Semanlink - Nils Reimers sur Twitter : "How to train state-of-the-art sentence embeddings?"

Impression

Recherche de Mot-clé

Recherche de Doc

Préférences...

Nils Reimers sur Twitter : "How to train state-of-the-art sentence embeddings?"

Tags:

Au sujet de ce document

sl:bookmarkOf : https://twitter.com/Nils_Reimers/status/1407309773238935564?s=20
sl:creationDate : 2021-06-22
sl:creationTime : 2021-06-22T14:54:27Z

Infos sur le fichier

Bookmark of: https://twitter.com/Nils_Reimers/status/1407309773238935564?s=20

Documents with similar tags (experimental)

Nils Reimers sur X : "The Azure team did a fantastic job bringing Cohere's latest LLMs on their platform..."

Tags:

2024-04-05 A propos

Nils Reimers sur Twitter : "Cross-Lingual Text-Classification just from English Data"

Tags:

2023-07-20 A propos

How to wrap without using tape - YouTube

Tags:

2023-07-03 A propos

Nils Reimers sur Twitter : "Building search products that support many languages was always a nightmare..."

Tags:

2023-02-16 A propos

cohere sur Twitter : "With neural search, you can finally have a powerful search function for internal data that works just as well as external search engines such as Google. Making it especially useful for searching internal company documents..."

Tags:

2023-01-23 A propos

Nils Reimers sur Twitter : "MTEB - Massive Text Embedding Benchmark ..."

Tags:

2022-10-17 A propos

Santiago sur Twitter : "If you have an Apple M1 or M2 and don't take advantage of its GPU, I'm about to change your life..."

Tags:

2022-10-07 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

Nils Reimers sur Twitter : "A nice thread on generalization performance for Dense Retrieval models..."

Tags:

2022-04-27 A propos

Nils Reimers sur Twitter : "Great post on SetFit"

Tags:

2022-03-31 A propos

Thomas Müller sur Twitter : "paper & code of a novel light-weight few-shot model based on sentence embeddings..."

Tags:

2022-03-30 A propos

[2004.09813] Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation

Tags:

2022-03-18 A propos

Nils Reimers sur Twitter : "Creating intent classes for chatbots is challenging This tutorial shows how to use sentence-transformers to find potentially overlapping intent classes and how to improve your data annotation work." / Twitter

Tags:

2022-02-19 A propos

Nils Reimers sur Twitter : "how to use the fast clustering algorithm from sentence-transformers..."

Tags:

2022-02-19 A propos

Nils Reimers sur Twitter : "Do dense retrieval models work out-of-the-box for your specific domain? Often the answer was No😢..."

Tags:

2021-12-15 A propos

Nils Reimers sur Twitter : "Neural Search for Low Resource Scenarios..."

Tags:

2021-10-27 A propos

Nils Reimers sur Twitter : "Introduction - Neural Search"

Tags:

2021-09-20 A propos

[2104.06979] TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning

Tags:

> The most
successful previous approaches like InferSent (Conneau
et al., 2017), Universial Sentence Encoder
(USE) (Cer et al., 2018) and SBERT (Reimers and
Gurevych, 2019) heavily relied on labeled data to
train sentence embedding models.
>
> TSDAE can
achieve up to 93.1% of the performance of indomain
supervised approaches. Further, we
show that TSDAE is **a strong domain adaptation
and pre-training method for sentence
embeddings**, significantly outperforming other
approaches like Masked Language Model.

> During training, TSDAE
encodes corrupted sentences into fixed-sized
vectors and requires the decoder to reconstruct the
original sentences from this sentence embedding.

- <https://www.sbert.net/examples/unsupervised_learning/TSDAE/README.html>
- [github](https://github.com/UKPLab/sentence-transformers/tree/master/examples/unsupervised_learning/TSDAE)
- [UKPLab/sentence-transformers: Sentence Embeddings with BERT & XLNet](doc:2020/07/ukplab_sentence_transformers_s)
- [twitter](https://twitter.com/KexinWang2049/status/1433361957579538432):

> **TSDAE can learn domain-specific sentence embeddings with unlabeled sentences**
>
> Most importantly, instead of STS (Semantic Textual Similarity), **we suggest evaluating unsupervised sentence embeddings on the domain-specific tasks&datasets, which is the real use case for them**. Actually, STS scores do not correlate with performance on specific tasks.

2021-09-01 A propos

Nandan Thakur sur Twitter : "@ikuyamada @Nils_Reimers Thanks @ikuyamad..."

Tags:

2021-07-09 A propos

Nandan Thakur sur Twitter : "how to create sentence-embeddings when little or zero in-domain training data is available"

Tags:

2021-06-03 A propos

Nils Reimers sur Twitter : EasyNMT Easy-to-use (3 lines of code), state-of-the-art neural machine translations

Tags:

2021-04-27 A propos

Nils Reimers sur Twitter : "SBERT Release v1.1.0"

Tags:

2021-04-22 A propos

Nils Reimers sur Twitter : "New models for Neural Information Retrieval..."

Tags:

2021-04-17 A propos