paper-with-me

홈 › Papers

AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model

2022-08-02 · Saleh Soltan, Shankar Ananthakrishnan, Jack FitzGerald, Rahul Gupta, Wael Hamza, Haidar Khan, Charith Peris, Stephen Rawls, Andy Rosenbaum, Anna Rumshisky, Chandana Satya Prakash, Mukund Sridhar, Fabian Triefenbach, Apurv Verma, Gokhan Tur, Prem Natarajan

In this work, we demonstrate that multilingual large-scale sequence-to-sequence (seq2seq) models, pre-trained on a mixture of denoising and Causal Language Modeling (CLM) tasks, are more efficient few-shot learners than decoder-only models on various tasks. In particular, we train a 20 billion parameter multilingual seq2seq model called Alexa Teacher Model (AlexaTM 20B) and show that it achieves state-of-the-art (SOTA) performance on 1-shot summarization tasks, outperforming a much larger 540B PaLM decoder model. AlexaTM 20B also achieves SOTA in 1-shot machine translation, especially for low-resource languages, across almost all language pairs supported by the model (Arabic, English, French, German, Hindi, Italian, Japanese, Marathi, Portuguese, Spanish, Tamil, and Telugu) on Flores-101 dataset. We also show in zero-shot setting, AlexaTM 20B outperforms GPT3 (175B) on SuperGLUE and SQuADv2 datasets and provides SOTA performance on multilingual tasks such as XNLI, XCOPA, Paws-X, and XWinograd. Overall, our results present a compelling case for seq2seq models as a powerful alternative to decoder-only models for Large-scale Language Model (LLM) training.

📄 PDF Abstract BibTeX arXiv:2208.01448

Code (1)

amazon-science/alexa-teacher-models pytorch

Tasks

Causal Language ModelingCommon Sense ReasoningCoreference ResolutionDecoderDenoisingFew-Shot LearningLanguage ModelingLanguage ModellingMachine TranslationNatural Language InferenceQuestion AnsweringWord Sense Disambiguation

Methods 이 논문이 사용한 방법론

PaLM 설명 없음
Sigmoid Activation 설명 없음
Tanh Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…
Seq2Seq Seq2Seq, or Sequence To Sequence, is a model used in sequence prediction tasks, such as language modelling and machine translation. The idea is to use one…

Similar Papers 제목 키워드 기반

LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging

2022-09-20 · COLING 2022 10 · Andy Rosenbaum, Saleh Soltan, Wael Hamza, Yannick Versley 외

We present LINGUIST, a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST), via fine-tuning AlexaTM 5B, a 5-billion-parameter multilingual sequence-to-sequence (seq2seq) model, on a fl…

intent-classificationIntent ClassificationLanguage ModelingLanguage Modelling+2

CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing

2022-10-13 · Andy Rosenbaum, Saleh Soltan, Wael Hamza, Amir Saffari 외

A bottleneck to developing Semantic Parsing (SP) models is the need for a large volume of human-labeled training data. Given the complexity and cost of human annotation for SP, labeled data is often scarce, particularly …

Data AugmentationSemantic Parsing

GeMQuAD : Generating Multilingual Question Answering Datasets from Large Language Models using Few Shot Learning

2024-04-14 · Amani Namboori, Shivam Mangale, Andy Rosenbaum, Saleh Soltan

The emergence of Large Language Models (LLMs) with capabilities like In-Context Learning (ICL) has ushered in new possibilities for data generation across various domains while minimizing the need for extensive data coll…

Extractive Question-AnsweringFew-Shot LearningIn-Context LearningMachine Translation+2

A Multi-Encoder Frozen-Decoder Approach for Fine-Tuning Large Language Models

2025-01-14 · Kaustubh D. Dhole

Among parameter-efficient fine-tuning methods, freezing has emerged as a popular strategy for speeding up training, reducing catastrophic forgetting, and improving downstream performance. We investigate the impact of fre…

Decoderparameter-efficient fine-tuning

Few-Shot Multilingual Open-Domain QA from 5 Examples

2025-02-27 · Fan Jiang, Tom Drummond, Trevor Cohn

Recent approaches to multilingual open-domain question answering (MLODQA) have achieved promising results given abundant language-specific training data. However, the considerable annotation cost limits the application o…

Few-Shot LearningOpen-Domain Question AnsweringQuestion Answering