The Machine INtelligence Development (MIND) Lab at the American University of Beirut (AUB) aims at providing state of the art solutions in the field of Artificial Intelligence with a focus on machine learning theory and applications. The lab has recently established a new identity, grew in size, and saw great progress in cutting-edge research in two main domains: Natural Language Processing and Context-Aware Sensing.
As we begin a new year, we are extremely proud of the diligence and perseverance that our lab has shown despite the challenges that oversaw the world and Lebanon the past year. Our students were able to push cutting-edge research, produce publications, compete in local and global challenges, and share their expertise with the world through open-source solutions and invited talks.
2020 Research Manifesto
Natural Language Processing (NLP)
Our NLP focused team has explored a wide range of challenges, from conversational systems and Arabic as a low-resource language to studying human reading comprehension.
Gilbert Badaro, our lab’s newest Ph.D. graduate, has investigated multiple link prediction approaches and different natural language processing variations in order to try to link a large lexical Arabic Resource, SAMA, to English WordNet. In his work, he used a machine learning approach and developed training data using existing small-scale Arabic WordNet. His latest article is important because it provides publicly a large-scale sentiment lexical resource for Arabic, ArSenL 2.0, to enable more accurate sentiment mining models. It also presents a benchmark dataset to be used by other researchers in the field interested in automatically evaluating approaches for Arabic WordNet expansion.
Obeida ElJundi has focused on exploring human reading comprehension. Reading comprehension is not the result of one single process as was thought before the 1970s. Rather, psychologists realized that a combination of several complex cognitive processes is involved. Traditional NLP algorithms used nowadays (e.g., RNN) cover some aspects of the reading comprehension cognitive processes, such as attention and forgetting, but render other aspects unaccounted for. Obeida has been looking into studying how the human brain reads and comprehends written text will help reveal what is missing and improve the overall performance of NLP.
Wissam Antoun has recently defended his thesis on Arabic Transformers for NLU and chatbots. This year, he trained the first Arabic BERT model, AraBERT, alongside his colleague, Fady Baly. Wissam is now planning to explore newer and better models for language understanding and generation, and he is off to a great start! Wissam and Fady have started 2021 by releasing 10 new Arabic Transformer Models (AraGPT2, AraELECTRA & AraBERTv2) on AUB Mind Lab and Hugging Face Github repositories.
Nataly Dalal has worked on designing lifelong learning for chatbots in customer support, thus allowing them to continuously learn and accumulate knowledge on their own from support forums posted on the web. Lifelong learning aims at producing chatbots that are more accurate, robust, and human-like.
Christian Hokayem has focused the bulk of his research on conversational automated negotiation agents. With the goal of improving user experience in an automated sales setting, he investigated what empathy is and tried to find a way to incorporate it into agents’ language generation and decision-making models. In his work, he formulated the problem as a multi-objective reinforcement learning problem and taught the bot to maximize user experience (represented by sentiment) and sales price.
Tarek Naous, our newest master’s student, has started with research focused on enabling empathetic behavior in conversational agents for the Arabic Language with the global aim of making human-machine interactions more similar to human-human interactions. In 2020, he was able to release a dataset of empathetic conversations in Arabic and propose a neural-based model for generating empathetic responses. His work was published in WANLP 2020 and is currently in progress for further development, where the challenge is improving performance given the limited dataset size we have.
Context-Aware Sensing
With a focus on overcoming the challenge of learning from limited labeled data, our work in context-aware sensing has been versatile, ranging from applications of healthcare, such as traumatic brain injuries and epilepsy prediction, to power load forecasting and human activity recognition.
Reem Mahmoud’s research interest is in personalized Machine Learning, which branches into problems of learning with little labeled data and advancing traditional transfer learning methods. This past year, she has looked into overcoming challenges of catastrophic forgetting in pre-trained neural networks on time-series applications, such as human activity recognition. Her work looked into improving performance on target tasks with limited training data while preserving performance on source tasks from the pre-trained model. This work, titled “Multi-Objective Learning to Overcome Catastrophic Forgetting in Time-series Applications,” has been recently submitted to the journal of ACM Transactions on Knowledge Discovery from Data.
Marc Djandji has focused his research for the past year on improving the performance of deep learning models when trained with limited labeled training examples. He has specifically investigated the problem under the application of short-term load forecasting. His work looks into scalable multi-task learning methods.
