paper-with-me

홈 › Papers

Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks

2018-01-01 · ICLR 2018 1 · Brenden Lake, Marco Baroni

Humans can understand and produce new utterances effortlessly, thanks to their systematic compositional skills. Once a person learns the meaning of a new verb "dax," he or she can immediately understand the meaning of "dax twice" or "sing and dax." In this paper, we introduce the SCAN domain, consisting of a set of simple compositional navigation commands paired with the corresponding action sequences. We then test the zero-shot generalization capabilities of a variety of recurrent neural networks (RNNs) trained on SCAN with sequence-to-sequence methods. We find that RNNs can generalize well when the differences between training and test commands are small, so that they can apply "mix-and-match" strategies to solve the task. However, when generalization requires systematic compositional skills (as in the "dax" example above), RNNs fail spectacularly. We conclude with a proof-of-concept experiment in neural machine translation, supporting the conjecture that lack of systematicity is an important factor explaining why neural networks need very large training sets.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

AllMachine TranslationTranslationZero-shot Generalization

Similar Papers 제목 키워드 기반

Linguistic generalization and compositionality in modern artificial neural networks

2019-03-30 · Marco Baroni

In the last decade, deep artificial neural networks have achieved astounding performance in many natural language processing tasks. Given the high productivity of language, these models must possess effective generalizat…

Systematic Generalization

Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?

2023-02-15 · Keito Kudo, Yoichi Aoki, Tatsuki Kuribayashi, Ana Brassard 외

Compositionality is a pivotal property of symbolic reasoning. However, how well recent neural models capture compositionality remains underexplored in the symbolic reasoning tasks. This study empirically addresses this q…

Arithmetic Reasoning

A Benchmark for Compositional Visual Reasoning

2022-06-11 · Aimen Zerroug, Mohit Vaishnav, Julien Colin, Sebastian Musslick 외

A fundamental component of human vision is our ability to parse complex visual scenes and judge the relations between their constituent objects. AI benchmarks for visual reasoning have driven rapid progress in recent yea…

Visual Reasoning

Fodor and Pylyshyn's Legacy -- Still No Human-like Systematic Compositionality in Neural Networks

2025-06-02 · Tim Woydt, Moritz Willig, Antonia Wüst, Lukas Helff 외

Strong meta-learning capabilities for systematic compositionality are emerging as an important skill for navigating the complex and changing tasks of today's world. However, in presenting models for robust adaptation to …

Meta-Learning

Compositional Temporal Grounding with Structured Variational Cross-Graph Correspondence Learning

2022-03-24 · CVPR 2022 1 · Juncheng Li, Junlin Xie, Long Qian, Linchao Zhu 외

Temporal grounding in videos aims to localize one target video segment that semantically corresponds to a given query sentence. Thanks to the semantic diversity of natural language descriptions, temporal grounding allows…

DiversitySemantic correspondenceSentence