Transcription of Sentence-BERT: Sentence Embeddings using Siamese BERT …
{{id}} {{{paragraph}}}
Example: air traffic controller
Sentence-BERT: Sentence Embeddings using Siamese BERT …
Sentence -BERT: Sentence Embeddings using Siamese BERT-NetworksNils Reimers and Iryna GurevychUbiquitous Knowledge Processing Lab (UKP-TUDA)Department of Computer Science, Technische Universit at (Devlin et al., 2018) and RoBERTa (Liuet al., 2019) has set a new state-of-the-artperformance on Sentence -pair regression taskslike semantic textual similarity (STS). How-ever, it requires that both sentences are fedinto the network, which causes a massive com-putational overhead: Finding the most sim-ilar pair in a collection of 10,000 sentencesrequires about 50 million inference computa-tions (~65 hours) with BERT.
Up to our knowl-edge, there is so far no evaluation if these methods lead to useful sentence embeddings. Sentence embeddings are a well studied area with dozens of proposed methods. Skip-Thought (Kiros et al.,2015) trains an encoder-decoder ar-chitecture to predict the surrounding sentences. InferSent (Conneau et al.,2017) uses labeled
Loading..
Tags:
Information
Domain:
Source:
Link to this page:
Please notify us if you found a problem with this document: