paper-with-me

Papers

Elaboration-Generating Commonsense Question Answering at Scale

2022-09-02 · Wenya Wang, Vivek Srikumar, Hanna Hajishirzi, Noah A. Smith

In question answering requiring common sense, language models (e.g., GPT-3) have been used to generate text expressing background knowledge that helps improve performance. Yet the cost of working with such models is very high; in this work, we finetune smaller language models to generate useful intermediate context, referred to here as elaborations. Our framework alternates between updating two language models -- an elaboration generator and an answer predictor -- allowing each to influence the other. Using less than 0.5% of the parameters of GPT-3, our model outperforms alternatives with similar sizes and closes the gap on GPT-3 on four commonsense question answering benchmarks. Human evaluations show that the quality of the generated elaborations is high.

📄 PDF Abstract BibTeX arXiv:2209.01232

Code (1)

happywwy/elabor 공식 구현 pytorch

Tasks

Common Sense ReasoningQuestion Answering

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…
Weight Decay 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
15 Ways to Contact How can i speak to someone at Delta Airlines 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…

Similar Papers 제목 키워드 기반

Generated Knowledge Prompting for Commonsense Reasoning

2021-11-16 · ACL ARR November 2021 11 · Anonymous

It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated know…

Language ModelingLanguage ModellingOpen-Ended Question Answering

Generated Knowledge Prompting for Commonsense Reasoning

2021-10-15 · ACL 2022 5 · Jiacheng Liu, Alisa Liu, Ximing Lu, Sean Welleck 외

It remains an open question whether incorporating external knowledge benefits commonsense reasoning while maintaining the flexibility of pretrained sequence models. To investigate this question, we develop generated know…

Language ModelingLanguage ModellingOpen-Ended Question Answering

ChatGPT is a Knowledgeable but Inexperienced Solver: An Investigation of Commonsense Problem in Large Language Models

2023-03-29 · Ning Bian, Xianpei Han, Le Sun, Hongyu Lin 외

Large language models (LLMs) have made significant progress in NLP. However, their ability to memorize, represent, and leverage commonsense knowledge has been a well-known pain point. In this paper, we specifically focus…

Instruction Following

ArT: All-round Thinker for Unsupervised Commonsense Question-Answering

2021-12-26 · Jiawei Wang, Hai Zhao

Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like k…

AllQuestion Answering

ArT: All-round Thinker for Unsupervised Commonsense Question Answering

2022-10-01 · COLING 2022 10 · Jiawei Wang, Hai Zhao

Without labeled question-answer pairs for necessary training, unsupervised commonsense question-answering (QA) appears to be extremely challenging due to its indispensable unique prerequisite on commonsense source like k…

AllQuestion Answering