Home /
Research
Showing 703 - 708 / 897
On the Practical Ability of Recurrent Neural Networks to Recognize Hierarchical Languages
SatwikBhattamishra, KabirAhuja, NavinGoyal....
Published date-11/08/2020
While recurrent models have been effective in NLP tasks, their performance on context-free languages (CFLs) has been found to be quite weak. Given that CFLs are believed to capture important …
Denoising Relation Extraction from Document-level Distant Supervision
ChaojunXiao, YuanYAO, RuobingXie....
Published date-11/08/2020
Denoising, RelationExtraction
Distant supervision (DS) has been widely used to generate auto-labeled data for sentence-level relation extraction (RE), which improves RE performance. However, the existing success of DS cannot be directly transferred …
Learning Continuous System Dynamics from Irregularly-Sampled Partial Observations
ZijieHuang, YizhouSun, WeiWang....
Published date-11/08/2020
MotionCapture
Many real-world systems, such as moving planets, can be considered as multi-agent dynamic systems, where objects interact with each other and co-evolve along with the time. Such dynamics is usually …
Integrating Human Gaze into Attention for Egocentric Activity Recognition
KyleMin, JasonJ.Corso....
Published date-11/08/2020
ActionRecognition, EgocentricActivityRecognition
It is well known that human gaze carries significant information about visual attention. However, there are three main difficulties in incorporating the gaze data in an attention mechanism of deep …
Performative Prediction in a Stateful World
GavinBrown, ShlomiHod, IdenKalemaj....
Published date-11/08/2020
Deployed supervised machine learning models make predictions that interact with and influence the world. This phenomenon is called "performative prediction" by Perdomo et al. (2020), who investigated it in a …
Naturalization of Text by the Insertion of Pauses and Filler Words
RichaSharma, ParthVipulShah, AshwiniM.Joshi....
Published date-11/07/2020
In this article, we introduce a set of methods to naturalize text based on natural human speech. Voice-based interactions provide a natural way of interfacing with electronic systems and are …