This year, Alaa Khaddaj had completed an internship at Signal Kinetics (MIT Media Lab) under the supervision of Prof. Fadel Adib, where they developed an apparatus that can detect contaminated food or counterfeit products. The system used a generative model (variational autoencoder) to generalize to new unseen environments and a transfer learning scheme to learn from multiple experiments simultaneously. Alaa’s other line of research was to develop a domain adaptation model that can generalize a classifier between two similar domains that have some differences. For his final year project, his team developed an intelligent question-answering system for customer support. This work has been submitted as a journal paper.
Mosbah Aouad has worked on developing deep learning models for short-term load forecasting for residential houses, where the challenge is to deal with the high non-linearities present in the load data. To build a sensitive model to varying load patterns and large peaks in the data, he designed an attention mechanism to augment a sequence-to-sequence network to capture these variations. On the other side, his thesis work has focused on biomedical image analysis with the aim of predicting the survival rate of penetrating traumatic brain injury (pTBI) patients from brain CT scans analysis. He is designing a representation learning approach that captures relevant features reflecting the severity of pTBIs from CT scan analysis directly.
Open-source Solutions, Competitions & Other Activities
Beyond the efforts in research, we are proud of the efforts our team has put into sharing and pushing their expertise through participating in competitions, open-sourcing solutions, and delivering talks.
Here are some of our highlights from 2020:
-
- We launched our AUB MIND Lab’s Github Repository and a brand new website for the group.
- Amir Hussein, Rim Achour, and Fady Baly ranked 1st place at QICC Cybersecurity contest in Fake News Detection task.
- Alaa Khaddaj won Best Paper Award at IEEE ICIoT 2020.
- Obeida ElJundi and his work on hULMonA were featured in WIRED Middle East
- AraBERT by our alumnus, Wissam Antoun, and Fady Baly has been featured in MIT Technology Review Arabia
- Marc Djandji, Fady Baly, and Wissam Antoun ranked 2nd Place at 4th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT 4) in Hate and Offensive speech detection tasks – Marseille, France 2020
- Wissam Antoun invited by IWAN Research Group at King Saud University to deliver a talk titled “AraBERT: Pretraining, fine-tuning, applications and demo (In Arabic),” September 2020.
- Wissam Antoun invited by PyData Khobar Meetup to deliver a talk titled “AraBERT: Pretraining, use cases and future improvements,” May 2020.
2020 Graduates
-
- Dalia Jaber – M.E. in Electrical & Computer Engineering
- Wissam Antoun – M.E. in Electrical & Computer Engineering
- Amir Hussein – M.E. in Electrical & Computer Engineering
- Alaa Khaddaj – B.E. in Electrical & Computer Engineering
- Gilbert Badaro – Ph.D. in Electrical & Computer Engineering
- Raslan Kain – M.E. in Electrical & Computer Engineering
2020 List of Publications
Journal Papers
-
- R. Mahmoud, H. Hajj, F. Karameh, “A Systematic Approach to Multi-Task Learning from Time-series Data” Elsevier Applied Soft Computing, Vol. 96 (2020), 106586.
- G. Badaro, H. Hajj, N. Habash, “A Link Prediction Approach for Accurately Mapping a Large-Scale Arabic Lexical Resource to English WordNet,” ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 19, no. 6 (2020): 1-38.
- N. Abbas, S. Sharafeddine, H. Hajj, and Z. Dawy, “Price-Aware Traffic Splitting in D2D HetNets with Cost-Energy-QoE Tradeoffs,” Computer Networks, vol. 172, p. 107169, 2020.
- A. Hussein, M. Djandji, R. Mahmoud, M. Dhabi, H. Hajj, “Augmenting Deep Learning with Adversarial Training for Robust Prediction of Epilepsy Seizures” ACM Transactions on Computing for Healthcare, June 2020, Article 18.
- S. Taleb, A. Yeretzian, R. A. Jabr, and H. Hajj. “Optimization of building form to reduce incident solar radiation.” Journal of Building Engineering 28 (2020): 101025.
Conference Papers
-
- W. Antoun, F. Baly, H. Hajj, “AraBERT: Transformer-based Model for Arabic Language Understanding.” In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pp. 9-15. 2020.
