research
∙
06/02/2023
NLPositionality: Characterizing Design Biases of Datasets and Models
Design biases in NLP systems, such as performance differences for differ...
share
research
∙
05/24/2023
Improving Language Models with Advantage-based Offline Policy Gradients
Improving language model generations according to some user-defined qual...
research
∙
10/14/2021
Delphi: Towards Machine Ethics and Norms
What would it take to teach a machine to behave ethically? While broad e...
research
∙
10/14/2021
Symbolic Knowledge Distillation: from General Language Models to Commonsense Models
The common practice for training commonsense models has gone from-human-...
research
∙
04/18/2021
CLIPScore: A Reference-free Evaluation Metric for Image Captioning
Image captioning has conventionally relied on reference-based automatic ...
research
∙
04/16/2021
proScript: Partially Ordered Scripts Generation via Pre-trained Language Models
Scripts - standardized event sequences describing typical everyday activ...
research
∙
03/24/2021
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
Commonsense AI has long been seen as a near impossible goal – until rece...
research
∙
03/24/2021
NaturalProofs: Mathematical Theorem Proving in Natural Language
Understanding and creating mathematics using natural mathematical langua...
research
∙
01/01/2021
Understanding Few-Shot Commonsense Knowledge Models
Providing natural language processing systems with commonsense knowledge...
research
∙
12/31/2020
Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
In social settings, much of human behavior is governed by unspoken rules...
research
∙
10/24/2020
NeuroLogic Decoding: (Un)supervised Neural Text Generation with Predicate Logic Constraints
Conditional text generation often requires lexical constraints, i.e., wh...
research
∙
10/15/2020
Natural Language Rationales with Full-Stack Visual Reasoning: From Pixels to Semantic Frames to Commonsense Graphs
Natural language rationales could provide intuitive, higher-level explan...
research
∙
10/12/2020
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
Recent years have brought about a renewed interest in commonsense repres...
research
∙
10/12/2020
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
Abductive and counterfactual reasoning, core abilities of everyday human...
research
∙
10/04/2020
Paragraph-Level Commonsense Transformers with Recurrent Memory
Human understanding of narrative texts requires making commonsense infer...
research
∙
08/20/2020
Scruples: A Corpus of Community Ethical Judgments on 32,000 Real-Life Anecdotes
As AI systems become an increasing part of people's everyday lives, it b...
research
∙
04/24/2020
G-DAUG: Generative Data Augmentation for Commonsense Reasoning
Recent advances in commonsense reasoning depend on large-scale human-ann...
research
∙
04/11/2020
Unsupervised Commonsense Question Answering with Self-Talk
Natural language understanding involves reading between the lines with i...
research
∙
02/10/2020
Adversarial Filters of Dataset Biases
Large neural models have demonstrated human-level performance on languag...
research
∙
11/26/2019
PIQA: Reasoning about Physical Commonsense in Natural Language
To apply eyeshadow without a brush, should I use a cotton swab or a toot...
research
∙
08/31/2019
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning
Understanding narratives requires reading between the lines, which in tu...
research
∙
08/15/2019
Abductive Commonsense Reasoning
Abductive reasoning is inference to the most plausible explanation. For ...
research
∙
07/24/2019
WINOGRANDE: An Adversarial Winograd Schema Challenge at Scale
The Winograd Schema Challenge (WSC), proposed by Levesque et al. (2011) ...
research
∙
10/03/2016
Phase-Mapper: An AI Platform to Accelerate High Throughput Materials Discovery
High-Throughput materials discovery involves the rapid synthesis, measur...
research
∙
08/17/2015
Variable Elimination in the Fourier Domain
The ability to represent complex high dimensional probability distributi...
research
∙
11/27/2014