Search Results for author:
Found 10 papers, 6 papers with code
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc.
Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
The FOLs from the finetuned-BB-derived MoIE verify the elimination of the shortcut.
Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier
The classification outcome should reflect a high uncertainty on ambiguous in-distribution samples that lie close to the decision boundary.
AutoNLU: Detecting, root-causing, and fixing NLU model errors
Improving the quality of Natural Language Understanding (NLU) models, and more specifically, task-oriented semantic parsing models, in production is a cumbersome task.
Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules
Our reasoner uses a state-of-the-art transformer-based generative commonsense knowledge base (KB) as its source of background knowledge for reasoning.
Conversational Neuro-Symbolic Commonsense Reasoning
More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit).
Compositional Generalization with Tree Stack Memory Units
We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain.
Look-up and Adapt: A One-shot Semantic Parser
In this paper, we propose a semantic parser that generalizes to out-of-domain examples by learning a general strategy for parsing an unseen utterance through adapting the logical forms of seen utterances, instead of learning to generate a logical form from scratch.
Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs
This is because they mostly rely either on black-box function evaluations that do not capture the structure of the program, or on detailed execution traces that are expensive to obtain, and hence the training data has poor coverage of the domain under consideration.
Spectral Methods for Correlated Topic Models
NID distributions are generated through the process of normalizing a family of independent Infinitely Divisible (ID) random variables.
