Papers with transfer learning tasks
Multilingual Universal Sentence Encoder for Semantic Retrieval (2020.acl-demos)
Copied to clipboard
Yinfei Yang, Daniel Cer, Amin Ahmad, Mandy Guo, Jax Law, Noah Constant, Gustavo Hernandez Abrego, Steve Yuan, Chris Tar, Yun-hsuan Sung, Brian Strope, Ray Kurzweil
| Challenge: | Using a multi-task trained dual-encoder, our models embed text from 16 languages into a shared semantic space. |
| Approach: | They propose retrieval focused multilingual sentence embedding models on TensorFlow Hub. |
| Outcome: | The models achieve state-of-the-art on monolingual and cross-lingual retrieval (SR) and retrieval question answering (ReQA) competitive performance is obtained on related tasks of translation pair bitext retrieval and retrieving question answering. |
Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models (2023.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in NLP have led to the use of pre-trained Transformer models for transfer learning tasks becoming the most common way to solve target tasks. |
| Approach: | They propose a 3-phase technique to adjust a base model for a classification task by adapting the model’s signal to the data distribution and a new data augmentation approach for Supervised Contrastive Learning to correct the unbalanced datasets. |
| Outcome: | The proposed method is compared with other methods and compares it with other approaches. |
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks (D19-1)
Copied to clipboard
| Challenge: | Existing methods for finding similar sentences require multiple inferences . a modern GPU requires 65 hours to find the most similar pair in 10,000 sentences . |
| Approach: | They propose a modification of the pretrained BERT network that uses siamese and triplet networks to derive semantically meaningful sentence embeddings. |
| Outcome: | The proposed method outperforms existing methods on sentence-pair regression tasks. |
Transfer Learning Methods for Domain Adaptation in Technical Logbook Datasets (2022.lrec-1)
Copied to clipboard
| Challenge: | Technical logbook data typically has both a domain, the field it comes from, and an application, what it is used for. |
| Approach: | They propose to use domain-specific technical language to identify technical logbook entries by using transfer learning to learn from different domains and from different datasets. |
| Outcome: | The proposed approach improves performance in all cases but one of the three domains studied. |
Improving Contrastive Learning of Sentence Embeddings from AI Feedback (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing methods to learn sentence embeddings with rich semantics are limited due to the discrete nature of natural language. |
| Approach: | They propose to use AI feedback to improve contrastive learning of sentence embeddings by combining human feedback and AI feedback. |
| Outcome: | The proposed method achieves state-of-the-art performance on several semantic textual similarity and transfer learning tasks compared to other unsupervised and supervised contrastive learning methods. |