We then construct a comprehensive benchmark with a total of 16 implemented models to evaluate several information fusion strategies~(i. e. early, late, and intermediate fusion) with state-of-the-art LiDAR detection algorithms.
To ensure the generalization of PPT, we formulate similar classification tasks into a unified task form and pre-train soft prompts for this unified task.
In this work, we investigate the application of prompt-learning on fine-grained entity typing in fully supervised, few-shot and zero-shot scenarios.
In this work, we propose a domain generalization (DG) approach to learn on several labeled source domains and transfer knowledge to a target domain that is inaccessible in training.
1 code implementation • 20 Jun 2021 • Zhengyan Zhang, Yuxian Gu, Xu Han, Shengqi Chen, Chaojun Xiao, Zhenbo Sun, Yuan YAO, Fanchao Qi, Jian Guan, Pei Ke, Yanzheng Cai, Guoyang Zeng, Zhixing Tan, Zhiyuan Liu, Minlie Huang, Wentao Han, Yang Liu, Xiaoyan Zhu, Maosong Sun
We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference.
In contrast to the state-of-the-art methods, the proposed methods solve the estimation and testing problem at once with several merits: 1) an accurate sparsity estimation; 2) point estimates with shrinkage/soft-thresholding property; 3) credible intervals for uncertainty quantification; 4) an optimal multiple testing procedure that controls false discovery rate.
Strong correlations between explanatory variables are problematic for high-dimensional regularized regression methods.
no code implementations • 14 Jun 2021 • Xu Han, Zhengyan Zhang, Ning Ding, Yuxian Gu, Xiao Liu, Yuqi Huo, Jiezhong Qiu, Yuan YAO, Ao Zhang, Liang Zhang, Wentao Han, Minlie Huang, Qin Jin, Yanyan Lan, Yang Liu, Zhiyuan Liu, Zhiwu Lu, Xipeng Qiu, Ruihua Song, Jie Tang, Ji-Rong Wen, Jinhui Yuan, Wayne Xin Zhao, Jun Zhu
Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success and become a milestone in the field of artificial intelligence (AI).
To establish the bidirectional connections between OpenRE and relation hierarchy, we propose the task of open hierarchical relation extraction and present a novel OHRE framework for the task.
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning.
Finally, we show that KI can well support lifelong learning and knowledge transfer.
This indicates that PTR is a promising approach to take advantage of both human prior knowledge and PLMs for those complicated classification tasks.
Distantly supervised (DS) relation extraction (RE) has attracted much attention in the past few years as it can utilize large-scale auto-labeled data.
In this paper, we present Few-NERD, a large-scale human-annotated few-shot NER dataset with a hierarchy of 8 coarse-grained and 66 fine-grained entity types.
Ranked #1 on Named Entity Recognition on Few-NERD (SUP)
In this work, we propose visual distant supervision, a novel paradigm of visual relation learning, which can train scene graph models without any human-labeled data.
This paper estimates the break point for large-dimensional factor models with a single structural break in factor loadings at a common unknown date.
We then perform contrastive semi-supervised learning on both the retrieved unlabeled and original labeled instances to help PLMs capture crucial task-related semantic features.
In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possible to extract identity factors from the I frame with a pre-trained face recognition network.
Few-shot classification requires classifiers to adapt to new classes with only a few training instances.
Existing EAE methods either extract each event argument roles independently or sequentially, which cannot adequately model the joint probability distribution among event arguments and their roles.
1 code implementation • 1 Dec 2020 • Zhengyan Zhang, Xu Han, Hao Zhou, Pei Ke, Yuxian Gu, Deming Ye, Yujia Qin, Yusheng Su, Haozhe Ji, Jian Guan, Fanchao Qi, Xiaozhi Wang, Yanan Zheng, Guoyang Zeng, Huanqi Cao, Shengqi Chen, Daixuan Li, Zhenbo Sun, Zhiyuan Liu, Minlie Huang, Wentao Han, Jie Tang, Juanzi Li, Xiaoyan Zhu, Maosong Sun
However, applying GPT-3 to address Chinese NLP tasks is still challenging, as the training corpus of GPT-3 is primarily English, and the parameters are not publicly available.
Combining reinforcement learning (RL) and molecular dynamics (MD) simulations, we propose a machine-learning approach (RL$^\ddag$) to automatically unravel chemical reaction mechanisms.
Distant supervision (DS) has been widely used to generate auto-labeled data for sentence-level relation extraction (RE), which improves RE performance.
However, the cross entropy loss can not take the different importance of each class in an self-driving system into account.
In the up to two orders of magnitude compressed domain, we can explicitly infer the expression from the residual frames and possibly extract identity factors from the I frame with a pre-trained face recognition network.
We find that (i) while context is the main source to support the predictions, RE models also heavily rely on the information from entity mentions, most of which is type information, and (ii) existing datasets may leak shallow heuristics via entity mentions and thus contribute to the high performance on RE benchmarks.
