Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations

• URL: http://arxiv.org/abs/2401.14212v3
• Date: Mon, 02 Dec 2024 10:30:50 GMT
• Title: Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations
• Authors: Wolf Nuyts, Ruben Cartuyvels, Marie-Francine Moens,
• Abstract summary: We show that we can predict 2D spatial layouts from language representations that implicitly or explicitly encode sentence syntax.<n>We propose a novel structural loss function that better enforces the syntactic structure of the input sentence.<n>The loss has the potential to be used in other generation tasks where a tree-like structure underlies the conditioning modality.
• Score: 21.636786771793364
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recognizing visual entities in a natural language sentence and arranging them in a 2D spatial layout require a compositional understanding of language and space. This task of layout prediction is valuable in text-to-image synthesis as it allows localized and controlled in-painting of the image. In this comparative study it is shown that we can predict layouts from language representations that implicitly or explicitly encode sentence syntax, if the sentences mention similar entity-relationships to the ones seen during training. To test compositional understanding, we collect a test set of grammatically correct sentences and layouts describing compositions of entities and relations that unlikely have been seen during training. Performance on this test set substantially drops, showing that current models rely on correlations in the training data and have difficulties in understanding the structure of the input sentences. We propose a novel structural loss function that better enforces the syntactic structure of the input sentence and show large performance gains in the task of 2D spatial layout prediction conditioned on text. The loss has the potential to be used in other generation tasks where a tree-like structure underlies the conditioning modality. Code, trained models and the USCOCO evaluation set are available via github.

Related papers

• Let's Predict Sentence by Sentence [31.702157701240967]
  We present a framework that adapts a pretrained token-level LM to operate in sentence space by autoregressively predicting continuous embeddings of next sentences.<n>Our results indicate that pretrained LMs can effectively transition to abstract, structured reasoning within latent embedding spaces.
  arXiv  Detail & Related papers  (2025-05-28T10:28:35Z)
• ComAlign: Compositional Alignment in Vision-Language Models [2.3250871476216814]
  We introduce Compositional Alignment (ComAlign) to discover more exact correspondence of text and image components. Our methodology emphasizes that the compositional structure extracted from the text modality must also be retained in the image modality. We train a lightweight network lying on top of existing visual and language encoders using a small dataset.
  arXiv  Detail & Related papers  (2024-09-12T16:46:41Z)
• Towards a theory of how the structure of language is acquired by deep neural networks [6.363756171493383]
  We use a tree-like generative model that captures many of the hierarchical structures found in natural languages. We show that token-token correlations can be used to build a representation of the grammar's hidden variables. We conjecture that the relationship between training set size and effective range of correlations holds beyond our synthetic datasets.
  arXiv  Detail & Related papers  (2024-05-28T17:01:22Z)
• A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions [50.469491454128246]
  We use text as the guidance to create graphic layouts, i.e., Text-to-labeled, aiming to lower the design barriers. Text-to-labeled is a challenging task, because it needs to consider the implicit, combined, and incomplete constraints from text. We present a two-stage approach, named parse-then-place, to address this problem.
  arXiv  Detail & Related papers  (2023-08-24T10:37:00Z)
• COSA: Concatenated Sample Pretrained Vision-Language Foundation Model [78.32081709802873]
  Most vision-language foundation models employ image-text datasets for pretraining. We propose COSA, a COncatenated SAmple pretrained vision-language foundation model. We achieve this by sequentially concatenating multiple image-text pairs as inputs for pretraining. This transformation effectively converts existing image-text corpora into a pseudo long-form video-paragraph corpus.
  arXiv  Detail & Related papers  (2023-06-15T12:29:42Z)
• Example-Based Machine Translation from Text to a Hierarchical Representation of Sign Language [1.3999481573773074]
  This article presents an original method for Text-to-Sign Translation. It compensates data scarcity using a domain-specific parallel corpus of alignments between text and hierarchical formal descriptions of Sign Language videos in AZee. Based on the detection of similarities present in the source text, the proposed algorithm exploits matches and substitutions of aligned segments to build multiple candidate translations. The resulting translations are in the form of AZee expressions, designed to be used as input to avatar systems.
  arXiv  Detail & Related papers  (2022-05-06T15:48:43Z)
• Integrating Visuospatial, Linguistic and Commonsense Structure into Story Visualization [81.26077816854449]
  We first explore the use of constituency parse trees for encoding structured input. Second, we augment the structured input with commonsense information and study the impact of this external knowledge on the generation of visual story. Third, we incorporate visual structure via bounding boxes and dense captioning to provide feedback about the characters/objects in generated images.
  arXiv  Detail & Related papers  (2021-10-21T00:16:02Z)
• Syntax-Enhanced Pre-trained Model [49.1659635460369]
  We study the problem of leveraging the syntactic structure of text to enhance pre-trained models such as BERT and RoBERTa. Existing methods utilize syntax of text either in the pre-training stage or in the fine-tuning stage, so that they suffer from discrepancy between the two stages. We present a model that utilizes the syntax of text in both pre-training and fine-tuning stages.
  arXiv  Detail & Related papers  (2020-12-28T06:48:04Z)
• Visually Grounded Compound PCFGs [65.04669567781634]
  Exploiting visual groundings for language understanding has recently been drawing much attention. We study visually grounded grammar induction and learn a constituency from both unlabeled text and its visual captions.
  arXiv  Detail & Related papers  (2020-09-25T19:07:00Z)
• Structure-Augmented Text Representation Learning for Efficient Knowledge Graph Completion [53.31911669146451]
  Human-curated knowledge graphs provide critical supportive information to various natural language processing tasks. These graphs are usually incomplete, urging auto-completion of them. graph embedding approaches, e.g., TransE, learn structured knowledge via representing graph elements into dense embeddings. textual encoding approaches, e.g., KG-BERT, resort to graph triple's text and triple-level contextualized representations.
  arXiv  Detail & Related papers  (2020-04-30T13:50:34Z)

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.