Papers by Dimitar Dimitrov

5 papers
MOMENTA: A Multimodal Framework for Detecting Harmful Memes and Their Targets (2021.findings-emnlp)

Copied to clipboard

Challenge: a growing number of harmful memes are being used for trolling, cyberbullying and abuse . a new approach to detect harmful meme images and texts is emerging .
Approach: They propose a multimodal deep neural network that detects harmful memes . they extend the recently released HarMeme dataset with additional memes and a new topic .
Outcome: The proposed framework outperforms rival methods in detecting harmful memes and their target social entities.
Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models (2024.naacl-long)

Copied to clipboard

Challenge: Pre-trained language models contain various kinds of knowledge.
Approach: They designed a probe that allows comparison of 34 million distinct paraphrases that follow a unified meta-template enabling the controlled variation of syntax and semantics across arbitrary relations.
Outcome: Extensive knowledge retrieval experiments show that prompts following clausal syntax have several desirable properties in comparison to appositive syntax.
Detecting Propaganda Techniques in Memes (2021.acl-long)

Copied to clipboard

Challenge: Propaganda can be defined as a form of communication that aims to influence opinions or the actions of people towards a specific goal.
Approach: They propose to detect the type of propaganda techniques used in memes by annotating them with 22 techniques.
Outcome: The proposed model identifies 22 propaganda techniques in memes, which can appear in text, image or both .
EXAMS-V: A Multi-Discipline Multilingual Multimodal Exam Benchmark for Evaluating Vision Language Models (2024.acl-long)

Copied to clipboard

Challenge: Existing benchmarks for vision language models are outdated and unable to accurately assess their performance.
Approach: They propose a multi-discipline multimodal multilingual exam benchmark for vision language models . they collect multiple-choice questions across 20 disciplines across 11 languages from 7 language families .
Outcome: The EXAMS-V exam includes 20,932 multiple-choice questions across 20 disciplines . the questions come in 11 languages from 7 language families and require advanced reasoning skills .
Detecting Harmful Memes and Their Targets (2021.findings-acl)

Copied to clipboard

Challenge: a growing body of research on meme analysis has focused on detecting harmful memes and their social entities . a meme is a form of content that is often harmless and designed to look funny . but its multimodal nature and camouflaged semantics make its analysis challenging .
Approach: They propose to use multimodal models to detect harmful memes and identify social entities that harmful meme targets.
Outcome: The proposed model can detect harmful memes and the social entities they target . the proposed model lacks the appropriate contexts and is poorly validated .

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