-
Neural Passage Retrieval with Improved Negative Contrast
In this paper we explore the effects of negative sampling in dual encode...
10/23/2020 ∙ by Jing Lu, et al. ∙
0
∙
share
read it
-
RRF102: Meeting the TREC-COVID Challenge with a 100+ Runs Ensemble
In this paper, we report the results of our participation in the TREC-CO...
10/01/2020 ∙ by Michael Bendersky, et al. ∙
0
∙
share
read it
-
Zero-shot Neural Retrieval via Domain-targeted Synthetic Query Generation
Deep neural scoring models have recently been shown to improve ranking q...
04/29/2020 ∙ by Ji Ma, et al. ∙
0
∙
share
read it
-
QURIOUS: Question Generation Pretraining for Text Generation
Recent trends in natural language processing using pretraining have shif...
04/23/2020 ∙ by Shashi Narayan, et al. ∙
0
∙
share
read it
-
The Practical Challenges of Active Learning: Lessons Learned from Live Experimentation
We tested in a live setting the use of active learning for selecting tex...
06/28/2019 ∙ by Jean-François Kagy, et al. ∙
0
∙
share
read it
-
Autonomous Tissue Manipulation via Surgical Robot Using Learning Based Model Predictive Control
Tissue manipulation is a frequently used fundamental subtask of any surg...
02/04/2019 ∙ by Changyeob Shin, et al. ∙
0
∙
share
read it
-
Learning Soft Tissue Dynamics in Image Space for Automated Bimanual Tissue Manipulation with Surgical Robots
In this paper, reinforcement learning and learning from demonstration in...
02/04/2019 ∙ by Changyeob Shin, et al. ∙
0
∙
share
read it
-
State-of-the-art Chinese Word Segmentation with Bi-LSTMs
A wide variety of neural-network architectures have been proposed for th...
08/20/2018 ∙ by Ji Ma, et al. ∙
0
∙
share
read it
-
Natural Language Processing with Small Feed-Forward Networks
We show that small and shallow feed-forward neural networks can achieve ...
08/01/2017 ∙ by Jan A. Botha, et al. ∙
0
∙
share
read it
-
SyntaxNet Models for the CoNLL 2017 Shared Task
We describe a baseline dependency parsing system for the CoNLL2017 Share...
03/15/2017 ∙ by Chris Alberti, et al. ∙
0
∙
share
read it
