Search Results for author: Dafna Shahaf

Found 27 papers, 12 papers with code

State of What Art? A Call for Multi-Prompt LLM Evaluation

1 code implementation31 Dec 2023 Moran Mizrahi, Guy Kaplan, Dan Malkin, Rotem Dror, Dafna Shahaf, Gabriel Stanovsky

Recent advances in large language models (LLMs) have led to the development of various evaluation benchmarks.

Imitation of Life: A Search Engine for Biologically Inspired Design

1 code implementation20 Dec 2023 Hen Emuna, Nadav Borenstein, Xin Qian, Hyeonsu Kang, Joel Chan, Aniket Kittur, Dafna Shahaf

We release data and code; we view BARcode as a step towards addressing the challenges that have historically hindered the practical application of BID to engineering innovation.

Natural Language Understanding

FAME: Flexible, Scalable Analogy Mappings Engine

no code implementations3 Nov 2023 Shahar Jacob, Chen Shani, Dafna Shahaf

In this work, we relax the input requirements, requiring only names of entities to be mapped.

Towards Concept-Aware Large Language Models

1 code implementation3 Nov 2023 Chen Shani, Jilles Vreeken, Dafna Shahaf

Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication.

IRFL: Image Recognition of Figurative Language

1 code implementation27 Mar 2023 Ron Yosef, Yonatan Bitton, Dafna Shahaf

We release our dataset, benchmark, and code, in hopes of driving the development of models that can better understand figurative language.

Classification Visual Reasoning

VASR: Visual Analogies of Situation Recognition

1 code implementation8 Dec 2022 Yonatan Bitton, Ron Yosef, Eli Strugo, Dafna Shahaf, Roy Schwartz, Gabriel Stanovsky

We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies.

Common Sense Reasoning Visual Analogies +1

The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck

no code implementations15 Nov 2022 Chen Shani, Jonathan Zarecki, Dafna Shahaf

Machine learning (ML) is revolutionizing the world, affecting almost every field of science and industry.

50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts

no code implementations31 Oct 2022 Moran Mizrahi, Dafna Shahaf

The web is full of guidance on a wide variety of tasks, from changing the oil in your car to baking an apple pie.

Cards Against AI: Predicting Humor in a Fill-in-the-blank Party Game

1 code implementation24 Oct 2022 Dan Ofer, Dafna Shahaf

We introduce a novel dataset of 300, 000 online games of Cards Against Humanity, including 785K unique jokes, analyze it and provide insights.

Feature Importance

Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes

1 code implementation21 Oct 2022 Oren Sultan, Dafna Shahaf

Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference -- abilities lacking in even the best AI systems today.

Analogical questions Analogical Similarity +2

Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking

no code implementations30 Nov 2021 Ronen Tamari, Kyle Richardson, Aviad Sar-Shalom, Noam Kahlon, Nelson Liu, Reut Tsarfaty, Dafna Shahaf

However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation.

Benchmarking Natural Language Understanding

E-Commerce Dispute Resolution Prediction

no code implementations13 Oct 2021 David Tsurel, Michael Doron, Alexander Nus, Arnon Dagan, Ido Guy, Dafna Shahaf

E-Commerce marketplaces support millions of daily transactions, and some disagreements between buyers and sellers are unavoidable.

Catchphrase: Automatic Detection of Cultural References

no code implementations ACL 2021 Nir Sweed, Dafna Shahaf

In this paper, we study snowclones originating from pop-culture quotes; our goal is to automatically detect cultural references in text.

Cultural Vocal Bursts Intensity Prediction

How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements

1 code implementation ACL 2021 Chen Shani, Nadav Borenstein, Dafna Shahaf

We construct a dataset containing thousands of funny papers and use it to learn classifiers, combining findings from psychology and linguistics with recent advances in NLP.

Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas

no code implementations19 Feb 2021 Tom Hope, Ronen Tamari, Hyeonsu Kang, Daniel Hershcovich, Joel Chan, Aniket Kittur, Dafna Shahaf

Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations.

Language (Re)modelling: Towards Embodied Language Understanding

no code implementations ACL 2020 Ronen Tamari, Chen Shani, Tom Hope, Miriam R. L. Petruck, Omri Abend, Dafna Shahaf

While natural language understanding (NLU) is advancing rapidly, today's technology differs from human-like language understanding in fundamental ways, notably in its inferior efficiency, interpretability, and generalization.

Natural Language Understanding Position

Ecological Semantics: Programming Environments for Situated Language Understanding

no code implementations10 Mar 2020 Ronen Tamari, Gabriel Stanovsky, Dafna Shahaf, Reut Tsarfaty

Large-scale natural language understanding (NLU) systems have made impressive progress: they can be applied flexibly across a variety of tasks, and employ minimal structural assumptions.

Common Sense Reasoning Grounded language learning +1

Analogy Mining for Specific Design Needs

no code implementations19 Dec 2017 Karni Gilon, Felicia Y Ng, Joel Chan, Hila Lifshitz Assaf, Aniket Kittur, Dafna Shahaf

Finding analogical inspirations in distant domains is a powerful way of solving problems.

Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons

1 code implementation13 Dec 2017 Tom Hope, Dafna Shahaf

By collecting rough guesses on groups of instances and using machine learning to infer the individual labels, our lightweight framework is able to address core crowdsourcing challenges and train machine learning models in a cost-effective way.

BIG-bench Machine Learning

A Machine Learning Approach to Routing

no code implementations10 Aug 2017 Asaf Valadarsky, Michael Schapira, Dafna Shahaf, Aviv Tamar

Can ideas and techniques from machine learning be leveraged to automatically generate "good" routing configurations?

BIG-bench Machine Learning reinforcement-learning +1

Accelerating Innovation Through Analogy Mining

no code implementations17 Jun 2017 Tom Hope, Joel Chan, Aniket Kittur, Dafna Shahaf

The availability of large idea repositories (e. g., the U. S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems.

Information Retrieval Retrieval

Ballpark Learning: Estimating Labels from Rough Group Comparisons

no code implementations30 Jun 2016 Tom Hope, Dafna Shahaf

We are interested in estimating individual labels given only coarse, aggregated signal over the data points.

Sentiment Analysis

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