In this paper, we propose a privacy-preserving medical relation extraction model based on federated learning, which enables training a central model with no single piece of private local data being shared or exchanged.
Inspired by this behavior of humans, we propose a method to let the machine imagine a scene during reading narrative for better comprehension.
Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base.
However, to figure out whether PLMs can be reliable knowledge sources and used as alternative knowledge bases (KBs), we need to further explore some critical features of PLMs.
no code implementations • 14 Oct 2021 • Hao Jiang, Ke Zhan, Jianwei Qu, Yongkang Wu, Zhaoye Fei, Xinyu Zhang, Lei Chen, Zhicheng Dou, Xipeng Qiu, Zikai Guo, Ruofei Lai, Jiawen Wu, Enrui Hu, Yinxia Zhang, Yantao Jia, Fan Yu, Zhao Cao
To increase the number of activated experts without an increase in computational cost, we propose SAM (Switch and Mixture) routing, an efficient hierarchical routing mechanism that activates multiple experts in a same device (GPU).
Finally, supervisory signal in rear compressor is computed based on condition probability and thus can control sample dynamic and further enhance the model performance.
Currently, the most popular method for open-domain Question Answering (QA) adopts "Retriever and Reader" pipeline, where the retriever extracts a list of candidate documents from a large set of documents followed by a ranker to rank the most relevant documents and the reader extracts answer from the candidates.
Then we propose a dual encoder-decoder structure to model the generation of responses in both positive and negative side based on the changes of the user's emotion status in the conversation.
The key of implementing ZSL is to leverage the prior knowledge of classes which builds the semantic relationship between classes and enables the transfer of the learned models (e. g., features) from training classes (i. e., seen classes) to unseen classes.
Although the self-supervised pre-training of transformer models has resulted in the revolutionizing of natural language processing (NLP) applications and the achievement of state-of-the-art results with regard to various benchmarks, this process is still vulnerable to small and imperceptible permutations originating from legitimate inputs.
Event detection (ED) aims to identify and classify event triggers in texts, which is a crucial subtask of event extraction (EE).
Knowledge graphs (KGs) consisting of triples are always incomplete, so it's important to do Knowledge Graph Completion (KGC) by predicting missing triples.
Long-tailed relation classification is a challenging problem as the head classes may dominate the training phase, thereby leading to the deterioration of the tail performance.
However, the side information of classes used now is limited to text descriptions and attribute annotations, which are in short of semantics of the classes.
In this work, we first introduce the hierarchical dependency and horizontal commonality between the two levels, and then propose an entity-enhanced dual tagging framework that enables the triple extraction (TE) task to utilize such interactions with self-learned entity features through an auxiliary entity extraction (EE) task, without breaking the joint decoding of relational triples.
Traditional approaches to the task of ACE event detection primarily regard multiple events in one sentence as independent ones and recognize them separately by using sentence-level information.
Fine-grained entity typing aims to assign entity mentions in the free text with types arranged in a hierarchical structure.
Knowledge graph embedding aims to embed entities and relations of knowledge graphs into low-dimensional vector spaces.
Ranked #1 on Link Prediction on WN18 (filtered)
Knowledge graph embedding aims to represent entities and relations in a large-scale knowledge graph as elements in a continuous vector space.