- T. Naous, C. Hokayem, H. Hajj, “Empathy-driven Arabic Conversational Chatbot,” Proceedings of the Fifth Arabic Natural Language Processing Workshop, December 2020, Barcelona, Spain (Online), pp 5-68.
- S. Taleb, A. Yeretzian, R. Jabr, H. Hajj, “Energy Optimization of Climate Adapted Buildings in an Urban Context: The Case of Subtropical Climate”, 35th PLEA Conference: Planning Post Carbon Cities, 1-3 September 2020 A Coruña, Spain.
- M. Djandji, F. Baly, W. Antoun, H. Hajj. “Multi-Task Learning using AraBert for Offensive Language Detection.” In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pp. 97-101. 2020.
- O. ElJundi, M. Dhaybi, K. Mokadam, H. Hajj, and D. Asmar, “Resources and End-to-End Neural Network Models for Arabic Image Captioning,” In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications – Volume 5: VISAPP, 233-241, 2020, Valletta, Malta.
- A. Khaddaj, H. Hajj, “Representation Learning for Adversarial Domain Adaptation in Text Classification,” In Proceedings of the IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT’20), Qatar, Feb 2-5, 2020. [Winner of best paper award]
- A. Maarouf, N. El Droubi, R. Morcel, H. Hajj, M. Saghir, and H. Akkary. “Optimized Distribution of an Accelerated Convolutional Neural Network across Multiple FPGAs.” In 2020 IEEE 28th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), pp. 235-235. IEEE, 2020.
- W. Antoun, F. Baly, R. Achour, A. Hussein, H. Hajj, “State of the Art Models for Fake News Detection Tasks,” In Proceedings of the IEEE International Conference on Informatics, IoT, and Enabling Technologies (ICIoT’20), Qatar, Feb 2-5, 2020.
To discover our lab and potential opportunities, visit our site or stay up to date with our news on LinkedIn and Twitter.
Great job for publishing such a beneficial web site. Your web log isn’t only useful but it is additionally really creative too. daftar exototo
Thanks for sharing nice information with us. i like your post and all you share with us is uptodate and quite informative, i would like to bookmark the page so i can come here again to read you, as you have done a wonderful job. alexistogel
Hi there, I found your blog via Google while searching for such kinda informative post and your post looks very interesting for me. Guest post
I was surfing the Internet for information and came across your blog. I am impressed by the information you have on this blog. It shows how well you understand this subject. alexistogel
I have read a few of the articles on your website now, and I really like your style. 토토사이트 추천
Thanks for publishing such a unique and great article. 안전한카지노 사이트
Really nice and interesting post. I was looking for this kind of information and enjoyed reading this one. Zonnepanelen installateurs
First You got a great blog .I will be interested in more similar topics. i see you got really very useful topics, i will be always checking your blog thanks. Airconditioning installateur
Thanks for sharing this information. I really like your blog post very much. You have really shared a informative and interesting blog post . Isolatie spouwmuur
The next time I read a blog, I hope that it doesnt disappoint me as much as this one. I mean, I know it was my choice to read, but I actually thought you have something interesting to say. All I hear is a bunch of whining about something that you could fix if you werent too busy looking for attention. Zwembadbouw
The web site is lovingly serviced and saved as much as date. So it should be, thanks for sharing this with us. Zonnepanelen plat dak
Easily, the article is actually the best topic on this registry related issue. I fit in with your conclusions and will eagerly look forward to your next updates. Buitenzwembaden
I finally found great post here.I will get back here. I just added your blog to my bookmark sites. thanks.Quality posts is the crucial to invite the visitors to visit the web page, that’s what this web page is providing. Prijs zonnepanelen
Great post I would like to thank you for the efforts you have made in writing this interesting and knowledgeable article. Aanleg zwembaden
Thank you for your post, I look for such article along time, today i find it finally. this post give me lots of advise it is very useful for me. Zonnepaneel installatie
It’s late finding this act. At least, it’s a thing to be familiar with that there are such events exist. I agree with your Blog and I will be back to inspect it more in the future so please keep up your act. Zonnepanelen plaatsen
This is such a great resource that you are providing and you give it away for free. Prijzen zonnepanelen
Took me time to read all the comments, but I really enjoyed the article. It proved to be Very helpful to me and I am sure to all the commenters here! It’s always nice when you can not only be informed, but also entertained! Isoleren spouwmuur
I liked your article and I hope you will have many entries or more Zonnepanelen prijs
it was a wonderful chance to visit this kind of site and I am happy to know. thank you so much for giving us a chance to have this opportunity.. Huawei batterij
