Challenge: Existing methods for incorporating syntactic inductive biases into transformers are limited . we introduce auxiliary loss function that converts bracketing decisions into differentiable orthogonality constraints on vector hidden states.
Approach: They propose to introduce syntactic inductive biases into transformer circuits through a structured regularizer.
Outcome: The proposed approach could unlock more robust and data-efficient learning in transformer language models . it integrates seamlessly with the standard LM objective, requiring no architectural changes.

Similar Papers

Transformer Grammars: Augmenting Transformer Language Models with Syntactic Inductive Biases at Scale (2022.tacl-1)

Copied to clipboard

Challenge: a novel class of Transformer language models that combine expressive power, scalability, and strong performance of Transformers and recursive syntactic compositions.
Approach: They introduce Transformer Grammars, a class of Transformer language models that combine expressive power and recursive syntactic compositions.
Outcome: The proposed model outperforms strong baselines on sentence-level language modeling perplexity and syntax-sensitive language evaluation metrics.
Tree-Planted Transformers: Unidirectional Transformer Language Models with Implicit Syntactic Supervision (2024.findings-acl)

Copied to clipboard

Challenge: Syntactic Language Models (SLMs) have difficulty with inference efficiency due to explicit generation of syntactical structures.
Approach: They propose a method to "plant" trees into attention weights of unidirectional Transformer LMs to implicitly reflect syntactic structures of natural language.
Outcome: The proposed method outperforms SLMs on the SyntaxGym benchmark.
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 .
Do Transformers Parse while Predicting the Masked Word? (2023.emnlp-main)

Copied to clipboard

Challenge: Existing studies show that pre-trained language models encode linguistic structures like parse trees while being trained unsupervised.
Approach: They propose to train pre-trained language models to encode linguistic structures like parse trees while unsupervised.
Outcome: The proposed model performs optimally for masked language modeling loss on the English PCFG.
Syntax-BERT: Improving Pre-trained Transformers with Syntax Trees (2021.eacl-main)

Copied to clipboard

Challenge: Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information.
Approach: They propose a plug-and-play framework that incorporates syntax trees into pre-trained Transformers.
Outcome: The proposed framework improves on pre-trained models on natural language understanding datasets and shows that it can be used to train pre-structured neural networks.
Rethinking Positional Encoding in Tree Transformer for Code Representation (2022.emnlp-main)

Copied to clipboard

Challenge: Recent works have proposed novel tree Transformers to capture the syntactic structure in source code.
Approach: They propose a novel tree Transformer encoding node positions based on a description method for tree structures to incorporate inductive bias into Transformer.
Outcome: The proposed model outperforms baselines on code summarization and completion tasks across two languages, and it is able to perform better on both local and global paradigms.
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 .
Generative Pretrained Structured Transformers: Unsupervised Syntactic Language Models at Scale (2024.acl-long)

Copied to clipboard

Challenge: Existing syntactic language models require a gold tree and sequential training to generate sentences.
Approach: They propose an unsupervised syntactic language model that incrementally generates a sentence with its syntaktic tree in a left-to-right manner.
Outcome: The proposed model outperforms existing models on grammar induction and comprehension tasks while holding a substantial acceleration on training.
A Systematic Study of Compositional Syntactic Transformer Language Models (2025.acl-long)

Copied to clipboard

Challenge: Syntactic language models (SLMs) incorporate syntactical biases into Transformers . authors identify key aspects of design choices in existing models and novel variants based on experimental results .
Approach: They propose a framework that incorporates existing and new SLMs to enhance Transformers by incorporating syntactic biases.
Outcome: The proposed framework improves on existing models and novel variants across language modeling, syntactic generalization, summarization, and inference efficiency.
Can Transformers Learn n-gram Language Models? (2024.emnlp-main)

Copied to clipboard

Challenge: Existing work has tested transformers' ability to represent formal languages, but language models are not classifiers of strings but rather distributions over them.
Approach: They relate transformers' ability to learn random n-gram language models to ngram language model (LM) they find add- smoothing outperforms transformers on the former, while transformers perform better on the latter .
Outcome: The proposed models outperform classical methods designed to learn n-gram LMs, while transformers perform better on the latter.

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