Search Results for author:
Found 29 papers, 4 papers with code
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
We show that our use of self-sampled correct and partially-correct solutions can benefit learning and help guide the sampling process, leading to more efficient exploration of the solution space.
Ranked #138 on
Arithmetic Reasoning
on GSM8K
Synchromesh: Reliable code generation from pre-trained language models
Then, Synchromesh feeds the examples to a pre-trained language model and samples programs using Constrained Semantic Decoding (CSD): a general framework for constraining the output to a set of valid programs in the target language.
CLUES: Few-Shot Learning Evaluation in Natural Language Understanding
We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks.
NL-EDIT: Correcting semantic parse errors through natural language interaction
We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors.
SCoRe: Pre-Training for Context Representation in Conversational Semantic Parsing
Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e. g., SQL, SPARQL) that can be executed against a structured ontology (e. g. databases, knowledge bases).
Ranked #3 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Structure-Grounded Pretraining for Text-to-SQL
Additionally, to evaluate different methods under more realistic text-table alignment settings, we create a new evaluation set Spider-Realistic based on Spider dev set with explicit mentions of column names removed, and adopt eight existing text-to-SQL datasets for cross-database evaluation.
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context
We explore learning web-based tasks from a human teacher through natural language explanations and a single demonstration.
Machine Teaching: A New Paradigm for Building Machine Learning Systems
This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the demand for machine learning systems and the ability for organizations to build them.
A Characterization of Prediction Errors
Understanding prediction errors and determining how to fix them is critical to building effective predictive systems.
Analysis of a Design Pattern for Teaching with Features and Labels
We analyze the potential risks and benefits of this teaching pattern through the use of teaching protocols, illustrative examples, and by providing bounds on the effort required for an optimal machine teacher using a linear learning algorithm, the most commonly used type of learners in interactive machine learning systems.
Selective Greedy Equivalence Search: Finding Optimal Bayesian Networks Using a Polynomial Number of Score Evaluations
We introduce Selective Greedy Equivalence Search (SGES), a restricted version of Greedy Equivalence Search (GES).
Regularized Minimax Conditional Entropy for Crowdsourcing
There is a rapidly increasing interest in crowdsourcing for data labeling.
Recursive Inversion Models for Permutations
We develop a new exponential family probabilistic model for permutations that can capture hierarchical structure, and that has the well known Mallows and generalized Mallows models as subclasses.
Asymptotic Model Selection for Directed Networks with Hidden Variables
We extend the Bayesian Information Criterion (BIC), an asymptotic approximation for the marginal likelihood, to Bayesian networks with hidden variables.
A Bayesian Approach to Learning Bayesian Networks with Local Structure
The majority of this work has concentrated on using decision-tree representations for the CPDs.
Structure and Parameter Learning for Causal Independence and Causal Interaction Models
This paper discusses causal independence models and a generalization of these models called causal interaction models.
Learning Mixtures of DAG Models
We describe computationally efficient methods for learning mixtures in which each component is a directed acyclic graphical model (mixtures of DAGs or MDAGs).
Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence (2003)
This is the Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence, which was held in Acapulco, Mexico, August 7-10 2003
CFW: A Collaborative Filtering System Using Posteriors Over Weights Of Evidence
We describe CFW, a computationally efficient algorithm for collaborative filtering that uses posteriors over weights of evidence.
A Model for Temporal Dependencies in Event Streams
We introduce the Piecewise-Constant Conditional Intensity Model, a model for learning temporal dependencies in event streams.
Improving Existing Fault Recovery Policies
In this paper we explain how to use data gathered from the interactions of the hand-made controller with the system, to create an optimized controller.
MAS: a multiplicative approximation scheme for probabilistic inference
We show how to optimize $\epsilon$-decompositions and provide a fast closed-form solution for an $L_2$ approximation.
