research
∙
06/27/2022
Parametrically Retargetable Decision-Makers Tend To Seek Power
If capable AI agents are generally incentivized to seek power in service...
share
research
∙
06/23/2022
Formalizing the Problem of Side Effect Regularization
AI objectives are often hard to specify properly. Some approaches tackle...
research
∙
06/16/2022
Explainable Models via Compression of Tree Ensembles
Ensemble models (bagging and gradient-boosting) of relational decision t...
research
∙
10/15/2021
Dynamic probabilistic logic models for effective abstractions in RL
State abstraction enables sample-efficient learning and better task tran...
research
∙
09/13/2021
From Heatmaps to Structural Explanations of Image Classifiers
This paper summarizes our endeavors in the past few years in terms of ex...
research
∙
09/10/2021
Improving Multilingual Translation by Representation and Gradient Regularization
Multilingual Neural Machine Translation (NMT) enables one model to serve...
research
∙
11/13/2020
Structured Attention Graphs for Understanding Deep Image Classifications
Attention maps are a popular way of explaining the decisions of convolut...
research
∙
10/18/2020
DeepAveragers: Offline Reinforcement Learning by Solving Derived Non-Parametric MDPs
We study an approach to offline reinforcement learning (RL) based on opt...
research
∙
10/06/2020
On the Sub-Layer Functionalities of Transformer Decoder
There have been significant efforts to interpret the encoder of Transfor...
research
∙
06/11/2020
Avoiding Side Effects in Complex Environments
Reward function specification can be difficult, even in simple environme...
research
∙
05/28/2020
Relation Extraction with Explanation
Recent neural models for relation extraction with distant supervision al...
research
∙
10/01/2019
The Choice Function Framework for Online Policy Improvement
There are notable examples of online search improving over hand-coded or...
research
∙
08/14/2019
Entity-aware ELMo: Learning Contextual Entity Representation for Entity Disambiguation
We present a new local entity disambiguation system. The key to our syst...
research
∙
02/26/2019
Conservative Agency via Attainable Utility Preservation
Reward functions are often misspecified. An agent optimizing an incorrec...
research
∙
02/22/2019
Saliency Learning: Teaching the Model Where to Pay Attention
Deep learning has emerged as a compelling solution to many NLP tasks wit...
research
∙
12/18/2018
Interactive Naming for Explaining Deep Neural Networks: A Formative Study
We consider the problem of explaining the decisions of deep neural netwo...
research
∙
09/11/2018
Learning Scripts as Hidden Markov Models
Scripts have been proposed to model the stereotypical event sequences fo...
research
∙
09/09/2018
Attentional Multi-Reading Sarcasm Detection
Recognizing sarcasm often requires a deep understanding of multiple sour...
research
∙
08/26/2018
Event Detection with Neural Networks: A Rigorous Empirical Evaluation
Detecting events and classifying them into predefined types is an import...
research
∙
08/12/2018
Interpreting Recurrent and Attention-Based Neural Models: a Case Study on Natural Language Inference
Deep learning models have achieved remarkable success in natural languag...
research
∙
06/19/2018
Joint Neural Entity Disambiguation with Output Space Search
In this paper, we present a novel model for entity disambiguation that c...
research
∙
05/26/2018
Dependent Gated Reading for Cloze-Style Question Answering
We present a novel deep learning architecture to address the cloze-style...
research
∙
02/15/2018
Event Nugget Detection with Forward-Backward Recurrent Neural Networks
Traditional event detection methods heavily rely on manually engineered ...
research
∙
06/27/2012