Picture for Rangan Majumder

Rangan Majumder

MS MARCO Web Search: a Large-scale Information-rich Web Dataset with Millions of Real Click Labels

Add code
May 13, 2024
Viaarxiv icon

Multilingual E5 Text Embeddings: A Technical Report

Add code
Feb 08, 2024
Viaarxiv icon

Improving Text Embeddings with Large Language Models

Add code
Dec 31, 2023
Viaarxiv icon

Large Search Model: Redefining Search Stack in the Era of LLMs

Add code
Oct 23, 2023
Viaarxiv icon

Inference with Reference: Lossless Acceleration of Large Language Models

Add code
Apr 10, 2023
Figure 1 for Inference with Reference: Lossless Acceleration of Large Language Models
Figure 2 for Inference with Reference: Lossless Acceleration of Large Language Models
Figure 3 for Inference with Reference: Lossless Acceleration of Large Language Models
Figure 4 for Inference with Reference: Lossless Acceleration of Large Language Models
Viaarxiv icon

LEAD: Liberal Feature-based Distillation for Dense Retrieval

Add code
Dec 10, 2022
Figure 1 for LEAD: Liberal Feature-based Distillation for Dense Retrieval
Figure 2 for LEAD: Liberal Feature-based Distillation for Dense Retrieval
Figure 3 for LEAD: Liberal Feature-based Distillation for Dense Retrieval
Figure 4 for LEAD: Liberal Feature-based Distillation for Dense Retrieval
Viaarxiv icon

Text Embeddings by Weakly-Supervised Contrastive Pre-training

Add code
Dec 07, 2022
Figure 1 for Text Embeddings by Weakly-Supervised Contrastive Pre-training
Figure 2 for Text Embeddings by Weakly-Supervised Contrastive Pre-training
Figure 3 for Text Embeddings by Weakly-Supervised Contrastive Pre-training
Figure 4 for Text Embeddings by Weakly-Supervised Contrastive Pre-training
Viaarxiv icon

PROD: Progressive Distillation for Dense Retrieval

Add code
Sep 27, 2022
Figure 1 for PROD: Progressive Distillation for Dense Retrieval
Figure 2 for PROD: Progressive Distillation for Dense Retrieval
Figure 3 for PROD: Progressive Distillation for Dense Retrieval
Figure 4 for PROD: Progressive Distillation for Dense Retrieval
Viaarxiv icon

SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval

Add code
Jul 06, 2022
Figure 1 for SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Figure 2 for SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Figure 3 for SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Figure 4 for SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrieval
Viaarxiv icon

XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation

Add code
Apr 19, 2020
Figure 1 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 2 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 3 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Figure 4 for XGLUE: A New Benchmark Dataset for Cross-lingual Pre-training, Understanding and Generation
Viaarxiv icon