paper-with-me

Papers

Visually Grounded Concept Composition

2021-09-29 · Findings (EMNLP) 2021 11 · BoWen Zhang, Hexiang Hu, Linlu Qiu, Peter Shaw, Fei Sha

We investigate ways to compose complex concepts in texts from primitive ones while grounding them in images. We propose Concept and Relation Graph (CRG), which builds on top of constituency analysis and consists of recursively combined concepts with predicate functions. Meanwhile, we propose a concept composition neural network called Composer to leverage the CRG for visually grounded concept learning. Specifically, we learn the grounding of both primitive and all composed concepts by aligning them to images and show that learning to compose leads to more robust grounding results, measured in text-to-image matching accuracy. Notably, our model can model grounded concepts forming at both the finer-grained sentence level and the coarser-grained intermediate level (or word-level). Composer leads to pronounced improvement in matching accuracy when the evaluation data has significant compound divergence from the training data.

📄 PDF Abstract BibTeX arXiv:2109.14115

Code (0)

등록된 구현이 없습니다.

Tasks

Sentence

Similar Papers 제목 키워드 기반

MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition

2023-11-02 · Guangyue Xu, Parisa Kordjamshidi, Joyce Chai

Humans have the ability to learn novel compositional concepts by recalling and generalizing primitive concepts acquired from past experiences. Inspired by this observation, in this paper, we propose MetaReVision, a retri…

Meta-LearningRetrieval

COVR: A test-bed for Visually Grounded Compositional Generalization with real images

2021-09-22 · EMNLP 2021 11 · Ben Bogin, Shivanshu Gupta, Matt Gardner, Jonathan Berant

While interest in models that generalize at test time to new compositions has risen in recent years, benchmarks in the visually-grounded domain have thus far been restricted to synthetic images. In this work, we propose …

A Meta-transfer Learning framework for Visually Grounded Compositional Concept Learning

2022-01-16 · ACL ARR January 2022 1 · Anonymous

Humans acquire language in a compositional and grounded manner.They can describe their perceptual world using novel compositions from already learnt elementary concepts. However, recent research shows that modern neural …

Meta-LearningTransfer Learning

Generative Models of Visually Grounded Imagination

2017-05-30 · ICLR 2018 1 · Ramakrishna Vedantam, Ian Fischer, Jonathan Huang, Kevin Murphy

It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In …

Attribute

Visually Grounded Continual Learning of Compositional Phrases

2020-05-02 · EMNLP 2020 11 · Xisen Jin, Junyi Du, Arka Sadhu, Ram Nevatia 외

Humans acquire language continually with much more limited access to data samples at a time, as compared to contemporary NLP systems. To study this human-like language acquisition ability, we present VisCOLL, a visually …

Continual LearningGrounded language learningLanguage AcquisitionLanguage Modelling