no code implementations • ACL (RepL4NLP) 2021 • Zihan Liu, Genta Indra Winata, Andrea Madotto, Pascale Fung
Recently, fine-tuning pre-trained language models (e. g., multilingual BERT) to downstream cross-lingual tasks has shown promising results.
1 code implementation • ACL (dialdoc) 2021 • Yan Xu, Etsuko Ishii, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, Pascale Fung
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users’ needs, which.
1 code implementation • 27 Feb 2024 • Shuangrui Ding, Zihan Liu, Xiaoyi Dong, Pan Zhang, Rui Qian, Conghui He, Dahua Lin, Jiaqi Wang
We present SongComposer, an innovative LLM designed for song composition.
no code implementations • 25 Feb 2024 • Zihan Liu, Han Li, Anfan Chen, Renwen Zhang, Yi-chieh Lee
We find Chinese participants tended to view CAs hedonically, perceived voice-based and physically embodied CAs as warmer and more competent, and generally expressed positive emotions.
no code implementations • 24 Feb 2024 • Chenrui Duan, Zelin Zang, Yongjie Xu, Hang He, Zihan Liu, Zijia Song, Ju-Sheng Zheng, Stan Z. Li
Metagenomic data, comprising mixed multi-species genomes, are prevalent in diverse environments like oceans and soils, significantly impacting human health and ecological functions.
no code implementations • 18 Jan 2024 • Zihan Liu, Wei Ping, Rajarshi Roy, Peng Xu, Chankyu Lee, Mohammad Shoeybi, Bryan Catanzaro
In this work, we introduce ChatQA, a family of conversational question answering (QA) models that obtain GPT-4 level accuracies.
no code implementations • 22 Oct 2023 • MengNan Qi, Yufan Huang, Maoquan Wang, Yongqiang Yao, Zihan Liu, Bin Gu, Colin Clement, Neel Sundaresan
In this paper we introduce a new metrics for programming language translation and these metrics address these basic syntax errors.
no code implementations • 14 Oct 2023 • Yufei Huang, Siyuan Li, Jin Su, Lirong Wu, Odin Zhang, Haitao Lin, Jingqi Qi, Zihan Liu, Zhangyang Gao, Yuyang Liu, Jiangbin Zheng, Stan. ZQ. Li
To study this problem, we identify a Protein 3D Graph Structure Learning Problem for Robust Protein Property Prediction (PGSL-RP3), collect benchmark datasets, and present a protein Structure embedding Alignment Optimization framework (SAO) to mitigate the problem of structure embedding bias between the predicted and experimental protein structures.
1 code implementation • 4 Oct 2023 • Zihan Liu, Ge Wang, Jiaqi Wang, Jiangbin Zheng, Stan Z. Li
Peptides are formed by the dehydration condensation of multiple amino acids.
no code implementations • 4 Oct 2023 • Peng Xu, Wei Ping, Xianchao Wu, Lawrence McAfee, Chen Zhu, Zihan Liu, Sandeep Subramanian, Evelina Bakhturina, Mohammad Shoeybi, Bryan Catanzaro
Perhaps surprisingly, we find that LLM with 4K context window using simple retrieval-augmentation at generation can achieve comparable performance to finetuned LLM with 16K context window via positional interpolation on long context tasks, while taking much less computation.
no code implementations • 25 Sep 2023 • Zihan Liu, Zewei Sun, Shanbo Cheng, ShuJian Huang, Mingxuan Wang
Document-level Neural Machine Translation (DocNMT) has been proven crucial for handling discourse phenomena by introducing document-level context information.
1 code implementation • 17 Jul 2023 • Zihan Liu, Jiaqi Wang, Yun Luo, Shuang Zhao, Wenbin Li, Stan Z. Li
In recent years, there has been an explosion of research on the application of deep learning to the prediction of various peptide properties, due to the significant development and market potential of peptides.
