no code implementations • 14 Mar 2024 • Shadi Iskander, Kira Radinsky, Yonatan Belinkov
Mitigating social biases typically requires identifying the social groups associated with each data sample.
1 code implementation • 17 May 2023 • Shadi Iskander, Kira Radinsky, Yonatan Belinkov
In this work, we propose Iterative Gradient-Based Projection (IGBP), a novel method for removing non-linear encoded concepts from neural representations.
1 code implementation • 12 Jun 2022 • Uriel Singer, Haggai Roitman, Ido Guy, Kira Radinsky
A common approach employed by most previous works is to apply a layer that aggregates information from the historical neighbors of a node.
1 code implementation • 16 Apr 2022 • Gal Peretz, Kira Radinsky
The dataset is composed of process texts, simulation questions, and their corresponding computer codes represented by the DSL. We propose a neural program synthesis approach based on reinforcement learning with a novel state-transition semantic reward.
1 code implementation • Findings (NAACL) 2022 • Guy D. Rosin, Kira Radinsky
We leverage these representations for the task of semantic change detection; we apply our proposed mechanism to BERT and experiment on three datasets in different languages (English, German, and Latin) that also vary in time, size, and genre.
2 code implementations • 12 Oct 2021 • Guy D. Rosin, Ido Guy, Kira Radinsky
Our world is constantly evolving, and so is the content on the web.
1 code implementation • 19 Aug 2021 • Uriel Singer, Kira Radinsky
To the best of our knowledge, we are the first to optimize GNNs for the equalized odds criteria.
1 code implementation • 22 Dec 2020 • Guy D. Rosin, Ido Guy, Kira Radinsky
A significant number of event-related queries are issued in Web search.
no code implementations • ICML 2020 • Tomer Golany, Daniel Freedman, Kira Radinsky
Generating training examples for supervised tasks is a long sought after goal in AI.
no code implementations • IJCNLP 2019 • Dor Ringel, Gal Lavee, Ido Guy, Kira Radinsky
In this work, we show that cross-cultural differences can be harnessed for natural language text classification.
1 code implementation • CONLL 2019 • Guy D. Rosin, Kira Radinsky
Though languages can evolve slowly, they can also react strongly to dramatic world events.
4 code implementations • 15 May 2019 • Dean Zadok, Tom Hirshberg, Amir Biran, Kira Radinsky, Ashish Kapoor
This paper describes the exploration and learnings during the process of developing a self-driving algorithm in simulation, followed by deployment on a real car.
Robotics
1 code implementation • 21 Mar 2019 • Uriel Singer, Ido Guy, Kira Radinsky
In this work, we present a method for node embedding in temporal graphs.
1 code implementation • CONLL 2018 • Eylon Shoshan, Kira Radinsky
The dataset contains text descriptions of biological processes, and for each process, all of the involved entities in the process are labeled, including implicitly mentioned ones.
no code implementations • 8 Aug 2018 • Dana Sagi, Tzoof Avny, Kira Radinsky, Eugene Agichtein
One of the main challenges in ranking is embedding the query and document pairs into a joint feature space, which can then be fed to a learning-to-rank algorithm.
2 code implementations • 8 Apr 2018 • Shahar Harel, Kira Radinsky
In this work, we develop an algorithmic unsupervised-approach that automatically generates potential drug molecules given a prototype drug.
1 code implementation • EMNLP 2017 • Guy D. Rosin, Eytan Adar, Kira Radinsky
Search systems are often focused on providing relevant results for the "now", assuming both corpora and user needs that focus on the present.
1 code implementation • CONLL 2017 • Yotam Eshel, Noam Cohen, Kira Radinsky, Shaul Markovitch, Ikuya Yamada, Omer Levy
We address the task of Named Entity Disambiguation (NED) for noisy text.
no code implementations • 4 Feb 2014 • Kira Radinsky, Sagie Davidovich, Shaul Markovitch
Our Pundit algorithm generalizes examples of causality pairs to infer a causality predictor.