NLP

Creating a Speaking Engagement Index for Speech Therapy Assessment using Deep Learning

University of North Texas AI Summer — Creating a Speaking Engagement Index for Speech Therapy Assessment using Deep Learning:

Worked with a team of six to implement an autoencoder to analyze the effect of dimension reduction on a machine learning model.
Implemented Google Speech API to an Android application.
The research aims to help medical professionals diagnose patients with autism.

HIT-SCIR at MRP 2020: Transition-based Parser and Iterative Inference Parser

This paper describes our submission system (HIT-SCIR) for the CoNLL 2020 shared task: Cross-Framework and Cross-Lingual Meaning Representation Parsing.
Our solution consists of two sub-systems:

transition-based parser for Flavor (1) frameworks (UCCA, EDS, PTG)
and iterative inference parser for Flavor (2) frameworks (DRG, AMR)

In the final evaluation, our system is ranked 3rd among the seven team both in Cross-Framework Track and Cross-Lingual Track, with the macro-averaged MRP F1 score of 0.81/0.69.