Share This Author
COMET-ATOMIC 2020: On Symbolic and Neural Commonsense Knowledge Graphs
It is proposed that manually constructed CSKGs will never achieve the coverage necessary to be applicable in all situations encountered by NLP agents, and a new evaluation framework for testing the utility of KGs based on how effectively implicit knowledge representations can be learned from them is proposed.
Towards comprehensive syntactic and semantic annotations of the clinical narrative
- D. Albright, Arrick Lanfranchi, G. Savova
- Computer ScienceJ. Am. Medical Informatics Assoc.
- 25 January 2013
This project takes a foundational step towards bringing the field of clinical NLP up to par with NLP in the general domain and provides a resource for research and application development that would have been previously impossible.
PropBank Annotation Guidelines
Social Chemistry 101: Learning to Reason about Social and Moral Norms
- Maxwell Forbes, Jena D. Hwang, Vered Shwartz, Maarten Sap, Yejin Choi
- Computer ScienceEMNLP
- 1 November 2020
A new conceptual formalism to study people's everyday social norms and moral judgments over a rich spectrum of real life situations described in natural language and a model framework, Neural Norm Transformer, learns and generalizes Social-Chem-101 to successfully reason about previously unseen situations, generating relevant (and potentially novel) attribute-aware social rules-of-thumb.
Delphi: Towards Machine Ethics and Norms
The first major attempt to computationally explore the vast space of moral implications in real-world settings is conducted, with Delphi, a unified model of descriptive ethics empowered by diverse data of people’s moral judgment from COMMONSENSE NORM BANK.
Moral Stories: Situated Reasoning about Norms, Intents, Actions, and their Consequences
- Denis Emelin, Ronan Le Bras, Jena D. Hwang, Maxwell Forbes, Yejin Choi
- Computer ScienceEMNLP
- 31 December 2020
Moral Stories, a crowd-sourced dataset of structured, branching narratives for the study of grounded, goal-oriented social reasoning, is introduced and decoding strategies that combine multiple expert models to significantly improve the quality of generated actions, consequences, and norms compared to strong baselines are proposed.
Building Universal Dependency Treebanks in Korean
This paper presents three treebanks in Korean that consist of dependency trees derived from existing treebanks, the Google UD Treebank, the Penn Korean Treebank, and the KAIST Treebank, and…
PropBank Annotation of Multilingual Light Verb Constructions
This paper has addressed the task of PropBank annotation of light verb constructions, which like multi-word expressions pose special problems and has evaluated 3 different possible methods of annotation.
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning
This paper proposes DeLorean, a new unsupervised decoding algorithm that can flexibly incorporate both the past and future contexts using only off-the-shelf, left-to-right language models and no supervision.
Thinking Like a Skeptic: Defeasible Inference in Natural Language
From Defeasible NLI, both a classification and generation task for defeasible inference are developed, and it is demonstrated that the generation task is much more challenging.