1 code implementation • 26 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.
no code implementations • 27 May 2023 • Yangjie Zhou, Yaoxu Song, Jingwen Leng, Zihan Liu, Weihao Cui, Zhendong Zhang, Cong Guo, Quan Chen, Li Li, Minyi Guo
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features.
1 code implementation • 13 Apr 2023 • Boxin Wang, Wei Ping, Peng Xu, Lawrence McAfee, Zihan Liu, Mohammad Shoeybi, Yi Dong, Oleksii Kuchaiev, Bo Li, Chaowei Xiao, Anima Anandkumar, Bryan Catanzaro
Thus, it is still an open question: shall we pretrain large autoregressive LMs with retrieval?
1 code implementation • 29 Mar 2023 • Zihan Liu, Yun Luo, Lirong Wu, Zicheng Liu, Stan Z. Li
It has become cognitive inertia to employ cross-entropy loss function in classification related tasks.
no code implementations • 9 Feb 2023 • Zhuolin Yang, Wei Ping, Zihan Liu, Vijay Korthikanti, Weili Nie, De-An Huang, Linxi Fan, Zhiding Yu, Shiyi Lan, Bo Li, Ming-Yu Liu, Yuke Zhu, Mohammad Shoeybi, Bryan Catanzaro, Chaowei Xiao, Anima Anandkumar
Augmenting pretrained language models (LMs) with a vision encoder (e. g., Flamingo) has obtained the state-of-the-art results in image-to-text generation.
1 code implementation • 8 Feb 2023 • Yun Luo, Zihan Liu, Stan Z. Li, Yue Zhang
(Dis)agreement detection aims to identify the authors' attitudes or positions (\textit{{agree, disagree, neutral}}) towards a specific text.
1 code implementation • 3 Dec 2022 • Ziwei Ji, Zihan Liu, Nayeon Lee, Tiezheng Yu, Bryan Wilie, Min Zeng, Pascale Fung
Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses.
no code implementations • 7 Nov 2022 • Zihan Liu, Hanyi Wang, Shilin Wang
As ultra-realistic face forgery techniques emerge, deepfake detection has attracted increasing attention due to security concerns.
1 code implementation • 14 Oct 2022 • Wenliang Dai, Zihan Liu, Ziwei Ji, Dan Su, Pascale Fung
Large-scale vision-language pre-trained (VLP) models are prone to hallucinate non-existent visual objects when generating text based on visual information.
1 code implementation • 30 Aug 2022 • Cong Guo, Chen Zhang, Jingwen Leng, Zihan Liu, Fan Yang, Yunxin Liu, Minyi Guo, Yuhao Zhu
In this work, we propose a fixed-length adaptive numerical data type called ANT to achieve low-bit quantization with tiny hardware overheads.
no code implementations • 26 Aug 2022 • Zihan Liu, Ge Wang, Yun Luo, Stan Z. Li
To address this issue, we propose a novel surrogate model with multi-level propagation that preserves the node dissimilarity information.
no code implementations • 19 Aug 2022 • Zihan Liu
Third, we propose to leverage different levels of domain-related corpora and additional masking of data in the pre-training for the cross-domain adaptation, and discover that more challenging pre-training can better address the domain discrepancy issue in the task knowledge transfer.
1 code implementation • COLING 2022 • Yun Luo, Zihan Liu, Yuefeng Shi, Stan Z Li, Yue Zhang
Meanwhile, ablation studies prove the significance of each module in our model.
1 code implementation • COLING 2022 • Yun Luo, Fang Guo, Zihan Liu, Yue Zhang
Cross-domain sentiment analysis aims to predict the sentiment of texts in the target domain using the model trained on the source domain to cope with the scarcity of labeled data.
1 code implementation • 7 Aug 2022 • Zihan Liu, Yun Luo, Lirong Wu, Siyuan Li, Zicheng Liu, Stan Z. Li
These errors arise from rough gradient usage due to the discreteness of the graph structure and from the unreliability in the meta-gradient on the graph structure.
