Search Results for author: Francis Ferraro

Found 34 papers, 7 papers with code

A General Framework for Auditing Differentially Private Machine Learning

no code implementations16 Oct 2022 Fred Lu, Joseph Munoz, Maya Fuchs, Tyler LeBlond, Elliott Zaresky-Williams, Edward Raff, Francis Ferraro, Brian Testa

We present a framework to statistically audit the privacy guarantee conferred by a differentially private machine learner in practice.

PASTA: A Dataset for Modeling Participant States in Narratives

no code implementations31 Jul 2022 Sayontan Ghosh, Mahnaz Koupaee, Isabella Chen, Francis Ferraro, Nathanael Chambers, Niranjan Balasubramanian

Often, these participant states are not explicitly mentioned in the narrative, left to be filled in via common-sense or inference.

Benchmarking Common Sense Reasoning

Neural Bregman Divergences for Distance Learning

no code implementations9 Jun 2022 Fred Lu, Edward Raff, Francis Ferraro

Many metric learning tasks, such as triplet learning, nearest neighbor retrieval, and visualization, are treated primarily as embedding tasks where the ultimate metric is some variant of the Euclidean distance (e. g., cosine or Mahalanobis), and the algorithm must learn to embed points into the pre-chosen space.

Metric Learning Retrieval

RevUp: Revise and Update Information Bottleneck for Event Representation

1 code implementation24 May 2022 Mehdi Rezaee, Francis Ferraro

We reparameterize the model's discrete variables with auxiliary continuous latent variables and a light-weight hierarchical structure.

Continuously Generalized Ordinal Regression for Linear and Deep Models

no code implementations14 Feb 2022 Fred Lu, Francis Ferraro, Edward Raff

Our method, which we term continuously generalized ordinal logistic, significantly outperforms the standard ordinal logistic model over a thorough set of ordinal regression benchmark datasets.

Inductive Bias regression

Transferring Semantic Knowledge Into Language Encoders

no code implementations14 Oct 2021 Mohammad Umair, Francis Ferraro

We introduce semantic form mid-tuning, an approach for transferring semantic knowledge from semantic meaning representations into transformer-based language encoders.

Reading Comprehension Sentence Embedding +1

Discriminative and Generative Transformer-based Models For Situation Entity Classification

no code implementations15 Sep 2021 Mehdi Rezaee, Kasra Darvish, Gaoussou Youssouf Kebe, Francis Ferraro

We re-examine the situation entity (SE) classification task with varying amounts of available training data.

Neural Variational Learning for Grounded Language Acquisition

no code implementations20 Jul 2021 Nisha Pillai, Cynthia Matuszek, Francis Ferraro

We propose a learning system in which language is grounded in visual percepts without specific pre-defined categories of terms.

Language Acquisition

Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment

no code implementations Findings (ACL) 2021 Ashwinkumar Ganesan, Francis Ferraro, Tim Oates

We propose a Bi-Directional Manifold Alignment (BDMA) that learns a non-linear mapping between two manifolds by explicitly training it to be bijective.


Sampling Approach Matters: Active Learning for Robotic Language Acquisition

no code implementations16 Nov 2020 Nisha Pillai, Edward Raff, Francis Ferraro, Cynthia Matuszek

Ordering the selection of training data using active learning can lead to improvements in learning efficiently from smaller corpora.

Active Learning Language Acquisition

A Discrete Variational Recurrent Topic Model without the Reparametrization Trick

1 code implementation NeurIPS 2020 Mehdi Rezaee, Francis Ferraro

We show how to learn a neural topic model with discrete random variables---one that explicitly models each word's assigned topic---using neural variational inference that does not rely on stochastic backpropagation to handle the discrete variables.

Variational Inference

Event Representation with Sequential, Semi-Supervised Discrete Variables

no code implementations NAACL 2021 Mehdi Rezaee, Francis Ferraro

Within the context of event modeling and understanding, we propose a new method for neural sequence modeling that takes partially-observed sequences of discrete, external knowledge into account.

Presentation and Analysis of a Multimodal Dataset for Grounded Language Learning

no code implementations29 Jul 2020 Patrick Jenkins, Rishabh Sachdeva, Gaoussou Youssouf Kebe, Padraig Higgins, Kasra Darvish, Edward Raff, Don Engel, John Winder, Francis Ferraro, Cynthia Matuszek

Grounded language acquisition -- learning how language-based interactions refer to the world around them -- is amajor area of research in robotics, NLP, and HCI.

Grounded language learning

Locality Preserving Loss: Neighbors that Live together, Align together

no code implementations EACL (AdaptNLP) 2021 Ashwinkumar Ganesan, Francis Ferraro, Tim Oates

We present a locality preserving loss (LPL) that improves the alignment between vector space embeddings while separating uncorrelated representations.

Natural Language Inference Sentence Embeddings +3

SURFACE: Semantically Rich Fact Validation with Explanations

no code implementations31 Oct 2018 Ankur Padia, Francis Ferraro, Tim Finin

Judging the veracity of a sentence making one or more claims is an important and challenging problem with many dimensions.

General Classification

UMBC at SemEval-2018 Task 8: Understanding Text about Malware

no code implementations SEMEVAL 2018 Ankur Padia, Arpita Roy, Taneeya Satyapanich, Francis Ferraro, SHimei Pan, Youngja Park, Anupam Joshi, Tim Finin

We describe the systems developed by the UMBC team for 2018 SemEval Task 8, SecureNLP (Semantic Extraction from CybersecUrity REports using Natural Language Processing).

Semantic Proto-Roles

no code implementations TACL 2015 Drew Reisinger, Rachel Rudinger, Francis Ferraro, Craig Harman, Kyle Rawlins, Benjamin Van Durme

We present the first large-scale, corpus based verification of Dowty{'}s seminal theory of proto-roles.

Semantic Role Labeling

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