Search Results for author: Alejandro Jaimes

Found 19 papers, 9 papers with code

A Novel Framework for Detecting Important Subevents from Crisis Events via Dynamic Semantic Graphs

no code implementations WNUT (ACL) 2021 Evangelia Spiliopoulou, Tanay Kumar Saha, Joel Tetreault, Alejandro Jaimes

Furthermore, we show that our approach significantly outperforms event detection baselines, highlighting the importance of aggregating information across tweets for our task.

Disaster Response Event Detection

Little Giants: Exploring the Potential of Small LLMs as Evaluation Metrics in Summarization in the Eval4NLP 2023 Shared Task

no code implementations1 Nov 2023 Neema Kotonya, Saran Krishnasamy, Joel Tetreault, Alejandro Jaimes

This paper describes and analyzes our participation in the 2023 Eval4NLP shared task, which focuses on assessing the effectiveness of prompt-based techniques to empower Large Language Models to handle the task of quality estimation, particularly in the context of evaluating machine translations and summaries.

One-Shot Learning

Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation

1 code implementation16 Oct 2023 Zijian Ding, Alison Smith-Renner, Wenjuan Zhang, Joel R. Tetreault, Alejandro Jaimes

To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e. g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation.

Headline Generation

Event Extraction as Question Generation and Answering

1 code implementation10 Jul 2023 Di Lu, Shihao Ran, Joel Tetreault, Alejandro Jaimes

In this paper, we propose QGA-EE, which enables a Question Generation (QG) model to generate questions that incorporate rich contextual information instead of using fixed templates.

Event Extraction Question Answering +2

A New Task and Dataset on Detecting Attacks on Human Rights Defenders

1 code implementation30 Jun 2023 Shihao Ran, Di Lu, Joel Tetreault, Aoife Cahill, Alejandro Jaimes

The ability to conduct retrospective analyses of attacks on human rights defenders over time and by location is important for humanitarian organizations to better understand historical or ongoing human rights violations and thus better manage the global impact of such events.

Humanitarian

BUMP: A Benchmark of Unfaithful Minimal Pairs for Meta-Evaluation of Faithfulness Metrics

1 code implementation20 Dec 2022 Liang Ma, Shuyang Cao, Robert L. Logan IV, Di Lu, Shihao Ran, Ke Zhang, Joel Tetreault, Alejandro Jaimes

The proliferation of automatic faithfulness metrics for summarization has produced a need for benchmarks to evaluate them.

GTN-ED: Event Detection Using Graph Transformer Networks

no code implementations NAACL (TextGraphs) 2021 Sanghamitra Dutta, Liang Ma, Tanay Kumar Saha, Di Lu, Joel Tetreault, Alejandro Jaimes

Recent works show that the graph structure of sentences, generated from dependency parsers, has potential for improving event detection.

Event Detection

Clustering of Social Media Messages for Humanitarian Aid Response during Crisis

1 code implementation23 Jul 2020 Swati Padhee, Tanay Kumar Saha, Joel Tetreault, Alejandro Jaimes

Social media has quickly grown into an essential tool for people to communicate and express their needs during crisis events.

Clustering Humanitarian +2

Multimodal Categorization of Crisis Events in Social Media

1 code implementation CVPR 2020 Mahdi Abavisani, Liwei Wu, Shengli Hu, Joel Tetreault, Alejandro Jaimes

Recent developments in image classification and natural language processing, coupled with the rapid growth in social media usage, have enabled fundamental advances in detecting breaking events around the world in real-time.

Event Detection Image Classification

Unsupervised Detection of Sub-events in Large Scale Disasters

no code implementations13 Dec 2019 Chidubem Arachie, Manas Gaur, Sam Anzaroot, William Groves, Ke Zhang, Alejandro Jaimes

Given the large amounts of posts, a major challenge is identifying the information that is useful and actionable.

To Click or Not To Click: Automatic Selection of Beautiful Thumbnails from Videos

2 code implementations6 Sep 2016 Yale Song, Miriam Redi, Jordi Vallmitjana, Alejandro Jaimes

Our system selects attractive thumbnails by analyzing various visual quality and aesthetic metrics of video frames, and performs a clustering analysis to determine the relevance to video content, thus making the resulting thumbnails more representative of the video.

Multimedia

TGIF: A New Dataset and Benchmark on Animated GIF Description

1 code implementation CVPR 2016 Yuncheng Li, Yale Song, Liangliang Cao, Joel Tetreault, Larry Goldberg, Alejandro Jaimes, Jiebo Luo

The motivation for this work is to develop a testbed for image sequence description systems, where the task is to generate natural language descriptions for animated GIFs or video clips.

Image Captioning Machine Translation +3

TVSum: Summarizing Web Videos Using Titles

no code implementations CVPR 2015 Yale Song, Jordi Vallmitjana, Amanda Stent, Alejandro Jaimes

We observe that a video title is often carefully chosen to be maximally descriptive of its main topic, and hence images related to the title can serve as a proxy for important visual concepts of the main topic.

Descriptive Image Retrieval +1

Video Co-Summarization: Video Summarization by Visual Co-Occurrence

no code implementations CVPR 2015 Wen-Sheng Chu, Yale Song, Alejandro Jaimes

We present video co-summarization, a novel perspective to video summarization that exploits visual co-occurrence across multiple videos.

Video Summarization

The Beauty of Capturing Faces: Rating the Quality of Digital Portraits

no code implementations28 Jan 2015 Miriam Redi, Nikhil Rasiwasia, Gaurav Aggarwal, Alejandro Jaimes

Digital portrait photographs are everywhere, and while the number of face pictures keeps growing, not much work has been done to on automatic portrait beauty assessment.

6 Seconds of Sound and Vision: Creativity in Micro-Videos

no code implementations CVPR 2014 Miriam Redi, Neil O Hare, Rossano Schifanella, Michele Trevisiol, Alejandro Jaimes

The notion of creativity, as opposed to related concepts such as beauty or interestingness, has not been studied from the perspective of automatic analysis of multimedia content.

Cannot find the paper you are looking for? You can Submit a new open access paper.