Papers by Bryan Plummer
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. |
Machine-Generated Text Localization (2024.findings-acl)
Copied to clipboard
| Challenge: | Prior work focused on identifying only part of a document as machine or human written . a key challenge is that short spans of text provide little information indicating if it is machine generated due to its short length . |
| Approach: | They propose a method that localizes the portions of a document that were machine generated. |
| Outcome: | The proposed method can detect changes in style or content to boost performance. |
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
Andrea Burns, Krishna Srinivasan, Joshua Ainslie, Geoff Brown, Bryan Plummer, Kate Saenko, Jianmo Ni, Mandy Guo
| 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. |
Show, Write, and Retrieve: Entity-aware Article Generation and Retrieval (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Prior work typically encodes all tokens in articles using pre-trained language models, however, many named entities are difficult to accurately recognize and predict by language models. |
| Approach: | They propose an ENtity-aware article GeneratIoN and rEtrieval framework to explicitly incorporate named entities into language models. |
| Outcome: | The proposed framework can boost article generation and retrieval performance, with a 4-5 perplexity improvement in article generation, and a 3-4% boost in recall@1 in article retrieval. |