paper-with-me

Papers

Compositional Generalization by Factorizing Alignment and Translation

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

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, human learners readily generalize in this way, e.g. by applying known grammatical rules to novel words. Inspired by work in cognitive science suggesting a functional distinction between systems for syntactic and semantic processing, we implement a modification to an existing approach in neural machine translation, imposing an analogous separation between alignment and translation. The resulting architecture substantially outperforms standard recurrent networks on the SCAN dataset, a compositional generalization task, without any additional supervision. Our work suggests that learning to align and to translate in separate modules may be a useful heuristic for capturing compositional structure.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Machine TranslationSystematic GeneralizationTranslation

Similar Papers 제목 키워드 기반

Compositional Generalization for Neural Semantic Parsing via Span-level Supervised Attention

2021-06-01 · NAACL 2021 4 · Pengcheng Yin, Hao Fang, Graham Neubig, Adam Pauls 외

We describe a span-level supervised attention loss that improves compositional generalization in semantic parsers. Our approach builds on existing losses that encourage attention maps in neural sequence-to-sequence model…

Machine TranslationSemantic ParsingTranslationWord Alignment

Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization

2020-12-08 · Yinuo Guo, Hualei Zhu, Zeqi Lin, Bei Chen 외

Human intelligence exhibits compositional generalization (i.e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability. In this paper, we revis…

Translation

Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing

2022-10-10 · Francesco Cazzaro, Davide Locatelli, Ariadna Quattoni, Xavier Carreras

Prior work in semantic parsing has shown that conventional seq2seq models fail at compositional generalization tasks. This limitation led to a resurgence of methods that model alignments between sentences and their corre…

Semantic Parsing

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 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 th…

Domain GeneralizationMachine TranslationNMTSentence+1