1 code implementation • 28 Jun 2022 • Junchen Ye, Zihan Liu, Bowen Du, Leilei Sun, Weimiao Li, Yanjie Fu, Hui Xiong
To equip the graph neural network with a flexible and practical graph structure, in this paper, we investigate how to model the evolutionary and multi-scale interactions of time series.
1 code implementation • BioNLP (ACL) 2022 • Samuel Cahyawijaya, Tiezheng Yu, Zihan Liu, Tiffany T. W. Mak, Xiaopu Zhou, Nancy Y. Ip, Pascale Fung
We apply SNP2Vec to perform long-sequence genomics modeling, and we evaluate the effectiveness of our approach on predicting Alzheimer's disease risk in a Chinese cohort.
1 code implementation • Findings (ACL) 2022 • Zihan Liu, Mostofa Patwary, Ryan Prenger, Shrimai Prabhumoye, Wei Ping, Mohammad Shoeybi, Bryan Catanzaro
We propose a multi-stage prompting approach to generate knowledgeable responses from a single pretrained LM.
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.
no code implementations • 1 Dec 2021 • Zihan Liu, Feijun Jiang, Yuxiang Hu, Chen Shi, Pascale Fung
Named entity recognition (NER) models generally perform poorly when large training datasets are unavailable for low-resource domains.
1 code implementation • 30 Nov 2021 • Siyuan Li, Zicheng Liu, Zedong Wang, Di wu, Zihan Liu, Stan Z. Li
Accordingly, we propose $\eta$-balanced mixup loss for complementary learning of the two sub-objectives.
Ranked #7 on Image Classification on Places205
no code implementations • 20 Oct 2021 • Zihan Liu, Yun Luo, Zelin Zang, Stan Z. Li
Gray-box graph attacks aim at disrupting the performance of the victim model by using inconspicuous attacks with limited knowledge of the victim model.
1 code implementation • EMNLP 2021 • Zeyu Li, Yilong Qin, Zihan Liu, Wei Wang
We study Comparative Preference Classification (CPC) which aims at predicting whether a preference comparison exists between two entities in a given sentence and, if so, which entity is preferred over the other.
1 code implementation • EMNLP 2021 • Tiezheng Yu, Wenliang Dai, Zihan Liu, Pascale Fung
Multimodal abstractive summarization (MAS) models that summarize videos (vision modality) and their corresponding transcripts (text modality) are able to extract the essential information from massive multimodal data on the Internet.
1 code implementation • 7 Jun 2021 • Etsuko Ishii, Yan Xu, Genta Indra Winata, Zhaojiang Lin, Andrea Madotto, Zihan Liu, Peng Xu, Pascale Fung
Information-seeking dialogue systems, including knowledge identification and response generation, aim to respond to users with fluent, coherent, and informative responses based on users' needs, which.
1 code implementation • ACL (RepL4NLP) 2021 • Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung
Experimental results illustrate that our model can significantly outperform existing strong baselines in cross-lingual and cross-domain settings, and our model can also achieve a good generalization ability on target languages of target domains.
1 code implementation • dialdoc (ACL) 2022 • Yan Xu, Etsuko Ishii, Samuel Cahyawijaya, Zihan Liu, Genta Indra Winata, Andrea Madotto, Dan Su, Pascale Fung
This paper proposes KnowExpert, a framework to bypass the explicit retrieval process and inject knowledge into the pre-trained language models with lightweight adapters and adapt to the knowledge-grounded dialogue task.
no code implementations • Findings (ACL) 2021 • Zihan Liu, Genta Indra Winata, Pascale Fung
The data scarcity in low-resource languages has become a bottleneck to building robust neural machine translation systems.
no code implementations • NAACL (CALCS) 2021 • Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Pascale Fung
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks.
2 code implementations • 24 Mar 2021 • Zicheng Liu, Siyuan Li, Di wu, Zihan Liu, ZhiYuan Chen, Lirong Wu, Stan Z. Li
Specifically, AutoMix reformulates the mixup classification into two sub-tasks (i. e., mixed sample generation and mixup classification) with corresponding sub-networks and solves them in a bi-level optimization framework.
Ranked #8 on Image Classification on Places205
1 code implementation • NAACL 2021 • Tiezheng Yu, Zihan Liu, Pascale Fung
State-of-the-art abstractive summarization models generally rely on extensive labeled data, which lowers their generalization ability on domains where such data are not available.
1 code implementation • NAACL 2021 • Wenliang Dai, Samuel Cahyawijaya, Zihan Liu, Pascale Fung
Existing works on multimodal affective computing tasks, such as emotion recognition, generally adopt a two-phase pipeline, first extracting feature representations for each single modality with hand-crafted algorithms and then performing end-to-end learning with the extracted features.
5 code implementations • 8 Dec 2020 • Zihan Liu, Yan Xu, Tiezheng Yu, Wenliang Dai, Ziwei Ji, Samuel Cahyawijaya, Andrea Madotto, Pascale Fung
Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains.
1 code implementation • SEMEVAL 2020 • Wenliang Dai, Tiezheng Yu, Zihan Liu, Pascale Fung
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task.
1 code implementation • EMNLP 2020 • Zihan Liu, Genta Indra Winata, Peng Xu, Zhaojiang Lin, Pascale Fung
Despite the promising results of current cross-lingual models for spoken language understanding systems, they still suffer from imperfect cross-lingual representation alignments between the source and target languages, which makes the performance sub-optimal.
1 code implementation • Findings of the Association for Computational Linguistics 2020 • Andrea Madotto, Samuel Cahyawijaya, Genta Indra Winata, Yan Xu, Zihan Liu, Zhaojiang Lin, Pascale Fung
In this paper, we propose a method to embed the KB, of any size, directly into the model parameters.
1 code implementation • Asian Chapter of the Association for Computational Linguistics 2020 • Wenliang Dai, Zihan Liu, Tiezheng Yu, Pascale Fung
Despite the recent achievements made in the multi-modal emotion recognition task, two problems still exist and have not been well investigated: 1) the relationship between different emotion categories are not utilized, which leads to sub-optimal performance; and 2) current models fail to cope well with low-resource emotions, especially for unseen emotions.
no code implementations • 21 Aug 2020 • Peng Xu, Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Pascale Fung
Most emotion recognition methods tackle the emotion understanding task by considering individual emotion independently while ignoring their fuzziness nature and the interconnections among them.
Ranked #3 on Emotion Classification on SemEval 2018 Task 1E-c
no code implementations • 14 Aug 2020 • Andrea Madotto, Zihan Liu, Zhaojiang Lin, Pascale Fung
In this paper, we evaluate the priming few-shot ability of language models in the NLU, DST, DP and NLG tasks.
1 code implementation • ACL 2020 • Genta Indra Winata, Samuel Cahyawijaya, Zhaojiang Lin, Zihan Liu, Peng Xu, Pascale Fung
An increasing number of people in the world today speak a mixed-language as a result of being multilingual.
no code implementations • 29 Apr 2020 • Zihan Liu, Genta Indra Winata, Andrea Madotto, Pascale Fung
Recently, fine-tuning pre-trained language models (e. g., multilingual BERT) to downstream cross-lingual tasks has shown promising results.
1 code implementation • 28 Apr 2020 • Wenliang Dai, Tiezheng Yu, Zihan Liu, Pascale Fung
Nowadays, offensive content in social media has become a serious problem, and automatically detecting offensive language is an essential task.
1 code implementation • ACL 2020 • Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung
In this paper, we propose a Coarse-to-fine approach (Coach) for cross-domain slot filling.
