Papers by Kate Saenko

6 papers
Detecting Cross-Modal Inconsistency to Defend Against Neural Fake News (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to defend against fake news are limited to text and metadata . authors identify weaknesses that adversaries can exploit by manipulating such technology .
Approach: They propose a more realistic defense mechanism to defend against machine-generated news . they use a NeuralNews dataset to identify weaknesses that adversaries can exploit .
Outcome: The proposed approach detects visual-semantic inconsistencies and provides a useful first line of defense against machine-generated disinformation.
Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation (P19-1)

Copied to clipboard

Challenge: Existing models that ground language into visual appearance and route structure are outperforming their visual counterparts in unseen new environments.
Approach: They propose to decompose the grounding procedure into a set of expert models with access to different modalities and ensemble them at prediction time.
Outcome: The proposed model outperforms models with only route structure and visual features on the benchmark Room-to-Room dataset.
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.
A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding (2023.emnlp-main)

Copied to clipboard

Challenge: Existing datasets for webpages contain only fragments of webpages . generative tasks like page description generation and section summarization are often left unstudied .
Approach: They introduce a Wikipedia Webpage suite that contains 2M pages with all associated image, text, and structure data.
Outcome: The proposed approach performs better than full attention with lower computational complexity.
Object Hallucination in Image Captioning (D18-1)

Copied to clipboard

Challenge: Existing image captioning metrics do not capture image relevance . current metrics only measure similarity to ground truth captions .
Approach: They propose a new image relevance metric to evaluate captioning models with veridical visual labels and assess their rate of object hallucination.
Outcome: The proposed metrics show that models with veridical visual labels have higher hallucination rates than models with lower hallucinosity.
Scaling Up Temporal Domain Generalization via Temporal Experts Averaging (2025.emnlp-main)

Copied to clipboard

Challenge: Temporal Domain Generalization (TDG) aims to generalize across temporal distribution shifts, e.g., lexical change over time.
Approach: They propose a framework that updates the entire model using weight averaging to maximize generalization potential while minimizing computational costs.
Outcome: The proposed framework outperforms previous methods by up to 69% while being up to 60x more efficient.

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