2 code implementations • IJCNLP 2019 • Libo Qin, Wanxiang Che, Yangming Li, Haoyang Wen, Ting Liu
In our framework, we adopt a joint model with Stack-Propagation which can directly use the intent information as input for slot filling, thus to capture the intent semantic knowledge.
Ranked #2 on Intent Detection on SNIPS
1 code implementation • ICLR 2021 • Yangming Li, Lemao Liu, Shuming Shi
Experiments on synthetic datasets and real-world datasets show that our model is robust to unlabeled entity problem and surpasses prior baselines.
1 code implementation • IJCNLP 2019 • Libo Qin, Yijia Liu, Wanxiang Che, Haoyang Wen, Yangming Li, Ting Liu
Querying the knowledge base (KB) has long been a challenge in the end-to-end task-oriented dialogue system.
Ranked #6 on Task-Oriented Dialogue Systems on KVRET
1 code implementation • 25 Feb 2020 • Fangbo Qin, Shan Lin, Yangming Li, Randall A. Bly, Kris S. Moe, Blake Hannaford
Accurate and real-time surgical instrument segmentation is important in the endoscopic vision of robot-assisted surgery, and significant challenges are posed by frequent instrument-tissue contacts and continuous change of observation perspective.
1 code implementation • 10 Mar 2020 • Shan Lin, Fangbo Qin, Yangming Li, Randall A. Bly, Kris S. Moe, Blake Hannaford
For live image segmentation, we first translate the live images to fake-cadaveric images with LC-GAN and then perform segmentation on the fake-cadaveric images with models trained on the real cadaveric dataset.
1 code implementation • NAACL 2021 • Yangming Li, Lemao Liu, Kaisheng Yao
Prior methods to text segmentation are mostly at token level.
1 code implementation • EMNLP 2021 • Jing Qian, Yibin Liu, Lemao Liu, Yangming Li, Haiyun Jiang, Haisong Zhang, Shuming Shi
Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision.
1 code implementation • 29 Jun 2016 • Blake Hannaford, Danying Hu, Dianmu Zhang, Yangming Li
The "Selector" node of a BT tries alternative strategies (its children) and returns success only if all of its children return failure.
Robotics
1 code implementation • 9 Mar 2022 • Wenye Lin, Yangming Li, Lemao Liu, Shuming Shi, Hai-Tao Zheng
Specifically, we transfer the knowledge from a teacher model to its student model by locally matching their predictions on all sub-structures, instead of the whole output space.
no code implementations • 30 Apr 2020 • Libo Qin, Minheng Ni, Yue Zhang, Wanxiang Che, Yangming Li, Ting Liu
Spoken language understanding has been addressed as a supervised learning problem, where a set of training data is available for each domain.
no code implementations • ACL 2020 • Yangming Li, Kaisheng Yao, Libo Qin, Wanxiang Che, Xiaolong Li, Ting Liu
Data-driven approaches using neural networks have achieved promising performances in natural language generation (NLG).
no code implementations • ACL 2020 • Yangming Li, Han Li, Kaisheng Yao, Xiaolong Li
One great challenge in neural sequence labeling is the data sparsity problem for rare entity words and phrases.
no code implementations • 16 Aug 2020 • Libo Qin, Wanxiang Che, Yangming Li, Minheng Ni, Ting Liu
In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately.
no code implementations • ACL 2021 • Yangming Li, Kaisheng Yao
We apply the proposed architecture to improve the general NMT models (e. g., Transformer).
no code implementations • Findings (EMNLP) 2021 • Yangming Li, Lemao Liu, Shuming Shi
In this work, we present Lexical Unit Analysis (LUA), a framework for general sequence segmentation tasks.
no code implementations • 29 Dec 2020 • Yangming Li, Kaisheng Yao
To address this problem, we propose a novel framework, heterogeneous rendering machines (HRM), that interprets how neural generators render an input dialogue act (DA) into an utterance.
no code implementations • 31 Dec 2020 • Haisong Zhang, Lemao Liu, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Jianchen Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
no code implementations • ACL 2022 • Yangming Li, Lemao Liu, Shuming Shi
Negative sampling is highly effective in handling missing annotations for named entity recognition (NER).
no code implementations • ACL 2021 • Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
no code implementations • 28 Sep 2020 • Yangming Li, Kaisheng Yao
We apply the proposed framework to improve the general NMT models (e. g., Transformer).
no code implementations • 5 Dec 2021 • Yangming Li, Neeraja Konuthula, Ian M. Humphreys, Kris Moe, Blake Hannaford, Randall Bly
Purpose: This paper presents a scheme for generating virtual intraoperative CT scans in order to improve surgical completeness in Endoscopic Sinus Surgeries (ESS).
no code implementations • 5 Dec 2021 • Yangming Li, Randall Bly, Sarah Akkina, Rajeev C. Saxena, Ian Humphreys, Mark Whipple, Kris Moe, Blake Hannaford
Different with classical surgical skill assessment algorithms, the proposed method 1) utilizes the kinematic features in surgical instrument relative movements, instead of using specific surgical tasks or the statistics to assess skills in real-time; 2) provide informative feedback, instead of a summative scores; 3) has the ability to incrementally learn from new data, instead of depending on a fixed dataset.
no code implementations • 19 Apr 2023 • Yangming Li
3D dense reconstruction refers to the process of obtaining the complete shape and texture features of 3D objects from 2D planar images.
no code implementations • 9 Aug 2023 • Yangming Li, Mihaela van der Schaar
Our theoretical study also suggests that the cumulative error is closely related to the generation quality of DMs.
no code implementations • 25 Sep 2023 • Yangming Li, Boris van Breugel, Mihaela van der Schaar
In light of our theoretical studies, we introduce soft mixture denoising (SMD), an expressive and efficient model for backward denoising.
no code implementations • 6 Nov 2023 • Yangming Li
While current generative models have achieved promising performances in time-series synthesis, they either make strong assumptions on the data format (e. g., regularities) or rely on pre-processing approaches (e. g., interpolations) to simplify the raw data.
no code implementations • 3 Feb 2024 • Yangming Li, Max Ruiz Luyten, Mihaela van der Schaar
The essence of score-based generative models (SGM) is to optimize a score-based model towards the score function.