Generative Pre-Trained Transformer for Design Concept Generation: An Exploration

Zhu, Qihao; Luo, Jianxi

doi:10.1017/pds.2022.185

Cited by 37 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Zhu and Luo (2021) fine-tune GPT-2 for mapping the problems (including categories) to solutions using problem-solution data obtained from RedDot 54 . They also explore the capabilities of GPT-3 that support analogy-by-design in terms of generating text descriptions upon providing source-target domain labels as inputs.…”

Section: Discussionmentioning

confidence: 99%

Natural language processing in-and-for design research

2022

View full text Add to dashboard Cite

We review the scholarly contributions that utilise natural language processing (NLP) techniques to support the design process. Using a heuristic approach, we gathered 223 articles that are published in 32 journals within the period 1991–present. We present state-of-the-art NLP in-and-for design research by reviewing these articles according to the type of natural language text sources: internal reports, design concepts, discourse transcripts, technical publications, consumer opinions and others. Upon summarising and identifying the gaps in these contributions, we utilise an existing design innovation framework to identify the applications that are currently being supported by NLP. We then propose a few methodological and theoretical directions for future NLP in-and-for design research.

show abstract

Section: Discussionmentioning

confidence: 99%

Natural language processing in-and-for design research

2022

View full text Add to dashboard Cite

show abstract

“…BERT only encodes and generates a language model, so an encoder is enough. It has powerful ability to learn and understand natural language representations such as BERT [14], GPT [17], ELECTRA [18], etc.…”

Section: Related Work a Pre-trained Language Modelsmentioning

confidence: 99%

Dialogue Logic Aware and Key Utterance Decoupling Model for Multi-Party Dialogue Reading Comprehension

Yang

Gao

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Multi-party dialogue machine reading comprehension (MRC) brings an unprecedented challenge due to the multiple speakers and the complex discourse linkages among speaker-aware utterances. The majority of current methods only consider the textual aspects of dialogue situations, and pay little attention to crucial speaker-aware cues. This prevents a model from capturing the speaker's intention and important discourse information for questions in a complex discourse relationship, leading to the model giving wrong answers. In this paper, we construct a dialogue logic graph module by the relational graph convolutional network (R-GCN) to structure the dialogue information, and design a speaker prediction task to enhance the ability to capture discourse logic. Additionally, we construct a key utterance information decoupling module that focuses on the key discourse information flow involve questions, and filters out noise information. Extensive experiments FriendsQA and Molweni show that our approach outperforms competitive baselines and current state-of-the-art models, especially when dealing with more rounds of dialogue and questions involving people, events and time.

show abstract

“…Furthermore, the hybrid model has obtained a greater accuracy Recently, large language models based on transformers [26] have achieved remarkable success in learning language representations through the utilization of vast amounts of data. Prominent examples of such models are OpenAI GPT [27], BERT [28], and RoBERTa [29]. These models have demonstrated exceptional performance when fine-tuned for various downstream tasks such as text classification, question answering, and natural language inference.…”

Section: Mandal and Senmentioning

confidence: 99%

Bengali Text Classification: A New multi-class Dataset and Performance Evaluation of Machine Learning and Deep Learning Models

Roy

Sarkar

Mandal

2023

Preprint

View full text Add to dashboard Cite

This study focuses on Bengali text classification using machine learning and deep learning techniques. Text classification is a fundamental task in natural language processing (NLP) that involves categorizing text documents into predefined categories or classes. While text classification has received considerable attention in the English language, there is a limited amount of research specifically addressing Bengali text classification. This gap in the literature highlights the need for exploring and developing effective techniques tailored to the Bengali language. Furthermore, although some datasets for Bengali text classification tasks have been produced, most of the datasets have a limited number of labels. In our work, we introduce a new dataset for the Bengali text classification task, which has 38 class labels. The dataset includes data from the leading Bengali newspapers. We have evaluated many state-of-the-art machine learning and deep learning classification methods on our dataset to construct a benchmark that will facilitate future research.

show abstract

Generative Pre-Trained Transformer for Design Concept Generation: An Exploration

Cited by 37 publications

References 38 publications

Natural language processing in-and-for design research

Natural language processing in-and-for design research

Dialogue Logic Aware and Key Utterance Decoupling Model for Multi-Party Dialogue Reading Comprehension

Bengali Text Classification: A New multi-class Dataset and Performance Evaluation of Machine Learning and Deep Learning Models

Contact Info

Product

Resources

About