Daniel Cer, Yinfei Yang, Sheng-yi Kong, Nan Hua, Nicole Limtiaco, Rhomni St. John, Noah Constant, Mario Guajardo-Cespedes, Steve Yuan, Chris Tar, Brian Strope, Ray Kurzweil
| Challenge: | TensorFlow Hub sentence embedding models have good task transfer performance . model variants allow for trade-offs between accuracy and compute resources . |
| Approach: | They propose easy-to-use TensorFlow Hub sentence embedding models with good task transfer performance. |
| Outcome: | The proposed models outperform models without transfer learning and those that use only word-level transfer on a number of NLP tasks. |
Similar Papers
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. |
Convolutional Neural Network for Universal Sentence Embeddings (C18-1)
Copied to clipboard
| Challenge: | Recent studies show that averaging word embeddings is effective for NLP but these models represent a sentence only in terms of features of words or uni-grams. |
| Approach: | They propose a CNN-based model that uses both features of words and n-grams to encode sentences. |
| Outcome: | The proposed model performs better than existing models in transfer learning setting and exceeds state of the art in supervised learning setting by initializing the parameters with the pre-trained sentence embeddings. |
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models (2022.findings-acl)
Copied to clipboard
| Challenge: | Sentence embeddings are useful for language processing tasks, but it is unclear how to produce them from encoder-decoder models. |
| Approach: | They investigate the effects of scaling up sentence encoders to 11B parameters on sentence embeddings from text-to-text transformers (T5) . |
| Outcome: | The proposed models outperform the previous best models on both SentEval and SentGLUE transfer tasks. |
Are the Best Multilingual Document Embeddings simply Based on Sentence Embeddings? (2023.findings-eacl)
Copied to clipboard
| Challenge: | obtaining document embeddings at document level is challenging due to computational requirements and lack of appropriate data. |
| Approach: | They compare methods to produce document-level representations from sentences based on LASER, LaBSE, and Sentence BERT pre-trained multilingual models. |
| Outcome: | The proposed methods produce document-level representations from sentences in 8 languages . the results show that a clever combination of sentence embeddings is usually better than encoding the full document as a single unit. |
A Deeper Look into Dependency-Based Word Embeddings (N18-4)
Copied to clipboard
| Challenge: | Word embeddings trained with dependency contexts excel at different tasks, and enhanced dependencies often improve performance. |
| Approach: | They propose to use dependency-based word embeddings to capture semantic similarity rather than relatedness. |
| Outcome: | The results show that word embeddings trained with Universal and Stanford dependencies excel at different tasks and that enhanced dependencies often improve performance. |
A Simple and Effective Unified Encoder for Document-Level Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for document-level machine translation use two separate encoders to model the source sentences and document- level contexts. |
| Approach: | They propose a unified encoder that can outperform existing models of dual-encoder models . they propose to use document-level contexts to model the interaction between the contexts and the source sentences . |
| Outcome: | The proposed model outperforms baseline models of dual-encoder models in terms of BLEU and METEOR scores. |
Low Resource Sequence Tagging using Sentence Reconstruction (2020.acl-main)
Copied to clipboard
| Challenge: | This work revisits the task of training sequence tagging models with limited resources using transfer learning. |
| Approach: | They propose a new loss that relies on sentence reconstruction from normalized embeddings. |
| Outcome: | The proposed method achieves 0.6 F1 score on Dutch datasets using only one sample. |
Learning Visually Grounded Sentence Representations (N18-1)
Copied to clipboard
| Challenge: | Unsupervised sentence representation models suffer from the grounding problem because of lack of association between symbols and external information. |
| Approach: | They train a sentence encoder to predict image features of a caption and use them as sentence representations. |
| Outcome: | The proposed model improves on word embeddings and word representations on standard benchmarks. |
Is Language Modeling Enough? Evaluating Effective Embedding Combinations (2020.lrec-1)
Copied to clipboard
Rudolf Schneider, Tom Oberhauser, Paul Grundmann, Felix Alexander Gers, Alexander Loeser, Steffen Staab
| Challenge: | specialized embeddings are not available for tasks like entity linking or paragraph classification. |
| Approach: | They evaluate whether universal embeddings can be complemented by specialized embeddables. |
| Outcome: | The proposed embeddings outperform state-of-the-art embeddables without any fine-tuning. |
When and Why Are Pre-Trained Word Embeddings Useful for Neural Machine Translation? (N18-2)
Copied to clipboard
| Challenge: | Pre-trained word embeddings have proven to be invaluable for improving performance in natural language analysis tasks where large-scale parallel corpora cannot be obtained. |
| Approach: | They perform five sets of experiments to analyze when pre-trained word embeddings can be useful in NMT tasks. |
| Outcome: | The embeddings provide gains of up to 20 BLEU points in the most favorable setting. |