Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Chenyan Xiong

Chenyan Xiong

Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

May 06, 2022
Zhenghao Liu, Han Zhang, Chenyan Xiong, Zhiyuan Liu, Yu Gu, Xiaohua Li

Figure 1 for Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

Figure 2 for Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

Figure 3 for Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

Figure 4 for Dimension Reduction for Efficient Dense Retrieval via Conditional Autoencoder

* 7 pages, 1 figure

Access Paper or Ask Questions

METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

Apr 16, 2022
Payal Bajaj, Chenyan Xiong, Guolin Ke, Xiaodong Liu, Di He, Saurabh Tiwary, Tie-Yan Liu, Paul Bennett, Xia Song, Jianfeng Gao

Figure 1 for METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

Figure 2 for METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

Figure 3 for METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

Figure 4 for METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals

* Update details in scaled initialization and add acknowledgement

Access Paper or Ask Questions

Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Apr 07, 2022
Yu Meng, Chenyan Xiong, Payal Bajaj, Saurabh Tiwary, Paul Bennett, Jiawei Han, Xia Song

Figure 1 for Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Figure 2 for Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Figure 3 for Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

Figure 4 for Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

* ICLR 2022. (Code and Models: https://github.com/microsoft/AMOS)

Access Paper or Ask Questions

Neural Approaches to Conversational Information Retrieval

Jan 13, 2022
Jianfeng Gao, Chenyan Xiong, Paul Bennett, Nick Craswell

Figure 1 for Neural Approaches to Conversational Information Retrieval

Figure 2 for Neural Approaches to Conversational Information Retrieval

Figure 3 for Neural Approaches to Conversational Information Retrieval

Figure 4 for Neural Approaches to Conversational Information Retrieval

* Book Draft

Access Paper or Ask Questions

Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Oct 10, 2021
Chen Zhao, Chenyan Xiong, Jordan Boyd-Graber, Hal Daumé III

Figure 1 for Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Figure 2 for Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Figure 3 for Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

Figure 4 for Distantly-Supervised Evidence Retrieval Enables Question Answering without Evidence Annotation

* EMNLP 2021

Access Paper or Ask Questions

TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

Sep 09, 2021
Huiyuan Xie, Zhenghao Liu, Chenyan Xiong, Zhiyuan Liu, Ann Copestake

Figure 1 for TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

Figure 2 for TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

Figure 3 for TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

Figure 4 for TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling

* Accepted to appear in Findings of EMNLP 2021

Access Paper or Ask Questions

Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

Aug 30, 2021
HongChien Yu, Chenyan Xiong, Jamie Callan

Figure 1 for Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

Figure 2 for Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

Figure 3 for Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

Figure 4 for Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

* Accepted at CIKM 2021

Access Paper or Ask Questions