Papers › Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural...

Improving Multi-Task Deep Neural Networks via Knowledge Distillation for Natural Language Understanding

20 Apr 2019arXiv:1904.09482archive 2025-07-28

Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao

This paper explores the use of knowledge distillation to improve a Multi-Task Deep Neural Network (MT-DNN) (Liu et al., 2019) for learning text representations across multiple natural language understanding tasks. Although ensemble learning can improve model performance, serving an ensemble of large DNNs such as MT-DNN can be prohibitively expensive. Here we apply the knowledge distillation method (Hinton et al., 2015) in the multi-task learning setting. For each task, we train an ensemble of different MT-DNNs (teacher) that outperforms any single model, and then train a single MT-DNN (student) via multi-task learning to distill knowledge from these ensemble teachers. We show that the distilled MT-DNN significantly outperforms the original MT-DNN on 7 out of 9 GLUE tasks, pushing the GLUE benchmark (single model) to 83.7% (1.5% absolute improvement (Based on the GLUE leaderboard at https://gluebenchmark.com/leaderboard as of April 1, 2019.)). The code and pre-trained models will be made publicly available at https://github.com/namisan/mt-dnn.

PaperPDFCode

In Syntology View this paper on Syntology, its page in Syntology's graph. That page lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

namisan/mt-dnn officialmentioned in papermentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CAMERO: Consistency Regularized Ensemble of Perturbed Language Models with Weight Sharing (arXiv:2204.06625; that paper's own run record: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
chunhuililili/mt_dnn mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Hybrid Neural Network Model for Commonsense Reasoning (arXiv:1907.11983; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
microsoft/MT-DNN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adversarial Regularization as Stackelberg Game: An Unrolled Optimization Approach (arXiv:2104.04886; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Ensemble LearningKnowledge DistillationMulti-Task LearningNatural Language InferenceNatural Language UnderstandingSemantic Textual SimilaritySentiment Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Natural Language Inference MultiNLI MT-DNN-ensemble Matched 87.9 #19 of 67 Archive leaderboard report
Natural Language Inference MultiNLI MT-DNN-ensemble Mismatched 87.4 #19 of 67 Archive leaderboard report
Semantic Textual Similarity SentEval MT-DNN-ensemble MRPC 92.7/90.3 #5 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval MT-DNN-ensemble SICK-E - #5 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval MT-DNN-ensemble SICK-R - #5 of 6 Archive leaderboard report
Semantic Textual Similarity SentEval MT-DNN-ensemble STS 91.1/90.7* #5 of 6 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification MT-DNN-ensemble Accuracy 96.5 #15 of 87 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Knowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections