no code implementations • NAACL (ACL) 2022 • Xue Zhao, Dayiheng Liu, Junwei Ding, Liang Yao, Mahone Yan, Huibo Wang, Wenqing Yao
Product Listing Ads (PLAs) are primary online advertisements merchants pay to attract more customers.
no code implementations • CL (ACL) 2022 • Yu Wan, Baosong Yang, Derek Fai Wong, Lidia Sam Chao, Liang Yao, Haibo Zhang, Boxing Chen
After empirically investigating the rationale behind this, we summarize two challenges in NMT for STs associated with translation error types above, respectively: (1) the imbalanced length distribution in training set intensifies model inference calibration over STs, leading to more over-translation cases on STs; and (2) the lack of contextual information forces NMT to have higher data uncertainty on short sentences, and thus NMT model is troubled by considerable mistranslation errors.
1 code implementation • Findings (NAACL) 2022 • Huan Lin, Baosong Yang, Liang Yao, Dayiheng Liu, Haibo Zhang, Jun Xie, Min Zhang, Jinsong Su
Diverse NMT aims at generating multiple diverse yet faithful translations given a source sentence.
1 code implementation • Findings (ACL) 2022 • Xingzhang Ren, Baosong Yang, Dayiheng Liu, Haibo Zhang, Xiaoyu Lv, Liang Yao, Jun Xie
Recognizing the language of ambiguous texts has become a main challenge in language identification (LID).
1 code implementation • 13 Mar 2024 • Liang Yao
Prompting methods play a crucial role in enhancing the capabilities of pre-trained large language models (LLMs).
1 code implementation • 26 Aug 2023 • Liang Yao, Jiazhen Peng, Chengsheng Mao, Yuan Luo
Knowledge graphs play a vital role in numerous artificial intelligence tasks, yet they frequently face the issue of incompleteness.
1 code implementation • 20 Feb 2023 • Liang Yao, Jiazhen Peng, Shenggong Ji, Qiang Liu, Hongyun Cai, Feng He, Xu Cheng
Friend recall is an important way to improve Daily Active Users (DAU) in online games.
1 code implementation • 7 May 2022 • Chengsheng Mao, Liang Yao, Yuan Luo
However, few have explored BERT on disease-specific medical domain tasks such as AKI early prediction.
no code implementations • 13 Jan 2022 • Yifeng Chen, Wenqing Chu, Fangfang Wang, Ying Tai, Ran Yi, Zhenye Gan, Liang Yao, Chengjie Wang, Xi Li
Recently, there is growing attention on one-stage panoptic segmentation methods which aim to segment instances and stuff jointly within a fully convolutional pipeline efficiently.
1 code implementation • ACL 2021 • Huan Lin, Liang Yao, Baosong Yang, Dayiheng Liu, Haibo Zhang, Weihua Luo, Degen Huang, Jinsong Su
Furthermore, we contribute the first Chinese-English parallel corpus annotated with user behavior called UDT-Corpus.
no code implementations • COLING 2020 • Liang Yao, Baosong Yang, Haibo Zhang, Boxing Chen, Weihua Luo
Query translation (QT) serves as a critical factor in successful cross-lingual information retrieval (CLIR).
no code implementations • 26 Oct 2020 • Tianchi Bi, Liang Yao, Baosong Yang, Haibo Zhang, Weihua Luo, Boxing Chen
Query translation (QT) is a key component in cross-lingual information retrieval system (CLIR).
no code implementations • 26 Oct 2020 • Liang Yao, Baosong Yang, Haibo Zhang, Weihua Luo, Boxing Chen
As a crucial role in cross-language information retrieval (CLIR), query translation has three main challenges: 1) the adequacy of translation; 2) the lack of in-domain parallel training data; and 3) the requisite of low latency.
1 code implementation • 12 Oct 2020 • Chengsheng Mao, Liang Yao, Yuan Luo
Graph Neural Network (GNN) aggregates the neighborhood of each node into the node embedding and shows its powerful capability for graph representation learning.
