Home      Library      Discussions      About
Join us

@ece.ust.hk

Aug 22, 2018
Computation and Language

We discussed model biases, especially toward gender identity terms, in abusive language detection. We found out that pre-trained word embeddings, model architecture, and different datasets all can have influence. Also, we found our proposed methods …

Reducing Gender Bias in Abusive Language Detection

Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced tra…
Nov 01, 2018
Computation and Language

GlobalTrait: Personality Alignment of Multilingual Word Embeddings

We propose a multilingual model to recognize Big Five Personality traits from text data in four different languages: English, Spanish, Dutch and Ital…
Oct 24, 2018
Computation and Language

Learn to Code-Switch: Data Augmentation using Copy Mechanism on Langu…

Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem parallel corpu…
Jun 04, 2014
Information Theory

Throughput Optimized Multi-Source Cooperative Networks With Compute…

In this work, we investigate a multi-source multi-cast network with the aid of an arbitrary number of relays, where it is assumed that no direct link…
May 02, 2018
Artificial Intelligence
Machine Learning

Investigating Audio, Visual, and Text Fusion Methods for End-to-End …

We propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video …
Apr 12, 2017
Information Theory

Hybrid Beamforming via the Kronecker Decomposition for the Millimet…

Despite its promising performance gain, the realization of mmWave massive MIMO still faces several practical challenges. In particular, implementing …
Jun 10, 2019
Computation and Language

CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialog…

Detecting emotion from dialogue is a challenge that has not yet been extensively surveyed. One could consider the emotion of each dialogue turn to be…
May 05, 2019
Networking and Internet Architecture
Artificial Intelligence
Distributed
Parallel
and Cluster Computing
Information Theory
Image and Video Processing

Towards Big data processing in IoT: network management for online edg…

Heavy data load and wide cover range have always been crucial problems for internet of things (IoT). However, in mobile-edge computing (MEC) network,…
Jul 28, 2019
Computation and Language

CAiRE: An End-to-End Empathetic Chatbot

In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach …
Apr 20, 2018
Computation and Language
Artificial Intelligence

Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and…

Dialogue policy transfer enables us to build dialogue policies in a target domain with little data by leveraging knowledge from a source domain with …
Jan 07, 2020
Computation and Language
Machine Learning

Attention over Parameters for Dialogue Systems

Dialogue systems require a great deal of different but complementary expertise to assist, inform, and entertain humans. For example, different domain…
Nov 24, 2015
Information Theory

Energy Efficiency with Proportional Rate Fairness in Multi-Relay OFDM…

This paper investigates the energy efficiency (EE) in multiple relay aided OFDM system, where decode-and-forward (DF) relay beamforming is employed t…
May 31, 2018
Computation and Language

Attention-Based LSTM for Psychological Stress Detection from Spoken …

We propose a Long Short-Term Memory (LSTM) with attention mechanism to classify psychological stress from self-conducted interview transcriptions. We…
May 30, 2018
Computation and Language

Bilingual Character Representation for Efficiently Addressing Out-o…

We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual …
Mar 18, 2014
Information Theory

High Speed Railway Wireless Communications: Efficiency v.s. Fairness

High speed railways (HSRs) have been deployed widely all over the world in recent years. Different from traditional cellular communication, its high …
May 30, 2018
Computation and Language

Bilingual Character Representation for Efficiently Addressing Out-o…

We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual …
Apr 23, 2018
Computation and Language

PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from…

This paper describes our system that has been submitted to SemEval-2018 Task 1: Affect in Tweets (AIT) to solve five subtasks. We focus on modeling b…
Oct 29, 2018
Computation and Language

Learning Comment Generation by Leveraging User-Generated Data

Existing models on open-domain comment generation produce repetitive and uninteresting response. To cope with this issue, we propose a combined appro…
Jul 28, 2019
Computation and Language

CAiRE: An End-to-End Empathetic Chatbot

In this paper, we present an end-to-end empathetic conversation agent CAiRE. Our system adapts TransferTransfo (Wolf et al., 2019) learning approach …
Nov 11, 2019
Computation and Language
Machine Learning

Zero-shot Cross-lingual Dialogue Systems with Transferable Latent V…

Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingu…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description