08/12/2020

FASTMATCH: Accelerating the Inference of BERT-based Text Matching

Shuai Pang, Jianqiang Ma, Zeyu Yan, Yang Zhang, Jianping Shen

Keywords:

Abstract Paper Similar Papers

Abstract: Recently, pre-trained language models such as BERT have shown state-of-the-art accuracies in text matching. When being applied to IR (or QA), the BERT-based matching models need to online calculate the representations and interactions for all query-candidate pairs. The high inference cost has prohibited the deployments of BERT-based matching models in many practical applications. To address this issue, we propose a novel BERT-based text matching model, in which the representations and the interactions are decoupled. Then, the representations of the candidates can be calculated and stored offline, and directly retrieved during the online matching phase. To conduct the interactions and generate final matching scores, a lightweight attention network is designed. Experiments based on several large scale text matching datasets show that the proposed model, called FASTMATCH, can achieve up to 100X speed-up to BERT and RoBERTa at the online matching phase, while keeping more up to 98.7% of the performance.

The video of this talk cannot be embedded. You can watch it here:
https://underline.io/lecture/6178-fastmatch-accelerating-the-inference-of-bert-based-text-matching
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at COLING 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 12:12 
 0
 0
 0
 0
 11:12 
 0
 0
 0
 0
 11:10 
 0
 0
 0
 0
 3:17 
 0
 0
 0
 0
 3:28 
 0
 0
 0
 0
 2:50 
 0
 0
 0
 0
 7:09 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 11:43 
 0
 0
 0
 0
 9:40 
 0
 0
 0
 0
 10:51 
 0
 0
 0
 0
 15:59 
 0
 0
 0
 0
 11:05 
 0
 0
 0
 0
 20:17 
 0
 1
 0
 0
 14:53 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 5:15 
 0
 0
 0
 0
 15:05 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 10:38 
 0
 0
 0
 0
 12:32 
 0
 0
 0
 0
 14:37 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:55 
 0
 0
 0
 1
 10:52 
 0
 0
 0
 0
 6:48 
 0
 0
 0
 0
 9:47 
 0
 0
 0
 0
 9:23 
 0
 0
 0
 0
 9:59 
 0
 0
 0
 0
 5:21 
 0
 0
 0
 0
 11:37 
 0
 0
 0
 0
 12:03 
 0
 0
 0
 0
 6:14 
 0
 0
 0
 0
 13:01 
 0
 0
 0
 0
 14:34 
 0
 0
 0
 0
 5:12 
 0
 0
 0
 0
 2:59 
 0
 0
 0
 0
 8:53 
 0
 0
 0
 0
 12:18