Cross-Domain Named Entity Recognition named-entity-recognition +3
2 code implementations • 28 Mar 2020 • Zhaojiang Lin, Genta Indra Winata, Peng Xu, Zihan Liu, Pascale Fung
Despite the great promise of Transformers in many sequence modeling tasks (e. g., machine translation), their deterministic nature hinders them from generalizing to high entropy tasks such as dialogue response generation.
1 code implementation • EMNLP (NLP4ConvAI) 2021 • Zhaojiang Lin, Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Yejin Bang, Etsuko Ishii, Pascale Fung
Experimental results show that the multilingual trained models outperform the translation-pipeline and that they are on par with the monolingual models, with the advantage of having a single model across multiple languages.
1 code implementation • 4 Mar 2020 • Genta Indra Winata, Samuel Cahyawijaya, Zihan Liu, Zhaojiang Lin, Andrea Madotto, Peng Xu, Pascale Fung
The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system.
Audio and Speech Processing Sound
1 code implementation • WS 2020 • Zihan Liu, Genta Indra Winata, Pascale Fung
Existing models for cross-domain named entity recognition (NER) rely on numerous unlabeled corpus or labeled NER training data in target domains.
Ranked #1 on Cross-Domain Named Entity Recognition on CoNLL04
no code implementations • 30 Jan 2020 • Zihan Liu, Genta Indra Winata, Samuel Cahyawijaya, Andrea Madotto, Zhaojiang Lin, Pascale Fung
To verify this hypothesis, we investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages.
1 code implementation • 3 Dec 2019 • Zihan Liu, Lubin Meng, Xiao Zhang, Weili Fang, Dongrui Wu
Multiple convolutional neural network (CNN) classifiers have been proposed for electroencephalogram (EEG) based brain-computer interfaces (BCIs).
1 code implementation • 21 Nov 2019 • Zihan Liu, Genta Indra Winata, Zhaojiang Lin, Peng Xu, Pascale Fung
Recently, data-driven task-oriented dialogue systems have achieved promising performance in English.
no code implementations • IJCNLP 2019 • Zihan Liu, Jamin Shin, Yan Xu, Genta Indra Winata, Peng Xu, Andrea Madotto, Pascale Fung
Despite the surging demands for multilingual task-oriented dialog systems (e. g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios.
no code implementations • WS 2019 • Dan Su, Yan Xu, Genta Indra Winata, Peng Xu, Hyeondey Kim, Zihan Liu, Pascale Fung
With a large number of datasets being released and new techniques being proposed, Question answering (QA) systems have witnessed great breakthroughs in reading comprehension (RC)tasks.
no code implementations • 30 Oct 2019 • Genta Indra Winata, Samuel Cahyawijaya, Zhaojiang Lin, Zihan Liu, Pascale Fung
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices.
1 code implementation • IJCNLP 2019 • Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu, Pascale Fung
In countries that speak multiple main languages, mixing up different languages within a conversation is commonly called code-switching.
no code implementations • 22 Aug 2019 • Zihan Liu, Bo Huang, Yuqi Cui, Yifan Xu, Bo Zhang, Lixia Zhu, Yang Wang, Lei Jin, Dongrui Wu
Accurate classification of embryo early development stages can provide embryologists valuable information for assessing the embryo quality, and hence is critical to the success of IVF.
no code implementations • WS 2019 • Zihan Liu, Yan Xu, Genta Indra Winata, Pascale Fung
This paper describes CAiRE's submission to the unsupervised machine translation track of the WMT'19 news shared task from German to Czech.
2 code implementations • 28 Jul 2019 • Zhaojiang Lin, Peng Xu, Genta Indra Winata, Farhad Bin Siddique, Zihan Liu, Jamin Shin, Pascale Fung
In this paper, we present an end-to-end empathetic conversation agent CAiRE.
1 code implementation • SEMEVAL 2019 • Nayeon Lee, Zihan Liu, Pascale Fung
This paper describes our system that has been submitted to SemEval-2019 Task 4: Hyperpartisan News Detection.