13 citations · 33 across the 11 of their papers we have counts for
14 papers
Knowledge is a Region in Weight Space for Fine-tuned Language Models
Almog Gueta, Elad Venezian, Colin Raffel +3
Research on neural networks has focused on understanding a single model trained on a single dataset. However, relatively little is known about the relationships between different m…
SimpleStyle: An Adaptable Style Transfer Approach
Elron Bandel, Yoav Katz, Noam Slonim +1
Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text…
ColD Fusion: Collaborative Descent for Distributed Multitask Finetuning
Shachar Don-Yehiya, Elad Venezian, Colin Raffel +3
We propose a new paradigm to continually evolve pretrained models, denoted ColD Fusion. It provides the benefits of multitask learning but leverages distributed computation with li…
Where to start? Analyzing the potential value of intermediate models
Leshem Choshen, Elad Venezian, Shachar Don-Yehia +2
Previous studies observed that finetuned models may be better base models than the vanilla pretrained model. Such a model, finetuned on some source dataset, may provide a better st…
Label Sleuth: From Unlabeled Text to a Classifier in a Few Hours
Eyal Shnarch, Alon Halfon, Ariel Gera +19
Text classification can be useful in many real-world scenarios, saving a lot of time for end users. However, building a custom classifier typically requires coding skills and ML kn…
VIRATrustData: A Trust-Annotated Corpus of Human-Chatbot Conversations About COVID-19 Vaccines
Roni Friedman, João Sedoc, Shai Gretz +5
Public trust in medical information is crucial for successful application of public health policies such as vaccine uptake. This is especially true when the information is offered…
Multi-Domain Targeted Sentiment Analysis
Orith Toledo-Ronen, Matan Orbach, Yoav Katz +1
Targeted Sentiment Analysis (TSA) is a central task for generating insights from consumer reviews. Such content is extremely diverse, with sites like Amazon or Yelp containing revi…
Benchmark Data and Evaluation Framework for Intent Discovery Around COVID-19 Vaccine Hesitancy
Shai Gretz, Assaf Toledo, Roni Friedman +7
The COVID-19 pandemic has made a huge global impact and cost millions of lives. As COVID-19 vaccines were rolled out, they were quickly met with widespread hesitancy. To address th…
Fusing finetuned models for better pretraining
Leshem Choshen, Elad Venezian, Noam Slonim +1
Pretrained models are the standard starting point for training. This approach consistently outperforms the use of a random initialization. However, pretraining is a costly endeavou…
Overview of the 2021 Key Point Analysis Shared Task
Roni Friedman, Lena Dankin, Yufang Hou +3
We describe the 2021 Key Point Analysis (KPA-2021) shared task on key point analysis that we organized as a part of the 8th Workshop on Argument Mining (ArgMining 2021) at EMNLP 20…
Project Debater APIs: Decomposing the AI Grand Challenge
Roy Bar-Haim, Yoav Kantor, Elad Venezian +2
Project Debater was revealed in 2019 as the first AI system that can debate human experts on complex topics. Engaging in a live debate requires a diverse set of skills, and Project…
YASO: A Targeted Sentiment Analysis Evaluation Dataset for Open-Domain Reviews
Matan Orbach, Orith Toledo-Ronen, Artem Spector +3
Current TSA evaluation in a cross-domain setup is restricted to the small set of review domains available in existing datasets. Such an evaluation is limited, and may not reflect t…
Fast End-to-End Wikification
Ilya Shnayderman, Liat Ein-Dor, Yosi Mass +7
Wikification of large corpora is beneficial for various NLP applications. Existing methods focus on quality performance rather than run-time, and are therefore non-feasible for lar…
Learning to combine Grammatical Error Corrections
Yoav Kantor, Yoav Katz, Leshem Choshen +5
The field of Grammatical Error Correction (GEC) has produced various systems to deal with focused phenomena or general text editing. We propose an automatic way to combine black-bo…