Grammar Induction from Visual, Speech and Text

• URL: http://arxiv.org/abs/2410.03739v1
• Date: Tue, 1 Oct 2024 02:24:18 GMT
• Title: Grammar Induction from Visual, Speech and Text
• Authors: Yu Zhao, Hao Fei, Shengqiong Wu, Meishan Zhang, Min Zhang, Tat-seng Chua,
• Abstract summary: This work introduces a novel visual-audio-text grammar induction task (textbfVAT-GI) Inspired by the fact that language grammar exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. We propose a visual-audio-text inside-outside autoencoder (textbfVaTiora) framework, which leverages rich modal-specific and complementary features for effective grammar parsing.
• Score: 91.98797120799227
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complementary roles to each other. With such intuition, this work introduces a novel \emph{unsupervised visual-audio-text grammar induction} task (named \textbf{VAT-GI}), to induce the constituent grammar trees from parallel images, text, and speech inputs. Inspired by the fact that language grammar natively exists beyond the texts, we argue that the text has not to be the predominant modality in grammar induction. Thus we further introduce a \emph{textless} setting of VAT-GI, wherein the task solely relies on visual and auditory inputs. To approach the task, we propose a visual-audio-text inside-outside recursive autoencoder (\textbf{VaTiora}) framework, which leverages rich modal-specific and complementary features for effective grammar parsing. Besides, a more challenging benchmark data is constructed to assess the generalization ability of VAT-GI system. Experiments on two benchmark datasets demonstrate that our proposed VaTiora system is more effective in incorporating the various multimodal signals, and also presents new state-of-the-art performance of VAT-GI.

Related papers

• Vision-Language Pre-Training for Boosting Scene Text Detectors [57.08046351495244]
  We specifically adapt vision-language joint learning for scene text detection. We propose to learn contextualized, joint representations through vision-language pre-training. The pre-trained model is able to produce more informative representations with richer semantics.
  arXiv  Detail & Related papers  (2022-04-29T03:53:54Z)
• Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting [69.77701325270047]
  This paper presents a weakly supervised pre-training method that can acquire effective scene text representations. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features. Experiments show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks.
  arXiv  Detail & Related papers  (2022-03-08T08:10:45Z)
• Dependency Induction Through the Lens of Visual Perception [81.91502968815746]
  We propose an unsupervised grammar induction model that leverages word concreteness and a structural vision-based to jointly learn constituency-structure and dependency-structure grammars. Our experiments show that the proposed extension outperforms the current state-of-the-art visually grounded models in constituency parsing even with a smaller grammar size.
  arXiv  Detail & Related papers  (2021-09-20T18:40:37Z)
• Video-aided Unsupervised Grammar Induction [108.53765268059425]
  We investigate video-aided grammar induction, which learns a constituency from both unlabeled text and its corresponding video. Video provides even richer information, including not only static objects but also actions and state changes useful for inducing verb phrases. We propose a Multi-Modal Compound PCFG model (MMC-PCFG) to effectively aggregate these rich features from different modalities.
  arXiv  Detail & Related papers  (2021-04-09T14:01:36Z)
• VLGrammar: Grounded Grammar Induction of Vision and Language [86.88273769411428]
  We study grounded grammar induction of vision and language in a joint learning framework. We present VLGrammar, a method that uses compound probabilistic context-free grammars (compound PCFGs) to induce the language grammar and the image grammar simultaneously.
  arXiv  Detail & Related papers  (2021-03-24T04:05:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.