Σχετικά με το έγγραφο αυτό
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Sebastian Hofstätter
- sl:arxiv_num : 2010.02666
- sl:arxiv_published : 2020-10-06T12:35:53Z
- sl:arxiv_summary : Retrieval and ranking models are the backbone of many applications such as
web search, open domain QA, or text-based recommender systems. The latency of
neural ranking models at query time is largely dependent on the architecture
and deliberate choices by their designers to trade-off effectiveness for higher
efficiency. This focus on low query latency of a rising number of efficient
ranking architectures make them feasible for production deployment. In machine
learning an increasingly common approach to close the effectiveness gap of more
efficient models is to apply knowledge distillation from a large teacher model
to a smaller student model. We find that different ranking architectures tend
to produce output scores in different magnitudes. Based on this finding, we
propose a cross-architecture training procedure with a margin focused loss
(Margin-MSE), that adapts knowledge distillation to the varying score output
distributions of different BERT and non-BERT passage ranking architectures. We
apply the teachable information as additional fine-grained labels to existing
training triples of the MSMARCO-Passage collection. We evaluate our procedure
of distilling knowledge from state-of-the-art concatenated BERT models to four
different efficient architectures (TK, ColBERT, PreTT, and a BERT CLS dot
product model). We show that across our evaluated architectures our Margin-MSE
knowledge distillation significantly improves re-ranking effectiveness without
compromising their efficiency. Additionally, we show our general distillation
method to improve nearest neighbor based index retrieval with the BERT dot
product model, offering competitive results with specialized and much more
costly training methods. To benefit the community, we publish the teacher-score
training files in a ready-to-use package.@en
- sl:arxiv_title : Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation@en
- sl:arxiv_updated : 2021-01-22T16:24:52Z
- sl:bookmarkOf : https://arxiv.org/abs/2010.02666
- sl:creationDate : 2021-12-16
- sl:creationTime : 2021-12-16T13:37:29Z
- sl:relatedDoc : http://www.semanlink.net/doc/2021/12/2112_07577_gpl_generative_ps
Προτιμήσεις...