Search Results for author: Holy Lovenia

Found 25 papers, 14 papers with code

Contrastive Learning for Inference in Dialogue

1 code implementation19 Oct 2023 Etsuko Ishii, Yan Xu, Bryan Wilie, Ziwei Ji, Holy Lovenia, Willy Chung, Pascale Fung

Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker.

Contrastive Learning

InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems

1 code implementation13 Oct 2023 Willy Chung, Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, Pascale Fung

We present InstructTODS, a novel off-the-shelf framework for zero-shot end-to-end task-oriented dialogue systems that can adapt to diverse domains without fine-tuning.

Dialogue State Tracking Informativeness +4

Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models

no code implementations9 Oct 2023 Holy Lovenia, Wenliang Dai, Samuel Cahyawijaya, Ziwei Ji, Pascale Fung

Object hallucination poses a significant challenge in vision-language (VL) models, often leading to the generation of nonsensical or unfaithful responses with non-existent objects.

Hallucination Object +2

Survey of Social Bias in Vision-Language Models

no code implementations24 Sep 2023 Nayeon Lee, Yejin Bang, Holy Lovenia, Samuel Cahyawijaya, Wenliang Dai, Pascale Fung

This survey aims to provide researchers with a high-level insight into the similarities and differences of social bias studies in pre-trained models across NLP, CV, and VL.

Fairness

Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition

1 code implementation26 Jun 2023 Samuel Cahyawijaya, Holy Lovenia, Willy Chung, Rita Frieske, Zihan Liu, Pascale Fung

In this work, we analyze the transferability of emotion recognition across three different languages--English, Mandarin Chinese, and Cantonese; and 2 different age groups--adults and the elderly.

Data Augmentation Speech Emotion Recognition

InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning

1 code implementation23 May 2023 Samuel Cahyawijaya, Holy Lovenia, Tiezheng Yu, Willy Chung, Pascale Fung

Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting.

Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue

1 code implementation28 Feb 2023 Holy Lovenia, Samuel Cahyawijaya, Pascale Fung

The demand for multimodal dialogue systems has been rising in various domains, emphasizing the importance of interpreting multimodal inputs from conversational and situational contexts.

How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling

1 code implementation25 Oct 2022 Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, Huan Zhong, MingQian Zhong, Yuk-Yu Nancy Ip, Pascale Fung

Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA.

Language Modelling

What Did I Just Hear? Detecting Pornographic Sounds in Adult Videos Using Neural Networks

no code implementations8 Sep 2022 Holy Lovenia, Dessi Puji Lestari, Rita Frieske

Audio-based pornographic detection enables efficient adult content filtering without sacrificing performance by exploiting distinct spectral characteristics.

Speech Artifact Removal from EEG Recordings of Spoken Word Production with Tensor Decomposition

no code implementations1 Jun 2022 Holy Lovenia, Hiroki Tanaka, Sakriani Sakti, Ayu Purwarianti, Satoshi Nakamura

Research about brain activities involving spoken word production is considerably underdeveloped because of the undiscovered characteristics of speech artifacts, which contaminate electroencephalogram (EEG) signals and prevent the inspection of the underlying cognitive processes.

blind source separation EEG +2

Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension

no code implementations30 Mar 2022 Holy Lovenia, Bryan Wilie, Willy Chung, Min Zeng, Samuel Cahyawijaya, Su Dan, Pascale Fung

Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task.

Data Augmentation Machine Reading Comprehension +1

Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset

1 code implementation LREC 2022 Tiezheng Yu, Rita Frieske, Peng Xu, Samuel Cahyawijaya, Cheuk Tung Shadow Yiu, Holy Lovenia, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, Pascale Fung

We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation

2 code implementations LREC 2022 Holy Lovenia, Samuel Cahyawijaya, Genta Indra Winata, Peng Xu, Xu Yan, Zihan Liu, Rita Frieske, Tiezheng Yu, Wenliang Dai, Elham J. Barezi, Qifeng Chen, Xiaojuan Ma, Bertram E. Shi, Pascale Fung

ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.

Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

no code implementations14 Sep 2021 Samuel Cahyawijaya, Genta Indra Winata, Holy Lovenia, Bryan Wilie, Wenliang Dai, Etsuko Ishii, Pascale Fung

While the recent advances in deep neural networks (DNN) bring remarkable success, the computational cost also increases considerably.

Nora: The Well-Being Coach

no code implementations1 Jun 2021 Genta Indra Winata, Holy Lovenia, Etsuko Ishii, Farhad Bin Siddique, Yongsheng Yang, Pascale Fung

The current pandemic has forced people globally to remain in isolation and practice social distancing, which creates the need for a system to combat the resulting loneliness and negative emotions.

Natural Language Understanding

Cannot find the paper you are looking for? You can Submit a new open access paper.