1 |
Optimizing a portfolio of agri-environmental investments ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
“Institution” and “institute”: tendency to the “false substitution” of concepts ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Delving Deeper into Cross-lingual Visual Question Answering ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Testing the interface hypothesis: the acquisition of English indirect questions by L1 speakers of Omani Arabic
|
|
|
|
In: Heliyon (2022)
|
|
BASE
|
|
Show details
|
|
5 |
Geschichte der Brille : Verfahren der Herstellung von Brillenfassungen aus Celluloseacetat : Terminologiearbeit im Sprachpaar Italienisch – Deutsch, Deutsch – Italienisch
|
|
Kloster, Iryna [Verfasser]. - Mainz : Universitätsbibliothek der Johannes Gutenberg-Universität Mainz, 2021
|
|
DNB Subject Category Language
|
|
Show details
|
|
6 |
Combating Temporal Drift in Crisis with Adapted Embeddings ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
The concept of security in the integration processes of the European union countries ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
The concept of security in the integration processes of the European union countries ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Ideas Challenge 2020/2021 : WikiData Integration with Repository Contents ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Ideas Challenge 2020/2021 : WikiData Integration with Repository Contents ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Annotation Curricula to Implicitly Train Non-Expert Annotators ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Lesia Ukrainka in the Global Information Space: Case-Study of the Audio Guide Creation for the Lesia Ukrainka Museum ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Lesia Ukrainka in the Global Information Space: Case-Study of the Audio Guide Creation for the Lesia Ukrainka Museum ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Smelting Gold and Silver for Improved Multilingual AMR-to-Text Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
TSDAE: Using Transformer-based Sequential Denoising Auto-Encoder for Unsupervised Sentence Embedding Learning ...
|
|
|
|
Abstract:
Learning sentence embeddings often requires a large amount of labeled data. However, for most tasks and domains, labeled data is seldom available and creating it is expensive. In this work, we present a new state-of-the-art unsupervised method based on pre-trained Transformers and Sequential Denoising Auto-Encoder (TSDAE) which outperforms previous approaches by up to 6.4 points. It can achieve up to 93.1% of the performance of in-domain 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. A crucial shortcoming of previous studies is the narrow evaluation: Most work mainly evaluates on the single task of Semantic Textual Similarity (STS), which does not require any domain knowledge. It is unclear if these proposed methods generalize to other domains and tasks. We fill this gap and evaluate TSDAE and other recent approaches on four different datasets from ...
|
|
Keyword:
Computational Linguistics; Machine Learning; Natural language generation
|
|
URL: https://underline.io/lecture/39314-tsdae-using-transformer-based-sequential-denoising-auto-encoder-for-unsupervised-sentence-embedding-learning https://dx.doi.org/10.48448/ymtp-md67
|
|
BASE
|
|
Hide details
|
|
17 |
The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
Investigating label suggestions for opinion mining in German Covid-19 social media ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|