• Publications
  • Influence
Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture
TLDR
In this paper, we propose to use a set of simple, uniform in architecture LSTM-based models to recover different kinds of temporal relations from text. Expand
  • 25
  • 2
  • PDF
Context-Aware Neural Model for Temporal Information Extraction
TLDR
We propose a context-aware neural network model for temporal information extraction. Expand
  • 25
  • 2
  • PDF
Structure-dependent tone sandhi in real and nonce disyllables in Shanghai Wu
TLDR
We investigated the productivity of the two tone sandhi types through 48 speakers’ productions of real and nonce disyllables in Shanghai Wu and found that the spreading sandhi generally applies productively to nonce words, while the phrase-level sandhi is better interpreted as phonetic contour reduction. Expand
  • 14
  • 2
  • PDF
Solving Math Word Problems with Double-Decoder Transformer
TLDR
This paper proposes a Transformer-based model to generate equations for math word problems. Expand
  • 2
  • 1
  • PDF
Structure-Dependent Tone Sandhi in Real and Nonce Words in Shanghai
Disyllabic sequences in Shanghai Wu undergo different types of tone sandhi depending on their syntactic structure: modifier-noun compounds spread the initial tone across the disyllable, whileExpand
  • 6
  • 1
  • PDF
Augmented reality eyeglasses for promoting home-based rehabilitation for children with cerebral palsy
TLDR
We have designed an augmented reality (AR) game for children with cerebral palsy (CP) to perform home-based neurorehabilitation. Expand
  • 8
A learning from demonstration framework to promote home-based neuromotor rehabilitation
TLDR
The paper proposes a learning from demonstration (LfD) framework which will enable children with motor disabilities to perform neuromotor rehabilitation exercises at home- and community- settings. Expand
  • 3
Triad-based Neural Network for Coreference Resolution
TLDR
We propose a triad-based neural network system that generates affinity scores between entity mentions for coreference resolution. Expand
  • 2
  • PDF
Automatic Labeling of Problem-Solving Dialogues for Computational Microgenetic Learning Analytics
TLDR
This paper presents a recurrent neural network model to automate the analysis of students’ computational thinking in problem-solving dialogue. Expand
  • 1
  • PDF
Prediction of glass transition temperature of polyacrylate using a quantitative structure property relationship model
Quantitative structure property relationships are systematically studied for glass transition temperature simulation of polyacrylate. A newly developed descriptor-generalized correlative index isExpand
  • 2