Search Results for author:
Found 29 papers, 14 papers with code
Dyna-bAbI: unlocking bAbI’s potential with dynamic synthetic benchmarking
However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation.
Visual Editing with LLM-based Tool Chaining: An Efficient Distillation Approach for Real-Time Applications
We present a practical distillation approach to fine-tune LLMs for invoking tools in real-time applications.
ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies
We demonstrate our pipeline and create ProPara-Logy, a dataset of analogies between scientific processes.
State of What Art? A Call for Multi-Prompt LLM Evaluation
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
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.
FAME: Flexible, Scalable Analogy Mappings Engine
In this work, we relax the input requirements, requiring only names of entities to be mapped.
Towards Concept-Aware Large Language Models
Concepts play a pivotal role in various human cognitive functions, including learning, reasoning and communication.
IRFL: Image Recognition of Figurative Language
We release our dataset, benchmark, and code, in hopes of driving the development of models that can better understand figurative language.
VASR: Visual Analogies of Situation Recognition
We leverage situation recognition annotations and the CLIP model to generate a large set of 500k candidate analogies.
Ranked #1 on
Visual Reasoning
on VASR
The Lean Data Scientist: Recent Advances towards Overcoming the Data Bottleneck
Machine learning (ML) is revolutionizing the world, affecting almost every field of science and industry.
Breakpoint Transformers for Modeling and Tracking Intermediate Beliefs
Can we teach natural language understanding models to track their beliefs through intermediate points in text?
50 Ways to Bake a Cookie: Mapping the Landscape of Procedural Texts
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
We introduce a novel dataset of 300, 000 online games of Cards Against Humanity, including 785K unique jokes, analyze it and provide insights.
Life is a Circus and We are the Clowns: Automatically Finding Analogies between Situations and Processes
Analogy-making gives rise to reasoning, abstraction, flexible categorization and counterfactual inference -- abilities lacking in even the best AI systems today.
Dyna-bAbI: unlocking bAbI's potential with dynamic synthetic benchmarking
However, the main synthetic resource for story understanding, the bAbI benchmark, lacks such a systematic mechanism for controllable task generation.
E-Commerce Dispute Resolution Prediction
E-Commerce marketplaces support millions of daily transactions, and some disagreements between buyers and sellers are unavoidable.
Catchphrase: Automatic Detection of Cultural References
In this paper, we study snowclones originating from pop-culture quotes; our goal is to automatically detect cultural references in text.
How Did This Get Funded?! Automatically Identifying Quirky Scientific Achievements
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.
"Alexa, what do you do for fun?" Characterizing playful requests with virtual assistants
Examples include jokes or absurd requests or questions such as, "Are you afraid of the dark?
Scaling Creative Inspiration with Fine-Grained Functional Aspects of Ideas
Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations.
Coming to Terms: Automatic Formation of Neologisms in Hebrew
Spoken languages are ever-changing, with new words entering them all the time.
Language (Re)modelling: Towards Embodied Language Understanding
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.
Ecological Semantics: Programming Environments for Situated Language Understanding
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.
Playing by the Book: An Interactive Game Approach for Action Graph Extraction from Text
Understanding procedural text requires tracking entities, actions and effects as the narrative unfolds.
Analogy Mining for Specific Design Needs
Finding analogical inspirations in distant domains is a powerful way of solving problems.
Ballpark Crowdsourcing: The Wisdom of Rough Group Comparisons
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.
A Machine Learning Approach to Routing
Can ideas and techniques from machine learning be leveraged to automatically generate "good" routing configurations?
Accelerating Innovation Through Analogy Mining
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.
Ballpark Learning: Estimating Labels from Rough Group Comparisons
We are interested in estimating individual labels given only coarse, aggregated signal over the data points.
