Language and Learning
Elastic Search & Kibana Hands on workshop
Building 504, room 5Computer Aided Text Analysis סדנא יישומית ל ניתוח ממוחשב של טקסט יועבר ע"י ד"ר יהונתן שלר :מומלץ לצפות בסרטון הבא לפני הסדנא מכון מדע הנתונים: הדגמת שימוש בכלי ניתוח "ידודותיים" - ניתוח ממוחשב של טקסט, ד"ר יהונתן שלר DSI - Text Analysis - Elastic2 :קישור למצגת :dashboardקישור ל http://dsi.biu.ac.il/kibana-tutorial-13-3-18 עבודה בסדנאות תעשה ... Read more
High-Order Attention Models for Visual Question Answering (Idan Schwartz, DSI Learning Club)
Gonda Building (901), Room 101Apr 26th, Thu 10:00 , Idan Schwartz (webpage). Technion – Israel Institute of Technology (PhD Student). Location: Gonda Building (901), Room 101. High-Order Attention Models for Visual Question Answering Abstract: The quest for algorithms that enable cognitive abilities is an important part of machine learning. A common trait in many recently investigated cognitive-like tasks is ... Read more
Talking to your Virtual Assistant about anything by Jonathan Berant (DSI Learning Club)
Gonda Building 901, Room 101On Thursday, May 3rd, we are hosting Jonathan Berant from TAU. Title: Talking to your Virtual Assistant about anything When: May 3rd, Thu 10:15. Light refreshments at 10:00. Where: Gonda Building 901, Room 101 Abstract: Conversational interfaces and virtual assistants are now part of our lives due to services such as Amazon Alexa, Google Voice, Microsoft Cortana, etc. Thus, translating natural language queries and commands ... Read more
DIY Classification & Dear Data Scientist, Label Data or Die (News, Economics and AI meetup)
Thomson-Reuters offices Park Ofer, 94 Derech Em Hamoshavot Oren Building (Building 6), entrance level floor · Petakh Tiqwa Park Ofer, 94 Derech Em Hamoshavot, Petakh Tiqwa, IsraelA News, Economics and AI meetup 18:00-18:30 gathering + pizza 18:30-19:00 "DIY Classification" by Ehud Azikri and Lior Weintraub 19:00-20:15 "Dear Data Scientist, Label Data or Die" by Tal Perry see meetup page for full details: http://meetu.ps/e/Fhrpb/1b3Yc/f
On the Expressive Power of ConvNets and RNNs as a Function of their Architecture by Or Sharir (DSI Learning Club)
Gonda Building (901), Room 101.May 31st, Thu 10:00 , Or Sharir (webpage). The Hebrew University of Jerusalem (PhD Student) Location: Gonda Building (901), Room 101. On the Expressive Power of ConvNets and RNNs as a Function of their Architecture Abstract: The driving force behind convolutional and recurrent networks — two of the most successful deep learning architectures to date ... Read more
Learning to Act from Observational Data: Machine Learning and Causal Inference in Healthcare by Uri Shalit (Technion) – DSI Learning Club
Gonda Building (901), Room 101.June 7th, Thu 10:00 , Uri Shalit (webpage). Technion – Israel Institute of Technology (Faculty). Location: Gonda Building (901), Room 101. Learning to Act from Observational Data: Machine Learning and Causal Inference in Healthcare Abstract: The proliferation of data collection in the health, commercial, and economic spheres, brings with it opportunities for extracting new knowledge ... Read more
“The missing elements in NLP” by Prof. Yoav Goldberg from Bar-Ilan (Amazon Research Day, Haifa)
Sammy Ofer Stadium, Haifa Pinkhas ve-Avraham Rutenberg St 2, Haifa, IsraelDetails & Registration: https://ard.amazon-ml.com/haifa/ PAssword: HaifaARD
News, Economics and AI meetup — Latest Research by the Bar-Ilan NLP Lab. (slides available)
Gonda Building (901), Room 101.Details This meeting will feature the BIU NLP Lab. Lab leaders Ido Dagan and Yoav Goldberg will tell us about current developments in their work. Some more bits of recent research will be introduced by Lab's senior grad students. Agenda: 18:00-18:20: gathering + pizzas 18:20-18:50: Prof. Ido Dagan: Extracting and Exploring Open Textual Knowledge (slides) 18:50-19:00: ... Read more
