Search Results for author: Yifan He

Found 26 papers, 10 papers with code

damo_nlp at MEDIQA 2021: Knowledge-based Preprocessing and Coverage-oriented Reranking for Medical Question Summarization

no code implementations NAACL (BioNLP) 2021 Yifan He, Mosha Chen, Songfang Huang

Medical question summarization is an important but difficult task, where the input is often complex and erroneous while annotated data is expensive to acquire.

Noisy Label Detection for Speaker Recognition

1 code implementation1 Dec 2022 Ruibin Yuan, Hanzhi Yin, Yi Wang, Yifan He, Yushi Ye, Lei Zhang

The success of deep neural networks requires both high annotation quality and massive data.

Metric Learning Speaker Recognition +1

Text-Aware Dual Routing Network for Visual Question Answering

no code implementations17 Nov 2022 Luoqian Jiang, Yifan He, Jian Chen

To address the above issues, we propose a Text-Aware Dual Routing Network (TDR) which simultaneously handles the VQA cases with and without understanding text information in the input images.

Optical Character Recognition (OCR) Question Answering +2

Knowledge-Driven Program Synthesis via Adaptive Replacement Mutation and Auto-constructed Subprogram Archives

1 code implementation8 Sep 2022 Yifan He, Claus Aranha, Tetsuya Sakurai

We compare the proposed method with PushGP, as well as a method using subprograms manually extracted by a human.

Program Synthesis

Distributed Feature Selection for High-dimensional Additive Models

no code implementations16 May 2022 Yifan He, Yong Zhou, Yang Feng

Distributed statistical learning is a common strategy for handling massive data where we divide the learning task into multiple local machines and aggregate the results afterward.

Additive models

Learning Deep Interleaved Networks with Asymmetric Co-Attention for Image Restoration

1 code implementation29 Oct 2020 Feng Li, Runmin Cong, Huihui Bai, Yifan He, Yao Zhao, Ce Zhu

In this paper, we present a deep interleaved network (DIN) that learns how information at different states should be combined for high-quality (HQ) images reconstruction.

Deblurring Image Deblurring +2

Robust Layout-aware IE for Visually Rich Documents with Pre-trained Language Models

no code implementations22 May 2020 Mengxi Wei, Yifan He, Qiong Zhang

Many business documents processed in modern NLP and IR pipelines are visually rich: in addition to text, their semantics can also be captured by visual traits such as layout, format, and fonts.

Deep Interleaved Network for Image Super-Resolution With Asymmetric Co-Attention

1 code implementation24 Apr 2020 Feng Li, Runming Cong, Huihui Bai, Yifan He

Recently, Convolutional Neural Networks (CNN) based image super-resolution (SR) have shown significant success in the literature.

Image Super-Resolution

Solving Portfolio Optimization Problems Using MOEA/D and Levy Flight

1 code implementation15 Mar 2020 Yifan He, Claus Aranha

Portfolio optimization is a financial task which requires the allocation of capital on a set of financial assets to achieve a better trade-off between return and risk.

Portfolio Optimization

Enriching Pre-trained Language Model with Entity Information for Relation Classification

5 code implementations20 May 2019 Shanchan Wu, Yifan He

In this paper, we propose a model that both leverages the pre-trained BERT language model and incorporates information from the target entities to tackle the relation classification task.

General Classification Language Modelling +1

Multi-Instance Learning for End-to-End Knowledge Base Question Answering

no code implementations6 Mar 2019 Mengxi Wei, Yifan He, Qiong Zhang, Luo Si

This paper proposes a novel approach based on multiple instance learning to address the problem of noisy answers by exploring consensus among answers to the same question in training end-to-end KBQA models.

Knowledge Base Question Answering Multiple Instance Learning

Entity Linking with a Paraphrase Flavor

1 code implementation LREC 2016 Maria Pershina, Yifan He, Ralph Grishman

The task of Named Entity Linking is to link entity mentions in the document to their correct entries in a knowledge base and to cluster NIL mentions.

Entity Disambiguation Entity Linking

Jointly Embedding Relations and Mentions for Knowledge Population

no code implementations RANLP 2015 Miao Fan, Kai Cao, Yifan He, Ralph Grishman

This paper contributes a joint embedding model for predicting relations between a pair of entities in the scenario of relation inference.

Relation Extraction

Annotating Relations in Scientific Articles

no code implementations LREC 2014 Adam Meyers, Giancarlo Lee, Angus Grieve-Smith, Yifan He, Harriet Taber

Relations (ABBREVIATE, EXEMPLIFY, ORIGINATE, REL{\_}WORK, OPINION) between entities (citations, jargon, people, organizations) are annotated for PubMed scientific articles.

Relation Extraction

Cannot find the paper you are looking for? You can Submit a new open access paper.