@inproceedings{jin-etal-2022-plug,
title = "Plug and Play Knowledge Distillation for k{NN}-{LM} with External Logits",
author = "Jin, Xuyang and
Ge, Tao and
Wei, Furu",
editor = "He, Yulan and
Ji, Heng and
Li, Sujian and
Liu, Yang and
Chang, Chua-Hui",
booktitle = "Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = nov,
year = "2022",
address = "Online only",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.aacl-short.57/",
doi = "10.18653/v1/2022.aacl-short.57",
pages = "463--469",
abstract = "Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2seq) tasks, KD for causal language modeling (LM) remains a challenge. In this paper, we present a novel perspective of knowledge distillation by proposing plug and play knowledge distillation (PP-KD) to improve a (student) kNN-LM that is the state-of-the-art in causal language modeling by leveraging external logits from either a powerful or a heterogeneous (teacher) LM. Unlike conventional logit-based KD where the teacher`s knowledge is built-in during training, PP-KD is plug and play: it stores the teacher`s knowledge (i.e., logits) externally and uses the teacher`s logits of the retrieved k-nearest neighbors during kNN-LM inference at test time. In contrast to marginal perplexity improvement by logit-based KD in conventional neural (causal) LM, PP-KD achieves a significant improvement, enhancing the kNN-LMs in multiple language modeling datasets, showing a novel and promising perspective for causal LM distillation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jin-etal-2022-plug">
<titleInfo>
<title>Plug and Play Knowledge Distillation for kNN-LM with External Logits</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuyang</namePart>
<namePart type="family">Jin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Ge</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Furu</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heng</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sujian</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chua-Hui</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online only</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2seq) tasks, KD for causal language modeling (LM) remains a challenge. In this paper, we present a novel perspective of knowledge distillation by proposing plug and play knowledge distillation (PP-KD) to improve a (student) kNN-LM that is the state-of-the-art in causal language modeling by leveraging external logits from either a powerful or a heterogeneous (teacher) LM. Unlike conventional logit-based KD where the teacher‘s knowledge is built-in during training, PP-KD is plug and play: it stores the teacher‘s knowledge (i.e., logits) externally and uses the teacher‘s logits of the retrieved k-nearest neighbors during kNN-LM inference at test time. In contrast to marginal perplexity improvement by logit-based KD in conventional neural (causal) LM, PP-KD achieves a significant improvement, enhancing the kNN-LMs in multiple language modeling datasets, showing a novel and promising perspective for causal LM distillation.</abstract>
<identifier type="citekey">jin-etal-2022-plug</identifier>
<identifier type="doi">10.18653/v1/2022.aacl-short.57</identifier>
<location>
<url>https://aclanthology.org/2022.aacl-short.57/</url>
</location>
<part>
<date>2022-11</date>
<extent unit="page">
<start>463</start>
<end>469</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Plug and Play Knowledge Distillation for kNN-LM with External Logits
%A Jin, Xuyang
%A Ge, Tao
%A Wei, Furu
%Y He, Yulan
%Y Ji, Heng
%Y Li, Sujian
%Y Liu, Yang
%Y Chang, Chua-Hui
%S Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2022
%8 November
%I Association for Computational Linguistics
%C Online only
%F jin-etal-2022-plug
%X Despite the promising evaluation results by knowledge distillation (KD) in natural language understanding (NLU) and sequence-to-sequence (seq2seq) tasks, KD for causal language modeling (LM) remains a challenge. In this paper, we present a novel perspective of knowledge distillation by proposing plug and play knowledge distillation (PP-KD) to improve a (student) kNN-LM that is the state-of-the-art in causal language modeling by leveraging external logits from either a powerful or a heterogeneous (teacher) LM. Unlike conventional logit-based KD where the teacher‘s knowledge is built-in during training, PP-KD is plug and play: it stores the teacher‘s knowledge (i.e., logits) externally and uses the teacher‘s logits of the retrieved k-nearest neighbors during kNN-LM inference at test time. In contrast to marginal perplexity improvement by logit-based KD in conventional neural (causal) LM, PP-KD achieves a significant improvement, enhancing the kNN-LMs in multiple language modeling datasets, showing a novel and promising perspective for causal LM distillation.
%R 10.18653/v1/2022.aacl-short.57
%U https://aclanthology.org/2022.aacl-short.57/
%U https://doi.org/10.18653/v1/2022.aacl-short.57
%P 463-469
Markdown (Informal)
[Plug and Play Knowledge Distillation for kNN-LM with External Logits](https://aclanthology.org/2022.aacl-short.57/) (Jin et al., AACL-IJCNLP 2022)
ACL
- Xuyang Jin, Tao Ge, and Furu Wei. 2022. Plug and Play Knowledge Distillation for kNN-LM with External Logits. In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 463–469, Online only. Association for Computational Linguistics.