yafu Li, Yongjing Yin, Yulong Chen, Yue Zhang

Modern neural machine translation (NMT) models have achieved competitive performance in standard benchmarks such as WMT. However, there still exist significant issues such as robustness, domain generalization, etc. In this paper, we study NMT models from the perspective of compositional generalization by building a benchmark dataset, CoGnition, consisting of 216k clean and consistent sentence pairs. We quantitatively analyze effects of various factors using compound translation error rate, then demonstrate that the NMT model fails badly on compositional generalization, although it performs remarkably well under traditional metrics.

📄 PDF Abstract BibTeX arXiv:2105.14802

Code (1)

yafuly/CoGnition 공식 구현

Tasks

Domain GeneralizationMachine TranslationNMTSentenceTranslation

Similar Papers 제목 키워드 기반

Evaluating Structural Generalization in Neural Machine Translation

2024-06-19 · Ryoma Kumon, Daiki Matsuoka, Hitomi Yanaka

Compositional generalization refers to the ability to generalize to novel combinations of previously observed words and syntactic structures. Since it is regarded as a desired property of neural models, recent work has a…

Machine TranslationSemantic ParsingSentenceTranslation

On Evaluating Multilingual Compositional Generalization with Translated Datasets

2023-06-20 · Zi Wang, Daniel Hershcovich

Compositional generalization allows efficient learning and human-like inductive biases. Since most research investigating compositional generalization in NLP is done on English, important questions remain underexplored. …

Machine TranslationSemantic ParsingTranslation

Compositional Generalization by Factorizing Alignment and Translation

2020-07-01 · ACL 2020 6 · Jacob Russin, Jason Jo, R O{'}Reilly, all 외

Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, hum…

Machine TranslationSystematic GeneralizationTranslation

Compositional Generalization via Neural-Symbolic Stack Machines

2020-08-15 · NeurIPS 2020 12 · Xinyun Chen, Chen Liang, Adams Wei Yu, Dawn Song 외

Despite achieving tremendous success, existing deep learning models have exposed limitations in compositional generalization, the capability to learn compositional rules and apply them to unseen cases in a systematic man…

Few-Shot LearningMachine TranslationTranslation

Can Transformers Jump Around Right in Natural Language? Assessing Performance Transfer from SCAN

2021-07-03 · EMNLP (BlackboxNLP) 2021 11 · Rahma Chaabouni, Roberto Dessì, Eugene Kharitonov

Despite their practical success, modern seq2seq architectures are unable to generalize systematically on several SCAN tasks. Hence, it is not clear if SCAN-style compositional generalization is useful in realistic NLP ta…

Machine TranslationTranslation