90 citations · 376 across the 23 of their papers we have counts for
26 papers
Survey of Social Bias in Vision-Language Models
Nayeon Lee, Yejin Bang, Holy Lovenia +3
In recent years, the rapid advancement of machine learning (ML) models, particularly transformer-based pre-trained models, has revolutionized Natural Language Processing (NLP) and…
Improving Fairness and Robustness in End-to-End Speech Recognition through unsupervised clustering
Irina-Elena Veliche, Pascale Fung
The challenge of fairness arises when Automatic Speech Recognition (ASR) systems do not perform equally well for all sub-groups of the population. In the past few years there have…
Confucius, Cyberpunk and Mr. Science: Comparing AI ethics between China and the EU
Pascale Fung, Hubert Etienne
The exponential development and application of artificial intelligence triggered an unprecedented global concern for potential social and ethical issues. Stakeholders from differen…
CAiRE_HKUST at SemEval-2019 Task 3: Hierarchical Attention for Dialogue Emotion Classification
Genta Indra Winata, Andrea Madotto, Zhaojiang Lin +4
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 independent, but in this paper…
A novel repetition normalized adversarial reward for headline generation
Peng Xu, Pascale Fung
While reinforcement learning can effectively improve language generation models, it often suffers from generating incoherent and repetitive phrases \cite{paulus2017deep}. In this p…
Towards Universal End-to-End Affect Recognition from Multilingual Speech by ConvNets
Dario Bertero, Onno Kampman, Pascale Fung
We propose an end-to-end affect recognition approach using a Convolutional Neural Network (CNN) that handles multiple languages, with applications to emotion and personality recogn…
GlobalTrait: Personality Alignment of Multilingual Word Embeddings
Farhad Bin Siddique, Dario Bertero, Pascale Fung
We propose a multilingual model to recognize Big Five Personality traits from text data in four different languages: English, Spanish, Dutch and Italian. Our analysis shows that wo…
Towards End-to-end Automatic Code-Switching Speech Recognition
Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu +1
Speech recognition in mixed language has difficulties to adapt end-to-end framework due to the lack of data and overlapping phone sets, for example in words such as "one" in Englis…
Learn to Code-Switch: Data Augmentation using Copy Mechanism on Language Modeling
Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu +1
Building large-scale datasets for training code-switching language models is challenging and very expensive. To alleviate this problem using parallel corpus has been a major workar…
Learning Comment Generation by Leveraging User-Generated Data
Zhaojiang Lin, Genta Indra Winata, Pascale Fung
Existing models on open-domain comment generation are difficult to train, and they produce repetitive and uninteresting responses. The problem is due to multiple and contradictory…
Emo2Vec: Learning Generalized Emotion Representation by Multi-task Training
Peng Xu, Andrea Madotto, Chien-Sheng Wu +2
In this paper, we propose Emo2Vec which encodes emotional semantics into vectors. We train Emo2Vec by multi-task learning six different emotion-related tasks, including emotion/sen…
Reducing Gender Bias in Abusive Language Detection
Ji Ho Park, Jamin Shin, Pascale Fung
Abusive language detection models tend to have a problem of being biased toward identity words of a certain group of people because of imbalanced training datasets. For example, "Y…
Attention-Based LSTM for Psychological Stress Detection from Spoken Language Using Distant Supervision
Genta Indra Winata, Onno Pepijn Kampman, Pascale Fung
We propose a Long Short-Term Memory (LSTM) with attention mechanism to classify psychological stress from self-conducted interview transcriptions. We apply distant supervision by a…
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
Andrea Madotto, Chien-Sheng Wu, Pascale Fung
End-to-end task-oriented dialog systems usually suffer from the challenge of incorporating knowledge bases. In this paper, we propose a novel yet simple end-to-end differentiable m…
Investigating Audio, Visual, and Text Fusion Methods for End-to-End Automatic Personality Prediction
Onno Kampman, Elham J. Barezi, Dario Bertero +1
We propose a tri-modal architecture to predict Big Five personality trait scores from video clips with different channels for audio, text, and video data. For each channel, stacked…
Code-Switching Language Modeling using Syntax-Aware Multi-Task Learning
Genta Indra Winata, Andrea Madotto, Chien-Sheng Wu +1
Lack of text data has been the major issue on code-switching language modeling. In this paper, we introduce multi-task learning based language model which shares syntax representat…
Bilingual Character Representation for Efficiently Addressing Out-of-Vocabulary Words in Code-Switching Named Entity Recognition
Genta Indra Winata, Chien-Sheng Wu, Andrea Madotto +1
We propose an LSTM-based model with hierarchical architecture on named entity recognition from code-switching Twitter data. Our model uses bilingual character representation and tr…
PlusEmo2Vec at SemEval-2018 Task 1: Exploiting emotion knowledge from emoji and #hashtags
Ji Ho Park, Peng Xu, Pascale Fung
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 both sentence and word level rep…
Cross-domain Dialogue Policy Transfer via Simultaneous Speech-act and Slot Alignment
Kaixiang Mo, Yu Zhang, Qiang Yang +1
Dialogue policy transfer enables us to build dialogue policies in a target domain with little data by leveraging knowledge from a source domain with plenty of data. Dialogue senten…
Fine Grained Knowledge Transfer for Personalized Task-oriented Dialogue Systems
Kaixiang Mo, Yu Zhang, Qiang Yang +1
Training a personalized dialogue system requires a lot of data, and the data collected for a single user is usually insufficient. One common practice for this problem is to share t…
One-step and Two-step Classification for Abusive Language Detection on Twitter
Ji Ho Park, Pascale Fung
Automatic abusive language detection is a difficult but important task for online social media. Our research explores a two-step approach of performing classification on abusive la…
Towards Empathetic Human-Robot Interactions
Pascale Fung, Dario Bertero, Yan Wan +6
Since the late 1990s when speech companies began providing their customer-service software in the market, people have gotten used to speaking to machines. As people interact more o…
A Pattern Matching method for finding Noun and Proper Noun Translations from Noisy Parallel Corpora
Pascale Fung
We present a pattern matching method for compiling a bilingual lexicon of nouns and proper nouns from unaligned, noisy parallel texts of Asian/Indo-European language pairs. Tagging…
Aligning Noisy Parallel Corpora Across Language Groups : Word Pair Feature Matching by Dynamic Time Warping
Pascale Fung, Kathleen McKeown
We propose a new algorithm called DK-vec for aligning pairs of Asian/Indo-European noisy parallel texts without sentence boundaries. DK-vec improves on previous alignment algorithm…