I wanted to leave a little comment to support you and wish you a good continuation. Wishing you the best of luck for all your blogging efforts. Zonnepanelen laten plaatsen
Ultimately, a problem that I’m passionate about. I have looked for data of this caliber for the previous various hours. Your site is greatly appreciated. alexistogel
Thanks for sharing nice information with us. i like your post and all you share with us is uptodate and quite informative, i would like to bookmark the page so i can come here again to read you, as you have done a wonderful job. hoki108
I really appreciate the kind of topics you post here. Thanks for sharing us a great information that is actually helpful. Good day! alexistogel
I really appreciate the kind of topics you post here. Thanks for sharing us a great information that is actually helpful. Good day! alexistogel
I recently came across your blog and have been reading along. I thought I would leave my first comment. I don’t know what to say except that I have enjoyed reading. Nice blog. I will keep visiting this blog very often. alexistogel login
Thanks for a very interesting blog. What else may I get that kind of info written in such a perfect approach? I’ve a undertaking that I am simply now operating on, and I have been at the look out for such info. PAUSHOKI
ytmp3 is a web-based service that converts YouTube videos into MP3 audio files. It requires no software downloads or installations.
I think about it is most required for making more on this get engaged alexistogel
Hello there, just became alert to your weblog thru Google,
and located that it’s truly informative. casinositesafe.com
Its a great pleasure reading your post.Its full of information I am looking for and I love to post a comment that “The content of your post is awesome” Great work. hoki108
This is very educational content and written well for a change. It’s nice to see that some people still understand how to write a quality post! https://www.roswellrent.com/
All the contents you mentioned in post is too good and can be very useful. I will keep it in mind, thanks for sharing the information keep updating, looking forward for more posts.Thanks RajaAkurat
I have read all the comments and suggestions posted by the visitors for this article are very fine,We will wait for your next article so only.Thanks! alexistogel
I really appreciate this wonderful post that you have provided for us. I assure this would be beneficial for most of the people. mutu 777
This is a great post. I like this topic.This site has lots of advantage.I found many interesting things from this site. It helps me in many ways.Thanks for posting this again. Mutu 777
I really loved reading your blog. It was very well authored and easy to undertand. Unlike additional blogs I have read which are really not tht good. I also found your posts very interesting. In fact after reading, I had to go show it to my friend and he ejoyed it as well! zola777
I was surfing net and fortunately came across this site and found very interesting stuff here. Its really fun to read. I enjoyed a lot. Thanks for sharing this wonderful information. zola777 login
You might comment on the order system of the blog. You should chat it’s splendid. Your blog audit would swell up your visitors. I was very pleased to find this site.I wanted to thank you for this great read!! Zonnepanelen Antwerpen
Really nice and interesting post. I was looking for this kind of information and enjoyed reading this one. Keep posting. Thanks for sharing. Spouwmuurisolatie
This is a great inspiring article.I am pretty much pleased with your good work.You put really very helpful information… Crepi gevelbekleding
I am looking for and I love to post a comment that “The content of your post is awesome” Great work! Lucht lucht warmtepomp
Really impressed! Everything is very open and very clear clarification of issues. It contains truly facts. Your website is very valuable. Thanks for sharing. Lucht water warmtepomp
Really nice and interesting post. I was looking for this kind of information and enjoyed reading this one. Warmtepompboiler
First You got a great blog .I will be interested in more similar topics. i see you got really very useful topics, i will be always checking your blog thanks. Crepi facade
I am happy to find this post Very useful for me, as it contains lot of information. I Always prefer to read The Quality and glad I found this thing in you post. Thanks MPOSPORT
I really enjoyed reading this post, big fan. Keep up the good work andplease tell me when can you publish more articles or where can I read more on the subject? Spouwmuur isoleren
I found your this post while searching for some related information on blog search…Its a good post..keep posting and update the information. MPOSPORT
I curious more interest in some of them hope you will give more information on this topics in your next articles. Gevelrenovatie
Welcome to the party of my life here you will learn everything about me. Premies gevelisolatie