6 citations · 22 across the 16 of their papers we have counts for
19 papers
Improving Neural Ranking Models with Traditional IR Methods
Anik Saha, Oktie Hassanzadeh, Alex Gittens +3
Neural ranking methods based on large transformer models have recently gained significant attention in the information retrieval community, and have been adopted by major commercia…
A Cross-Domain Evaluation of Approaches for Causal Knowledge Extraction
Anik Saha, Oktie Hassanzadeh, Alex Gittens +3
Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understan…
LakeBench: Benchmarks for Data Discovery over Data Lakes
Kavitha Srinivas, Julian Dolby, Ibrahim Abdelaziz +6
Within enterprises, there is a growing need to intelligently navigate data lakes, specifically focusing on data discovery. Of particular importance to enterprises is the ability to…
Generalized Planning in PDDL Domains with Pretrained Large Language Models
Tom Silver, Soham Dan, Kavitha Srinivas +3
Recent work has considered whether large language models (LLMs) can function as planners: given a task, generate a plan. We investigate whether LLMs can serve as generalized planne…
Some congruences for and -regular partitions
T Kathiravan, K Srinivas, Usha K Sangale
Let count the number of , -regular partitions respectively. In this paper we shall derive infinite families of congruen…
A Vision for Semantically Enriched Data Science
Udayan Khurana, Kavitha Srinivas, Sainyam Galhotra +1
The recent efforts in automation of machine learning or data science has achieved success in various tasks such as hyper-parameter optimization or model selection. However, key are…
Serenity: Library Based Python Code Analysis for Code Completion and Automated Machine Learning
Wenting Zhao, Ibrahim Abdelaziz, Julian Dolby +3
Dynamically typed languages such as Python have become very popular. Among other strengths, Python's dynamic nature and its straightforward linking to native code have made it the…
Exploring Code Style Transfer with Neural Networks
Karl Munson, Anish Savla, Chih-Kai Ting +3
Style is a significant component of natural language text, reflecting a change in the tone of text while keeping the underlying information the same. Even though programming langua…
A Survey on Semantics in Automated Data Science
Udayan Khurana, Kavitha Srinivas, Horst Samulowitz
Data Scientists leverage common sense reasoning and domain knowledge to understand and enrich data for building predictive models. In recent years, we have witnessed a surge in too…
Large Scale Generation of Labeled Type Data for Python
Ibrahim Abdelaziz, Julian Dolby, Kavitha Srinivas
Recently, dynamically typed languages, such as Python, have gained unprecedented popularity. Although these languages alleviate the need for mandatory type annotations, types still…
Federated Data Science to Break Down Silos [Vision]
Essam Mansour, Kavitha Srinivas, Katja Hose
Similar to Open Data initiatives, data science as a community has launched initiatives for sharing not only data but entire pipelines, derivatives, artifacts, etc. (Open Data Scien…
A Scalable AutoML Approach Based on Graph Neural Networks
Mossad Helali, Essam Mansour, Ibrahim Abdelaziz +2
AutoML systems build machine learning models automatically by performing a search over valid data transformations and learners, along with hyper-parameter optimization for each lea…
Can Machines Read Coding Manuals Yet? -- A Benchmark for Building Better Language Models for Code Understanding
Ibrahim Abdelaziz, Julian Dolby, Jamie McCusker +1
Code understanding is an increasingly important application of Artificial Intelligence. A fundamental aspect of understanding code is understanding text about code, e.g., documenta…
Euclidean algorithm in Galois Quartic Fields
K Srinivas, M Subramani, Usha K Sangale
We prove that all imaginary biquadratic fields and cyclic quartic fields of class number are Euclidean.
Learning to Guide a Saturation-Based Theorem Prover
Ibrahim Abdelaziz, Maxwell Crouse, Bassem Makni +8
Traditional automated theorem provers have relied on manually tuned heuristics to guide how they perform proof search. Recently, however, there has been a surge of interest in the…
A Toolkit for Generating Code Knowledge Graphs
Ibrahim Abdelaziz, Julian Dolby, Jamie McCusker +1
Knowledge graphs have been proven extremely useful in powering diverse applications in semantic search and natural language understanding. In this paper, we present GraphGen4Code,…
A Deep Reinforcement Learning Approach to First-Order Logic Theorem Proving
Maxwell Crouse, Ibrahim Abdelaziz, Bassem Makni +7
Automated theorem provers have traditionally relied on manually tuned heuristics to guide how they perform proof search. Deep reinforcement learning has been proposed as a way to o…
Merging datasets through deep learning
Kavitha Srinivas, Abraham Gale, Julian Dolby
Merging datasets is a key operation for data analytics. A frequent requirement for merging is joining across columns that have different surface forms for the same entity (e.g., th…
A Principled Approach to Bridging the Gap between Graph Data and their Schemas
Marcelo Arenas, Gonzalo I. Diaz, Achille Fokoue +2
Although RDF graphs have schema information associated with them, in practice it is very common to find cases in which data do not fully conform to their schema. A prominent exampl…