Video-aided Unsupervised Grammar Induction

TL;DR

This paper introduces a multi-modal grammar induction model that leverages rich video features to improve unsupervised constituency parsing, outperforming previous models on multiple benchmarks.

Contribution

It proposes the MMC-PCFG model that effectively integrates diverse video features for grammar induction, advancing beyond prior text-image based methods.

Findings

MMC-PCFG outperforms previous state-of-the-art systems

Leveraging video information improves grammar induction accuracy

Model trained end-to-end on multiple benchmarks

Abstract

We investigate video-aided grammar induction, which learns a constituency parser from both unlabeled text and its corresponding video. Existing methods of multi-modal grammar induction focus on learning syntactic grammars from text-image pairs, with promising results showing that the information from static images is useful in induction. However, videos provide even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. In this paper, we explore rich features (e.g. action, object, scene, audio, face, OCR and speech) from videos, taking the recent Compound PCFG model as the baseline. We further propose a Multi-Modal Compound PCFG model (MMC-PCFG) to effectively aggregate these rich features from different modalities. Our proposed MMC-PCFG is trained end-to-end and outperforms each individual modality and previous state-of-the-art systems on three benchmarks, i.e. DiDeMo, YouCook2 and MSRVTT, confirming the effectiveness of leveraging video information for unsupervised grammar induction.