# Re-evaluating the Need for Multimodal Signals in Unsupervised Grammar Induction

arXiv: https://arxiv.org/abs/2212.10564 · HTML: https://mlsanity.com/paper/2212.10564/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 43 references that are in the map.
- First posted on arXiv 20 Dec 2022.

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Efficient Estimation of Word Representations in Vector Space](https://mlsanity.com/paper/1301.3781/) (2013)
- [Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset](https://mlsanity.com/paper/1705.07750/) (2017)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Identity Mappings in Deep Residual Networks](https://mlsanity.com/paper/1603.05027/) (2016)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [CNN Architectures for Large-Scale Audio Classification](https://mlsanity.com/paper/1609.09430/) (2016)
- [Localizing Moments in Video with Natural Language](https://mlsanity.com/paper/1708.01641/) (2017)
- [Towards Automatic Learning of Procedures from Web Instructional Videos](https://mlsanity.com/paper/1703.09788/) (2017)
- [Constituency Parsing with a Self-Attentive Encoder](https://mlsanity.com/paper/1805.01052/) (2018)
- [Multilingual Constituency Parsing with Self-Attention and Pre-Training](https://mlsanity.com/paper/1812.11760/) (2018)
- [Ordered Neurons: Integrating Tree Structures into Recurrent Neural Networks](https://mlsanity.com/paper/1810.09536/) (2018)
- [Compound Probabilistic Context-Free Grammars for Grammar Induction](https://mlsanity.com/paper/1906.10225/) (2019)
- [PixelLink: Detecting Scene Text via Instance Segmentation](https://mlsanity.com/paper/1801.01315/) (2018)
- [Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders](https://mlsanity.com/paper/1904.02142/) (2019)
- [Neural Language Modeling by Jointly Learning Syntax and Lexicon](https://mlsanity.com/paper/1711.02013/) (2017)
- [Visually Grounded Neural Syntax Acquisition](https://mlsanity.com/paper/1906.02890/) (2019)
- [Visually Grounded Compound PCFGs](https://mlsanity.com/paper/2009.12404/) (2020)
- [Unsupervised Parsing via Constituency Tests](https://mlsanity.com/paper/2010.03146/) (2020)
- [Video-aided Unsupervised Grammar Induction](https://mlsanity.com/paper/2104.04369/) (2021)
- [What is Learned in Visually Grounded Neural Syntax Acquisition](https://mlsanity.com/paper/2005.01678/) (2020)

## Built on by (most cited first, 2 of 2)

- [A Survey of Inductive Reasoning for Large Language Models](https://mlsanity.com/paper/2510.10182/) (2025)
- [Reframing linguistic bootstrapping as joint inference using visually-grounded grammar induction models](https://mlsanity.com/paper/2406.11977/) (2024)

## Abstract (arXiv)

Are multimodal inputs necessary for grammar induction? Recent work has shown that multimodal training inputs can improve grammar induction. However, these improvements are based on comparisons to weak text-only baselines that were trained on relatively little textual data. To determine whether multimodal inputs are needed in regimes with large amounts of textual training data, we design a stronger text-only baseline, which we refer to as LC-PCFG. LC-PCFG is a C-PFCG that incorporates em-beddings from text-only large language models (LLMs). We use a fixed grammar family to directly compare LC-PCFG to various multi-modal grammar induction methods. We compare performance on four benchmark datasets. LC-PCFG provides an up to 17% relative improvement in Corpus-F1 compared to state-of-the-art multimodal grammar induction methods. LC-PCFG is also more computationally efficient, providing an up to 85% reduction in parameter count and 8.8x reduction in training time compared to multimodal approaches. These results suggest that multimodal inputs may not be necessary for grammar induction, and emphasize the importance of strong vision-free baselines for evaluating the benefit of multimodal approaches.