Search Results for author:
Found 12 papers, 5 papers with code
LaMDA: Language Models for Dialog Applications
We demonstrate that fine-tuning with annotated data and enabling the model to consult external knowledge sources can lead to significant improvements towards the two key challenges of safety and factual grounding.
Measuring Attribution in Natural Language Generation Models
With recent improvements in natural language generation (NLG) models for various applications, it has become imperative to have the means to identify and evaluate whether NLG output is only sharing verifiable information about the external world.
Retrieval-guided Counterfactual Generation for QA
To address these challenges, we develop a Retrieve-Generate-Filter(RGF) technique to create counterfactual evaluation and training data with minimal human supervision.
Decontextualization: Making Sentences Stand-Alone
Models for question answering, dialogue agents, and summarization often interpret the meaning of a sentence in a rich context and use that meaning in a new context.
QED: A Framework and Dataset for Explanations in Question Answering
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility and trust.
Compositional Generalization in Image Captioning
Image captioning models are usually evaluated on their ability to describe a held-out set of images, not on their ability to generalize to unseen concepts.
Ellipsis Resolution as Question Answering: An Evaluation
Most, if not all forms of ellipsis (e. g., so does Mary) are similar to reading comprehension questions (what does Mary do), in that in order to resolve them, we need to identify an appropriate text span in the preceding discourse.
Textual Analogy Parsing: What's Shared and What's Compared among Analogous Facts
To understand a sentence like "whereas only 10% of White Americans live at or below the poverty line, 28% of African Americans do" it is important not only to identify individual facts, e. g., poverty rates of distinct demographic groups, but also the higher-order relations between them, e. g., the disparity between them.
Learning a SAT Solver from Single-Bit Supervision
We present NeuroSAT, a message passing neural network that learns to solve SAT problems after only being trained as a classifier to predict satisfiability.
The Pragmatics of Indirect Commands in Collaborative Discourse
We focus on a less understood family of utterances for eliciting agent action, locatives like \emph{The chair is in the other room}, and demonstrate how these utterances indirectly command in specific game state contexts.
Graph Neural Networks and Boolean Satisfiability
In a weakly-supervised setting, that is, without problem specific feature engineering, Graph Neural Networks can learn features of satisfiability.
