Do you want to publish a course? Click here

Fast, Effective, and Self-Supervised: Transforming Masked Language Models into Universal Lexical and Sentence Encoders

سريع وفعال ومشرف ذاتي: تحويل نماذج لغة ملثمين إلى تشفير المعجمات والعامة العالمية

571   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

Previous work has indicated that pretrained Masked Language Models (MLMs) are not effective as universal lexical and sentence encoders off-the-shelf, i.e., without further task-specific fine-tuning on NLI, sentence similarity, or paraphrasing tasks using annotated task data. In this work, we demonstrate that it is possible to turn MLMs into effective lexical and sentence encoders even without any additional data, relying simply on self-supervision. We propose an extremely simple, fast, and effective contrastive learning technique, termed Mirror-BERT, which converts MLMs (e.g., BERT and RoBERTa) into such encoders in 20-30 seconds with no access to additional external knowledge. Mirror-BERT relies on identical and slightly modified string pairs as positive (i.e., synonymous) fine-tuning examples, and aims to maximise their similarity during identity fine-tuning''. We report huge gains over off-the-shelf MLMs with Mirror-BERT both in lexical-level and in sentence-level tasks, across different domains and different languages. Notably, in sentence similarity (STS) and question-answer entailment (QNLI) tasks, our self-supervised Mirror-BERT model even matches the performance of the Sentence-BERT models from prior work which rely on annotated task data. Finally, we delve deeper into the inner workings of MLMs, and suggest some evidence on why this simple Mirror-BERT fine-tuning approach can yield effective universal lexical and sentence encoders.



References used
https://aclanthology.org/
rate research

Read More

In this paper, we present three supervised systems for English lexical complexity prediction of single and multiword expressions for SemEval-2021 Task 1. We explore the use of statistical baseline features, masked language models, and character-level encoders to predict the complexity of a target token in context. Our best system combines information from these three sources. The results indicate that information from masked language models and character-level encoders can be combined to improve lexical complexity prediction.
Large language models have become increasingly difficult to train because of the growing computation time and cost. In this work, we present SRU++, a highly-efficient architecture that combines fast recurrence and attention for sequence modeling. SRU ++ exhibits strong modeling capacity and training efficiency. On standard language modeling tasks such as Enwik8, Wiki-103 and Billion Word datasets, our model obtains better bits-per-character and perplexity while using 3x-10x less training cost compared to top-performing Transformer models. For instance, our model achieves a state-of-the-art result on the Enwik8 dataset using 1.6 days of training on an 8-GPU machine. We further demonstrate that SRU++ requires minimal attention for near state-of-the-art performance. Our results suggest jointly leveraging fast recurrence with little attention as a promising direction for accelerating model training and inference.
Masked language modeling (MLM) is one of the key sub-tasks in vision-language pretraining. In the cross-modal setting, tokens in the sentence are masked at random, and the model predicts the masked tokens given the image and the text. In this paper, we observe several key disadvantages of MLM in this setting. First, as captions tend to be short, in a third of the sentences no token is sampled. Second, the majority of masked tokens are stop-words and punctuation, leading to under-utilization of the image. We investigate a range of alternative masking strategies specific to the cross-modal setting that address these shortcomings, aiming for better fusion of text and image in the learned representation. When pre-training the LXMERT model, our alternative masking strategies consistently improve over the original masking strategy on three downstream tasks, especially in low resource settings. Further, our pre-training approach substantially outperforms the baseline model on a prompt-based probing task designed to elicit image objects. These results and our analysis indicate that our method allows for better utilization of the training data.
For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality bar of the website, especially at a large scale. We thus propose a programmatic solution to generate product advertising headlines using retail content. We propose a state of the art application of Reinforcement Learning (RL) Policy gradient methods on Transformer (Vaswani et al., 2017) based Masked Language Models (Devlin et al., 2019). Our method creates the advertising headline by jointly conditioning on multiple products that a seller wishes to advertise. We demonstrate that our method outperforms existing Transformer and LSTM + RL methods in overlap metrics and quality audits. We also show that our model generated headlines outperform human submitted headlines in terms of both grammar and creative quality as determined by audits.
Transformer architecture has become ubiquitous in the natural language processing field. To interpret the Transformer-based models, their attention patterns have been extensively analyzed. However, the Transformer architecture is not only composed of the multi-head attention; other components can also contribute to Transformers' progressive performance. In this study, we extended the scope of the analysis of Transformers from solely the attention patterns to the whole attention block, i.e., multi-head attention, residual connection, and layer normalization. Our analysis of Transformer-based masked language models shows that the token-to-token interaction performed via attention has less impact on the intermediate representations than previously assumed. These results provide new intuitive explanations of existing reports; for example, discarding the learned attention patterns tends not to adversely affect the performance. The codes of our experiments are publicly available.

suggested questions

comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا