Challenge: Existing models rely on UI metadata, which is often missing or not accessible.
Approach: They propose a vision and language model that can learn generic visio-linguistic representations of UIs . they use a dataset to train Lexi, which is based on UI metadata .
Outcome: The proposed model can handle unique features of UI screens, including text richness and context sensitivity.

Similar Papers

Tell Me What’s Next: Textual Foresight for Generic UI Representations (2024.findings-acl)

Copied to clipboard

Challenge: Prior work has learned strong visual representations with local or global captioning losses, but fails to retain both granularities.
Approach: They propose a pretraining objective for learning UI screen representations using captioning.
Outcome: The proposed approach outperforms state-of-the-art on generation tasks with 28x fewer images.
Learning to Represent Image and Text with Denotation Graph (2020.emnlp-main)

Copied to clipboard

Challenge: Recent advances in learning representations of visual and language information have been a problem with many applications.
Approach: They propose to extract visual expressions from images aligned with linguistic expressions that describe the images to learn representations from implicit expressions.
Outcome: The proposed representations lead to stronger empirical results on downstream tasks of cross-modal image retrieval, referring expression, and compositional attribute-object recognition.
Mapping Natural Language Instructions to Mobile UI Action Sequences (2020.acl-main)

Copied to clipboard

Challenge: a new problem of grounding natural language instructions to mobile UI actions is emerging . we use a Transformer to extract action phrase tuples from long-range natural language instruction .
Approach: They propose a dataset that pairs English instructions with actions performed by people on a mobile UI emulator.
Outcome: The proposed model achieves 70.59% accuracy on predicting complete ground-truth action sequences in PixelHelp.
Towards Better Semantic Understanding of Mobile Interfaces (2022.coling-1)

Copied to clipboard

Challenge: a dataset of 500k unique annotations is released to improve mobile accessibility and automation capabilities.
Approach: They propose to use an annotation dataset to improve the accessibility of mobile UIs . they use images and view hierarchies to augment annotations for icons and their semantics - and use multimodal inputs to build models.
Outcome: The proposed dataset shows that it can be used to improve UIs and categories on unseen apps.
Graph Pre-training for AMR Parsing and Generation (2022.acl-long)

Copied to clipboard

Challenge: Abstract meaning representation (AMR) highlights the core semantic information of text in a graph structure.
Approach: They propose two graph auto-encoding strategies for graph-to-graph pre-training and four tasks to integrate text and graph information during pre-tuning to improve structure awareness.
Outcome: The proposed model is superior to pre-trained language models on AMR parsing and AMR-to-text generation tasks.
From Perception to Reasoning: Enhancing Vision-Language Models for Mobile UI Understanding (2025.findings-acl)

Copied to clipboard

Challenge: Accurately grounding visual and textual elements within mobile user interfaces remains a challenge for Vision-Language Models (VLMs).
Approach: They propose a mobile UI understanding model trained on a dataset specifically tailored for mobile screen understanding and grounding.
Outcome: The proposed model achieves significant gains in accuracy across all perception tasks and on reasoning benchmarks.
Are Visual-Linguistic Models Commonsense Knowledge Bases? (2022.coling-1)

Copied to clipboard

Challenge: PTLMs are used to extract knowledge from text on demand.
Approach: They compare visual-linguistic and language-only visual-language models in a zero-shot commonsense question answering inference task.
Outcome: The proposed models are highly promising on certain types of commonsense knowledge associated with the visual world.
Recent Advances in Pre-trained Language Models: Why Do They Work and How Do They Work (2022.aacl-tutorials)

Copied to clipboard

Challenge: Pre-trained language models are language models that are pre-taught on large-scaled corpora in a self-supervised fashion.
Approach: This tutorial provides a broad and comprehensive introduction to pre-trained language models . it focuses on emerging methods that enable PLMs to perform diverse downstream tasks .
Outcome: This tutorial focuses on the benefits of pre-trained language models and how to use them in NLP tasks.
lingvis.io - A Linguistic Visual Analytics Framework (P19-3)

Copied to clipboard

Challenge: Using a modular framework, linguistic visual analytics applications can be rapidly prototypized using a web-based framework.
Approach: They propose a modular framework for rapid prototyping of linguistic, web-based, visual analytics applications.
Outcome: The proposed framework supports rapid prototyping of linguistic, web-based, visual analytics applications.
Pixology: Probing the Linguistic and Visual Capabilities of Pixel-based Language Models (2024.emnlp-main)

Copied to clipboard

Challenge: PIXEL is a vision transformer that has been pre-trained on rendered text . however, it is not able to outperform monolingual subwords like BERT .
Approach: They propose to use PIXEL as a vision transformer to train on rendered text to explore the gap between its visual and linguistic understanding.
Outcome: The proposed model outperforms monolingual subword models in most other contexts, but it lacks the linguistic knowledge to perform in language tasks.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations