Search Results
End-to-end NLP Pipelines in Rust
Libraries allowing NLP practitioners but also non-specialists to leverage state-of-the-art models have been instrumental in the democratization of this technology.
CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation
We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers.
Ranked #1 on
Text-to-Code Generation
on CodeXGLUE - CONCODE
Recommending Comprehensive Solutions for Programming Tasks by Mining Crowd Knowledge
To address these two problems, we propose CROKAGE (Crowd Knowledge Answer Generator), a tool that takes the description of a programming task (the query) and provides a comprehensive solution for the task.
Software Engineering
Contextual Word Representations: A Contextual Introduction
This introduction aims to tell the story of how we put words into computers.
EstNLTK - NLP Toolkit for Estonian
Although there are many tools for natural language processing tasks in Estonian, these tools are very loosely interoperable, and it is not easy to build practical applications on top of them.
KQA Pro: A Dataset with Explicit Compositional Programs for Complex Question Answering over Knowledge Base
To this end, we introduce KQA Pro, a dataset for Complex KBQA including ~120K diverse natural language questions.
OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare.
Empirical Study of Transformers for Source Code
In this work, we conduct a thorough empirical study of the capabilities of Transformers to utilize syntactic information in different tasks.
COMEX: A Tool for Generating Customized Source Code Representations
To overcome this barrier, we propose our tool COMEX - a framework that allows researchers and developers to create and combine multiple code-views which can be used by machine learning (ML) models for various SE tasks.
Open-Ended Visual Question-Answering
This thesis report studies methods to solve Visual Question-Answering (VQA) tasks with a Deep Learning framework.
