Papers by Mahmoud Azab

6 papers
Towards Extracting Medical Family History from Natural Language Interactions: A New Dataset and Baselines (D19-1)

Copied to clipboard

Challenge: Using dialog agents, we can collect family history data from in-person consultations and crowdsource it to a genetic counselor.
Approach: They propose to use natural language interactions annotated with medical family histories to collect information from a genetic counselor and crowdsourcing.
Outcome: The proposed system averages 0.87 on complex sentences on the targeted relations.
Fighting FIRe with FIRE: Assessing the Validity of Text-to-Video Retrieval Benchmarks (2023.findings-eacl)

Copied to clipboard

Challenge: Existing benchmarks for text-to-video retrieval are incomplete, resulting in false negatives . a recent state-of-the-art model gains 25% recall points, but this is not the case for TVR.
Approach: They propose to retire video captioning datasets as TVR benchmarks . they propose to annotate and release additional caption-video pairs to mitigate this flaw .
Outcome: The proposed method fails to accurately reflect reality, despite lack of purpose-built benchmarks.
SIMMC-VR: A Task-oriented Multimodal Dialog Dataset with Situated and Immersive VR Streams (2023.acl-long)

Copied to clipboard

Challenge: Existing models lack a large-scale benchmark to capture user–assistant interactions . et al., 2022: 145-160.
Approach: They propose a video-grounded task-oriented dialog dataset that captures real-world AI-assisted user scenarios in VR.
Outcome: The proposed dataset captures real-world AI-assisted user scenarios in VR.
Speaker Naming in Movies (N18-1)

Copied to clipboard

Challenge: Identifying speakers and their names in movies is a primary task for many video analysis problems, such as automatic subtitle labeling.
Approach: They propose a model that leverages visual, textual, and acoustic modalities in an unified optimization framework for speaker naming in movies.
Outcome: The proposed model outperforms baseline models on the MovieQA 2017 challenge for speaker naming in movies and TV shows on visual, textual, and acoustic modalities.
Normalized Contrastive Learning for Text-Video Retrieval (2022.emnlp-main)

Copied to clipboard

Challenge: Cross-modal contrastive learning suffers from incorrect normalization of the sum retrieval probabilities of each text or video instance.
Approach: They propose a normalized contrastive learning algorithm that normalizes the sum retrieval probabilities of each instance so that every text and video instance is fairly represented.
Outcome: Empirical results show that NCL brings significant gains in text-video retrieval on different model architectures without any architecture engineering.
LifeQA: A Real-life Dataset for Video Question Answering (2020.lrec-1)

Copied to clipboard

Challenge: Existing video question answering datasets consist of movies and TV shows, but they are not representative of our day-to-day lives.
Approach: They propose a benchmark dataset for video question answering that focuses on day-to-day situations.
Outcome: The proposed dataset analyzes the challenging but realistic aspects of LifeQA . it consists of video clips and over 2.3k multiple-choice questions .

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