Challenge: LSTMs and Transformers perform well at capturing the surface statistics of child-directed speech, but both model types generalize in a way consistent with an incorrect linear rule than the correct hierarchical rule.
Approach: They train LSTMs and Transformers on text from the CHILDES corpus and evaluate what they learn about English yes/no questions.
Outcome: The proposed models perform well at capturing the surface statistics of child-directed speech, but generalize more consistent with an incorrect linear rule than the correct hierarchical rule.

Similar Papers

Semantic Training Signals Promote Hierarchical Syntactic Generalization in Transformers (2024.emnlp-main)

Copied to clipboard

Challenge: Neural networks without hierarchical biases struggle to learn linguistic rules that come naturally to humans . et al., 2018: Transformers trained on form and meaning favor hierarchically generalization more than those trained on forms alone.
Approach: They examine whether neural networks without hierarchical biases can generalize more like humans . they find that Transformers trained on form and meaning favor hierarchic generalization .
Outcome: The proposed neural networks perform better on syntactic evaluations when trained on form and meaning compared to those trained on forms alone.
Learning Syntax Without Planting Trees: Understanding Hierarchical Generalization in Transformers (2025.tacl-1)

Copied to clipboard

Challenge: Inductive biases in transformers can cause hierarchical generalization without explicitly encoding structural bias.
Approach: They investigate sources of inductive bias in transformer models and their training that could cause such preference for hierarchical generalization.
Outcome: The proposed model can generalize to novel syntactic forms without explicit bias . the proposed model is able to generalize on a dataset with a hierarchical grammar .
Does Syntax Need to Grow on Trees? Sources of Hierarchical Inductive Bias in Sequence-to-Sequence Networks (2020.tacl-1)

Copied to clipboard

Challenge: Inductive biases can arise from any aspect of the model architecture, study finds . we investigate which architectural factors affect how models generalize .
Approach: They investigate which architectural factors affect generalization behavior of neural network models . they use English question formation and English tense reinflection as test cases .
Outcome: The findings suggest that human-like generalization requires architectural syntactic structure.
How to Plant Trees in Language Models: Data and Architectural Effects on the Emergence of Syntactic Inductive Biases (2023.acl-long)

Copied to clipboard

Challenge: a recent study found that pre-training can teach language models to rely on hierarchical syntactic features . aaron ramirez: we find that pretraining on simpler language induces a hierarchic bias .
Approach: They find that pre-training can teach language models to rely on hierarchical syntactic features . authors: this suggests that in cognitively plausible language acquisition settings, models may be more data-efficient .
Outcome: a recent study shows that pre-training can teach language models to rely on hierarchical features . the findings suggest that in plausible language acquisition settings, language models may be more data-efficient than previously thought .
Does Vision Accelerate Hierarchical Generalization in Neural Language Learners? (2025.coling-main)

Copied to clipboard

Challenge: Neural language models (LMs) are arguably less data-efficient than humans from a language acquisition perspective.
Approach: They investigate the advantage of grounded language acquisition over visual input to improve syntactic generalization.
Outcome: The proposed model is less efficient than humans in language acquisition . it shows that visual input helps syntactic generalization, but not vision .
Revisiting the Hierarchical Multiscale LSTM (C18-1)

Copied to clipboard

Challenge: Hierarchical Multiscale LSTM model learns structure from character input . high complexity of architecture, training and implementations might hinder its applicability .
Approach: They propose to reproduce and ablate hierarchical multiscale LSTM language model and show that simplifying certain aspects of the architecture can improve its performance.
Outcome: The proposed model performs better when simplified and linguistic units are learned by different levels of the model.
Grokking of Hierarchical Structure in Vanilla Transformers (2023.acl-short)

Copied to clipboard

Challenge: a recent study has shown that neural sequence models like transformers can generalize hierarchically when training for extended periods.
Approach: They show that transformers can learn to generalize hierarchically after long training periods . they call this phenomenon structural grokking, which exhibits inverted U-shaped scaling in model depth .
Outcome: The proposed model generalizes better than both very deep and very shallow models on multiple datasets.
LSTMs Compose—and Learn—Bottom-Up (2020.findings-emnlp)

Copied to clipboard

Challenge: Recent work in NLP shows that LSTMs capture compositional structure in language data.
Approach: They propose to measure the decompositional interdependence between word meanings in an LSTM based on their gate interactions.
Outcome: The proposed model can model syntactic relationships rather than learning the longer-range relations independently.
Data Drives Unstable Hierarchical Generalization in LMs (2025.emnlp-main)

Copied to clipboard

Challenge: Early in training, LMs can behave like n-gram models but eventually learn tree-based syntactic rules and generalize out of distribution (OOD).
Approach: They study how complex data drives hierarchical rules, while less complex encourages shortcut learning . they find a model uses rules to generalize if its training data is *diverse* .
Outcome: The proposed model learns to generalize hierarchically if its training data is complex . a model learn if it includes center-embedded clauses, a special syntactic structure .
Structural Supervision Improves Few-Shot Learning and Syntactic Generalization in Neural Language Models (2020.emnlp-main)

Copied to clipboard

Challenge: Existing studies have not investigated the relationship between a token's frequency in the training corpus and syntactic properties models learn about it.
Approach: They develop controlled experiments that probe models’ syntactic nominal number and verbal argument structure generalizations for tokens seen as few as two times during training.
Outcome: The proposed models can make syntactic generalizations for tokens seen as few as two times during training and transfer them to transformed contexts.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations