Semanlink - NAVER LABS Europe : "@Nils_Reimers of @huggingface on 'Unsupervised domain adaptation for neural search'"

NAVER LABS Europe : "@Nils_Reimers of @huggingface on 'Unsupervised domain adaptation for neural search'"

Tags:

Au sujet de ce document

sl:bookmarkOf : https://twitter.com/naverlabseurope/status/1501110742279413762?s=20&t=X3K2Chz3SAyRreUdOWNQLA
sl:creationDate : 2022-03-09
sl:creationTime : 2022-03-09T10:53:24Z

Infos sur le fichier

Bookmark of: https://twitter.com/naverlabseurope/status/1501110742279413762?s=20&t=X3K2Chz3SAyRreUdOWNQLA

Documents with similar tags (experimental)

[2112.07577] GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval

Tags:

An unsupervised domain adaptation technique for dense retrieval models

1. synthetic queries
are generated for each passage from the target corpus (using an existing pre-trained [T5](tag:text_to_text_transfer_transformer)
encoder-decoder)
2. the generated queries are used for mining negative
passages (retrieving the most similar
paragraphs using an existing dense retrieval
model == hard negatives!)
3. the query-passage pairs are labeled by a cross-encoder and used to train the domain-adapted
dense retriever (using method described in [Hofstätter et al.,
2020](doc:2021/12/2010_02666_improving_efficien))

[Nils Reimers sur Twitter](doc:2021/12/nils_reimers_sur_twitter_do_), [GitHub](https://github.com/UKPLab/gpl),  by the author of [TSDAE](doc:2021/09/2104_06979_tsdae_using_trans)

Claims to improve "Doc2Query" [Document Expansion by Query Prediction](doc:2022/01/1904_08375_document_expansion): ([src](https://twitter.com/KexinWang2049/status/1471435779415150598))

> - GPL: Uses doc2query to construct synthetic data and does knowledge distillation (i.e. training) on that data.
> - Doc2query: Generates queries to extend the documents and use BM25 on top of them w/o training.

2021-12-15 A propos