Semanlink - Unsupervised Sentence Embedding Learning AND Synthetic Data

Impression

Recherche de Mot-clé

Recherche de Doc

Préférences...

Mots-clés liés

Arxiv Doc - Dense retriever - Documentation - Domain adaptation - Domain adaptation (NLP) - Embedding Model Fine-tuning - GPL (Generative Pseudo Labeling) - J'y étais - Jerry Liu - Multilingual NLP - Neural Search - Nils Reimers - RAG (Retrieval-Augmented Generation) - Sentence-BERT: Domain adaptation - Synthetic Data - Synthetic QA data - Tweet - Unsupervised Domain Adaptation (NLP) - Unsupervised Sentence Embedding Learning -

Unsupervised Sentence Embedding Learning AND Synthetic Data

Descendants partagés

GPL (Generative Pseudo Labeling)

9 Documents

Jerry Liu sur X : "One major way to improve your RAG system is to fine-tune your embedding model"

Tags:

2023-08-25 A propos

Domain Adaptation with Generative Pseudo-Labeling (GPL) | Pinecone

Tags:

2023-04-09 A propos

[2205.11498] Domain Adaptation for Memory-Efficient Dense Retrieval

Tags:

2022-09-26 A propos

Domain transfer with GGPL: German Generative Pseudo Labeling 🥨 | by Matthias Richter | Jun, 2022 | ML6team

Tags:

2022-06-02 A propos

Nils Reimers sur Twitter : "GPL goes multi-lingual..."

Tags:

2022-06-01 A propos

Ramsri Goutham Golla sur Twitter : "Hi @Nils_Reimers For GPL you used "msmarco-distilbert-base-tas-b" model and ..."

Tags:

2022-04-27 A propos

Domain Adaptation — Sentence-Transformers documentation

Tags:

2022-03-31 A propos

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

Tags:

2022-03-09 A propos

[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