Search Results for author:
Found 17 papers, 7 papers with code
Learn and Review: Enhancing Continual Named Entity Recognition via Reviewing Synthetic Samples
However, the existing method depends on the relevance between tasks and is prone to inter-type confusion. In this paper, we propose a novel two-stage framework Learn-and-Review (L&R) for continual NER under the type-incremental setting to alleviate the above issues. Specifically, for the learning stage, we distill the old knowledge from teacher to a student on the current dataset.
Continual Named Entity Recognition
named-entity-recognition
+2
Dynamic Multistep Reasoning based on Video Scene Graph for Video Question Answering
Then, it performs multistep reasoning for better answer decision between the representations of the question and the video, and dynamically integrate the reasoning results.
BDKG at MEDIQA 2021: System Report for the Radiology Report Summarization Task
This paper presents our winning system at the Radiology Report Summarization track of the MEDIQA 2021 shared task.
EmRel: Joint Representation of Entities and Embedded Relations for Multi-triple Extraction
Multi-triple extraction is a challenging task due to the existence of informative inter-triple correlations, and consequently rich interactions across the constituent entities and relations. While existing works only explore entity representations, we propose to explicitly introduce relation representation, jointly represent it with entities, and novelly align them to identify valid triples. We perform comprehensive experiments on document-level relation extraction and joint entity and relation extraction along with ablations to demonstrate the advantage of the proposed method.
Document-level Relation Extraction
Joint Entity and Relation Extraction
+2
SDSAT: Accelerating LLM Inference through Speculative Decoding with Semantic Adaptive Tokens
The core strategies involve: 1) Fine-tune the model by incorporating semantic adaptive tokens that possess flexible decoding capabilities without changing its structure, allowing them to generate high-quality draft tokens.
Improving Video Retrieval by Adaptive Margin
While most video retrieval methods overlook that phenomenon, we propose an adaptive margin changed with the distance between positive and negative pairs to solve the aforementioned issue.
Mixture of Experts for Biomedical Question Answering
In this paper, in order to alleviate the parameter competition problem, we propose a Mixture-of-Expert (MoE) based question answering method called MoEBQA that decouples the computation for different types of questions by sparse routing.
Complex Evolutional Pattern Learning for Temporal Knowledge Graph Reasoning
Furthermore, these models are all trained offline, which cannot well adapt to the changes of evolutional patterns from then on.
Building Chinese Biomedical Language Models via Multi-Level Text Discrimination
In this work we introduce eHealth, a Chinese biomedical PLM built from scratch with a new pre-training framework.
Set-Estimation based Networked Model Predictive Control for Energy Management of Faulty Microgrids
In microgrid control systems, faults may occur in both electrical and communication layers.
Link Prediction on N-ary Relational Facts: A Graph-based Approach
The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention.
Entity Structure Within and Throughout: Modeling Mention Dependencies for Document-Level Relation Extraction
Our experiments demonstrate the usefulness of the proposed entity structure and the effectiveness of SSAN.
Ranked #3 on
Relation Extraction
on DocRED
Multi-view Classification Model for Knowledge Graph Completion
This paper describes a novel multi-view classification model for knowledge graph completion, where multiple classification views are performed based on both content and context information for candidate triple evaluation.
Knowledge-Enhanced Named Entity Disambiguation for Short Text
Named entity disambiguation is an important task that plays the role of bridge between text and knowledge.
Event Extraction as Multi-turn Question Answering
Most traditional approaches formulate this task as classification problems, with event types or argument roles taken as golden labels.
CoKE: Contextualized Knowledge Graph Embedding
This work presents Contextualized Knowledge Graph Embedding (CoKE), a novel paradigm that takes into account such contextual nature, and learns dynamic, flexible, and fully contextualized entity and relation embeddings.
Multi-grained Attention with Object-level Grounding for Visual Question Answering
Attention mechanisms are widely used in Visual Question Answering (VQA) to search for visual clues related to the question.