“Automated text classification and its applications for detecting truths and lies” by Dr. Jonathan Schler
901 (brain center), room 102Invited talk, as part of "Language of lies: recent advances in research and future prospects" Workshop
Djame Seddah – Analysis of “noisy” textual social media data in Hebrew and French
Building 408, room #8תשתיות לניתוח טקסטים רועשים (נגיד מטוויטר) בעברית ובצרפתית
GPT-3 and its Few-shot Learning Capabilities – Talk by Prof. Yoav Goldberg
zoomTitle: GPT-3 and its Few-shot Learning Capabilities Abstract: A recent paper by OpenAI, "Language Models are Few-Shot Learners", introduced GPT-3, a huge pre-trained language model, and a claim that it acts as a very effective few-shot learner. While I was skeptic at first, I got access to the GPT-3 model, and after playing with it ... Read more
Diffusion Models Beat GANs? – Eliya Nachmani (TAU & FAIR)
Recording: https://us02web.zoom.us/rec/share/AJjsXIl29nyD0ZSbadWHFd54QJFAB8sfV0b1WdcSY-kMvJE68rmdk595OO_yCUoK.f4P_M3-T4nfR5h91 Eliya Nachmani from TAU & FAIR. Title: Diffusion Models Beat GANs? Abstract: I will give a short introduction to generative diffusion models and present their performance compared to other generative models (including GANs). Moreover, I will present two works that we did in the last year: (i) Noise Estimation for Generative Diffusion Models: ... Read more
Marginal Contribution Feature Importance – an Axiomatic Approach for Explaining Data. Amnon Catav (TAU).
The recording of Amnon's talk: https://us02web.zoom.us/rec/share/TxC7tgud-XyP-h577Pa-EwhLt9Bi4P7BCurUbafwRuW_-UiCxJDG8L9gAJylLiU4.OMMHDUVzuEc4ZVnE?startTime=1636279531000 Title: Marginal Contribution Feature Importance - an Axiomatic Approach for Explaining Data Abstract: In recent years, methods were proposed for assigning feature importance scores to measure the contribution of individual features. While in some cases the goal is to understand a specific model, in many cases the goal is ... Read more
NLP session at AI Week – featuring talks by Prof. Yoav Goldberg and Prof. Ido Dagan
Keynote Yoav Goldberg , Research Director of AI2 Israel; Professor at the Computer Science Department, Bar-Ilan University 11:05 - 11:25 Calendar 1 Calendar Beyond End-to-End: the Case of Multi-text Summarization Ido Dagan , Professor at the Department of Computer Science, Bar-Ilan University; Director, Bar-Ilan Data Science Institute
Investigating fine-tuning of pre-trained language models. Marius Mosbach, from Saarland University
Building 105, Room 106On the 21st of June Marius Mosbach, from Saarland University will give a talk at the lab. He's here for a visit of about 2.5 weeks (starting from June 7th), so be nice to him and say hi =) If you'd like to chat with him (and you should!), add your name in the attached ... Read more
Genomic language model for function prediction of microbial genes – Danielle Miller (TAU)
בחדר 212 בניין 212דוקטורנטית מאת״א תבוא להרצות על מודלי שפה לגנומים בקטריאלים. מוזמנים להגיע ולהפיץ לסטודנטים ולחברי סגל נוספים. ההרצאה תתקיים בשעה 14:00 ביום ב׳ 12.12 בחדר 212 בניין 212. כמו כן, אני מתכנן לשדר אותה בזום: https://us02web.zoom.us/j/5509052372 Title: Genomic language model for function prediction of microbial genes Abstract: Revealing the function of uncharacterized genes is a fundamental challenge in an era of ever-increasing ... Read more
Advanced Machine Learning Methods to Accelerate Materials Discovery (Santiago Miret, Intel)
Building 605, room 11Hi everyone, You are invited to attend the talk of Santiago Miret at the NLP group seminar that will be held on Thursday 9.3.23, at 11 am. The talk will last approximately 1.5 hours including Q&A. See more details below. Best Regards, Idan Location: Building 605, room 11 Title: Advanced Machine Learning Methods to Accelerate Materials ... Read more