3 code implementations • 7 Sep 2019 • Liang Yao, Chengsheng Mao, Yuan Luo
Knowledge graphs are important resources for many artificial intelligence tasks but often suffer from incompleteness.
Ranked #5 on Link Prediction on UMLS
no code implementations • 2 Apr 2019 • Prakash Adekkanattu, Guoqian Jiang, Yuan Luo, Paul R. Kingsbury, Zhen-Xing Xu, Luke V. Rasmussen, Jennifer A. Pacheco, Richard C. Kiefer, Daniel J. Stone, Pascal S. Brandt, Liang Yao, Yizhen Zhong, Yu Deng, Fei Wang, Jessica S. Ancker, Thomas R. Campion, Jyotishman Pathak
While the NLP system showed high precision and recall measurements for four target concepts (aortic valve regurgitation, left atrium size at end systole, mitral valve regurgitation, tricuspid valve regurgitation) across all sites, we found moderate or poor results for the remaining concepts and the NLP system performance varied between individual sites.
1 code implementation • 31 Mar 2019 • Chengsheng Mao, Liang Yao, Yuan Luo
However, most of the existing approaches for image representation ignore the relations between images and consider each input image independently.
1 code implementation • 31 Mar 2019 • Chengsheng Mao, Liang Yao, Yuan Luo
In this study, we construct a graph to associate 4 types of medical entities, i. e., patients, encounters, lab tests, and medications, and applied a graph neural network to learn node embeddings for medication recommendation and lab test imputation.
no code implementations • 7 Nov 2018 • Yikuan Li, Liang Yao, Chengsheng Mao, Anand Srivastava, Xiaoqian Jiang, Yuan Luo
We developed data-driven prediction models to estimate the risk of new AKI onset.
no code implementations • WS 2018 • Yongchao Deng, Shanbo Cheng, Jun Lu, Kai Song, Jingang Wang, Shenglan Wu, Liang Yao, Guchun Zhang, Haibo Zhang, Pei Zhang, Changfeng Zhu, Boxing Chen
We participated in 5 translation directions including English ↔ Russian, English ↔ Turkish in both directions and English → Chinese.
no code implementations • 20 Sep 2018 • Chengsheng Mao, Liang Yao, Yuan Luo
In this paper, we recognize that novel classes should be different from each other, and propose distribution networks for open set learning that can model different novel classes based on probability distributions.
1 code implementation • 20 Sep 2018 • Chengsheng Mao, Yiheng Pan, Zexian Zeng, Liang Yao, Yuan Luo
However, most of the previous deep neural network classifiers were based on deterministic architectures which are usually very noise-sensitive and are likely to aggravate the overfitting issue.
9 code implementations • 15 Sep 2018 • Liang Yao, Chengsheng Mao, Yuan Luo
We build a single text graph for a corpus based on word co-occurrence and document word relations, then learn a Text Graph Convolutional Network (Text GCN) for the corpus.
Ranked #6 on Text Classification on Ohsumed
1 code implementation • 17 Jul 2018 • Himanshu Sharma, Chengsheng Mao, Yizhen Zhang, Haleh Vatani, Liang Yao, Yizhen Zhong, Luke Rasmussen, Guoqian Jiang, Jyotishman Pathak, Yuan Luo
Our system facilitates portable phenotyping of obesity and its 15 comorbidities based on the unstructured patient discharge summaries, while achieving a performance that often ranked among the top 10 of the challenge participants.
no code implementations • 17 Jul 2018 • Liang Yao, Chengsheng Mao, Yuan Luo
Clinical text classification is an important problem in medical natural language processing.
Ranked #2 on Clinical Note Phenotyping on I2B2 2008: Obesity
no code implementations • WS 2016 • Yu Hong, Liang Yao, Mengyi Liu, Tongtao Zhang, Wenxuan Zhou, Jianmin Yao, Heng Ji
We present a novel method of comparable corpora construction.