Systematic generalization with edge transformers

L Bergen, T O'Donnell… - Advances in Neural …, 2021 - proceedings.neurips.cc
Recent research suggests that systematic generalization in natural language understanding
remains a challenge for state-of-the-art neural models such as Transformers and Graph …

Finding needles in a haystack: Sampling structurally-diverse training sets from synthetic data for compositional generalization

I Oren, J Herzig, J Berant - arxiv preprint arxiv:2109.02575, 2021 - arxiv.org
Modern semantic parsers suffer from two principal limitations. First, training requires
expensive collection of utterance-program pairs. Second, semantic parsers fail to generalize …

Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks

Y Jiang, M Bansal - arxiv preprint arxiv:2109.15256, 2021 - arxiv.org
Systematic compositionality is an essential mechanism in human language, allowing the
recombination of known parts to create novel expressions. However, existing neural models …

Compositional generalization in multilingual semantic parsing over Wikidata

R Cui, R Aralikatte, H Lent… - Transactions of the …, 2022 - direct.mit.edu
Semantic parsing (SP) allows humans to leverage vast knowledge resources through
natural interaction. However, parsers are mostly designed for and evaluated on English …

Data factors for better compositional generalization

X Zhou, Y Jiang, M Bansal - arxiv preprint arxiv:2311.04420, 2023 - arxiv.org
Recent diagnostic datasets on compositional generalization, such as SCAN (Lake and
Baroni, 2018) and COGS (Kim and Linzen, 2020), expose severe problems in models …

Mutual exclusivity training and primitive augmentation to induce compositionality

Y Jiang, X Zhou, M Bansal - arxiv preprint arxiv:2211.15578, 2022 - arxiv.org
Recent datasets expose the lack of the systematic generalization ability in standard
sequence-to-sequence models. In this work, we analyze this behavior of seq2seq models …

Transformer module networks for systematic generalization in visual question answering

M Yamada, V D'Amario, K Takemoto… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Transformers achieve great performance on Visual Question Answering (VQA). However,
their systematic generalization capabilities, ie, handling novel combinations of known …

Understanding robust generalization in learning regular languages

S Dan, O Bastani, D Roth - International Conference on …, 2022 - proceedings.mlr.press
A key feature of human intelligence is the ability to generalize beyond the training
distribution, for instance, parsing longer sentences than seen in the past. Currently, deep …

Compositional generalization in dependency parsing

E Goodwin, S Reddy, TJ O'Donnell… - arxiv preprint arxiv …, 2021 - arxiv.org
Compositionality--the ability to combine familiar units like words into novel phrases and
sentences--has been the focus of intense interest in artificial intelligence in recent years. To …

On Evaluating Multilingual Compositional Generalization with Translated Datasets

Z Wang, D Hershcovich - arxiv preprint arxiv:2306.11420, 2023 - arxiv.org
Compositional generalization allows efficient learning and human-like inductive biases.
Since most research investigating compositional generalization in NLP is done on English …