Ranked #16 on Relation Extraction on TACRED
On the one hand, sparse KGs contain less information, which makes it difficult for the model to choose correct paths.
In this paper, we propose a novel framework named Coke to dynamically select contextual knowledge and embed knowledge context according to textual context for PLMs, which can avoid the effect of redundant and ambiguous knowledge in KGs that cannot match the input text.
They are therefore not designed for the registration of images with strong pathologies for example in the context of brain tumors, and traumatic brain injuries.
Thus, we propose a learning-based calibration method that focuses on multi-label semantic segmentation.
Continual relation learning aims to continually train a model on new data to learn incessantly emerging novel relations while avoiding catastrophically forgetting old relations.
Most existing datasets exhibit the following issues that limit further development of ED: (1) Data scarcity.
Deep learning is transforming many areas in science, and it has great potential in modeling molecular systems.
Relational facts are an important component of human knowledge, which are hidden in vast amounts of text.
In this work, we propose a challenging adversarial language game called Adversarial Taboo as an example, in which an attacker and a defender compete around a target word.
Open relation extraction (OpenRE) aims to extract relational facts from the open-domain corpus.
Existing event extraction methods classify each argument role independently, ignoring the conceptual correlations between different argument roles.
Specifically, we first illustrate that using a deep convolutional neural network to predict atlas probabilities can better distinguish correct atlas labels from incorrect ones than relying on image intensity difference as is typical in JLF.
We present FewRel 2. 0, a more challenging task to investigate two aspects of few-shot relation classification models: (1) Can they adapt to a new domain with only a handful of instances?
OpenNRE is an open-source and extensible toolkit that provides a unified framework to implement neural models for relation extraction (RE).
Multi-hop knowledge graph (KG) reasoning is an effective and explainable method for predicting the target entity via reasoning paths in query answering (QA) task.
Ranked #3 on Link Prediction on NELL-995
To address new relations with few-shot instances, we propose a novel bootstrapping approach, Neural Snowball, to learn new relations by transferring semantic knowledge about existing relations.
Recently, optical neural networks (ONNs) integrated in photonic chips has received extensive attention because they are expected to implement the same pattern recognition tasks in the electronic platforms with high efficiency and low power consumption.
Fact verification (FV) is a challenging task which requires to retrieve relevant evidence from plain text and use the evidence to verify given claims.
Ranked #2 on Fact Verification on FEVER
We introduce a conceptually simple and effective method to quantify the similarity between relations in knowledge bases.
Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs.
Ranked #38 on Relation Extraction on DocRED
Modern weakly supervised methods for event detection (ED) avoid time-consuming human annotation and achieve promising results by learning from auto-labeled data.
Neural language representation models such as BERT pre-trained on large-scale corpora can well capture rich semantic patterns from plain text, and be fine-tuned to consistently improve the performance of various NLP tasks.
Ranked #1 on Entity Linking on FIGER
Experiments on 3D brain MRI data show that by selecting a good initial atlas set MAS with VoteNet significantly outperforms a number of other label fusion strategies as well as a direct DL segmentation approach.
In contrast to existing approaches, our framework combines two registration methods: an affine registration and a vector momentum-parameterized stationary velocity field (vSVF) model.
Ranked #2 on Image Registration on Osteoarthritis Initiative
Knowledge representation learning (KRL) aims to represent entities and relations in knowledge graph in low-dimensional semantic space, which have been widely used in massive knowledge-driven tasks.
Based on the low-rank property and an over-estimation of the core tensor, this joint estimation problem is solved by promoting (group) sparsity of the over-estimated core tensor.
To demonstrate the effectiveness of DIAG-NRE, we apply it to two real-world datasets and present both significant and interpretable improvements over state-of-the-art methods.
We release an open toolkit for knowledge embedding (OpenKE), which provides a unified framework and various fundamental models to embed knowledge graphs into a continuous low-dimensional space.
The relation of each sentence is first recognized by distant supervision methods, and then filtered by crowdworkers.
In this paper, we develop a low than character feature embedding called radical embedding, and apply it on LSTM model for sentence segmentation of pre modern Chinese texts.
In this paper, we aim to incorporate the hierarchical information of relations for distantly supervised relation extraction and propose a novel hierarchical attention scheme.
To address these issues, we propose an adversarial multi-lingual neural relation extraction (AMNRE) model, which builds both consistent and individual representations for each sentence to consider the consistency and diversity among languages.
As shown in the experiments on a large-scale benchmark dataset in relation extraction, our denoising method can effectively filter out noisy instances and achieve significant improvements as compared with the state-of-the-art models.
Locating the center of convex objects is important in both image processing and unsupervised machine learning/data clustering fields.
Extracting the brain from images with strong pathologies, for example, the presence of a tumor or of a traumatic brain injury, is challenging.
Registration involving one or more images containing pathologies is challenging, as standard image similarity measures and spatial transforms cannot account for common changes due to pathologies.
Joint representation learning of text and knowledge within a unified semantic space enables us to perform knowledge graph completion more accurately.
Texture plays an important role in many image analysis applications.