Multilingual Universal Sentence Encoder for Semantic Retrieval
arXiv:1907.04307
Abstract
We introduce two pre-trained retrieval focused multilingual sentence encoding models, respectively based on the Transformer and CNN model architectures. The models embed text from 16 languages into a single semantic space using a multi-task trained dual-encoder that learns tied representations using translation based bridge tasks (Chidambaram al., 2018). The models provide performance that is competitive with the state-of-the-art on: semantic retrieval (SR), translation pair bitext retrieval (BR) and retrieval question answering (ReQA). On English transfer learning tasks, our sentence-level embeddings approach, and in some cases exceed, the performance of monolingual, English only, sentence embedding models. Our models are made available for download on TensorFlow Hub.
6 pages, 6 tables, 2 listings, and 1 figure
Cited by in corpus (15)
- Towards Zero-shot Cross-lingual Image Retrieval
- KorNLI and KorSTS: New Benchmark Datasets for Korean Natural Language Understanding
- Cross-language sentiment analysis of European Twitter messages duringthe COVID-19 pandemic
- MultiReQA: A Cross-Domain Evaluation for Retrieval Question Answering Models
- Intelligent Translation Memory Matching and Retrieval with Sentence Encoders
- Automatic Difficulty Classification of Arabic Sentences
- Evaluation of Sentence Representations in Polish
- Multi-task Learning for Cross-Lingual Sentiment Analysis
- Towards Zero-shot Cross-lingual Image Retrieval and Tagging
- PROVENANCE: An Intermediary-Free Solution for Digital Content Verification
- Crossing Variational Autoencoders for Answer Retrieval
- Auto-detecting groups based on textual similarity for group recommendations
- A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations
- Generating User-Centred Explanations via Illocutionary Question Answering: From Philosophy to Interfaces
- Global Explainability of BERT-Based Evaluation Metrics by Disentangling along Linguistic Factors