Greenformer: Factorization Toolkit for Efficient Deep Neural Networks

Cahyawijaya, Samuel; Winata, Genta Indra; Lovenia, Holy; Wilie, Bryan; Dai, Wujiao; Ishii, Etsuko; Fung, Pascale

doi:10.48550/arxiv.2109.06762

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prompt-based learning has been successfully applied to various NLP applications, including machine translation, summarization (Radford et al, 2019), question answering (Petroni et al, 2019;Jiang et al, 2020), fact checking , text classification (Schick and Schütze, 2021a,b), relation extraction (Gao et al, 2020b;, and multimodal learning (Tsimpoukelli et al, 2021). Cahyawijaya et al (2021) explored matrix factorization (Winata et al, 2019(Winata et al, , 2020 to accelerate the prompt-based inference. As with every machine learning technique, prompt-based learning comes with pros and cons.…”

Section: Related Workmentioning

confidence: 99%

Few-Shot Bot: Prompt-Based Learning for Dialogue Systems

Madotto,

Lin,

Winata

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Learning to converse using only a few examples is a great challenge in conversational AI. The current best conversational models, which are either good chit-chatters (e.g., Blender-Bot) or goal-oriented systems (e.g., MinTL), are language models (LMs) fine-tuned on large conversational datasets. Training these models is expensive, both in terms of computational resources and time, and it is hard to keep them up to date with new conversational skills.A simple yet unexplored solution is prompt-based few-shot learning (Brown et al., 2020) which does not require gradient-based fine-tuning but instead uses a few examples in the LM context as the only source of learning. In this paper, we explore prompt-based few-shot learning in dialogue tasks. We benchmark LMs of different sizes in nine response generation tasks, which include four knowledge-grounded tasks, a task-oriented generations task, three open-chat tasks, and controlled stylistic generation, and five conversational parsing tasks, which include dialogue state tracking, graph path generation, persona information extraction, document retrieval, and internet query generation. The current largest released LM (GPT-J-6B) using prompt-based few-shot learning, and thus requiring no training, achieves competitive performance to fully trained state-of-the-art models. Moreover, we propose a novel prompt-based few-shot classifier, that also does not require any fine-tuning, to select the most appropriate prompt given a dialogue history. Finally, by combining the power of prompt-based few-shot learning and a Skill Selector, we create an end-to-end chatbot named the Few-Shot Bot (FSB), which automatically selects the most appropriate conversational skill, queries different knowledge bases or the internet, and uses the retrieved knowledge to generate a human-like response, all using only few dialogue examples per skill.

show abstract