A complete survey on generative ai (aigc): Is chatgpt from gpt-4 to gpt-5 all you need?

C Zhang, C Zhang, S Zheng, Y Qiao, C Li… - arXiv preprint arXiv …, 2023 - arxiv.org
As ChatGPT goes viral, generative AI (AIGC, aka AI-generated content) has made headlines
everywhere because of its ability to analyze and create text, images, and beyond. With such …

Recent advances in deep learning based dialogue systems: A systematic survey

J Ni, T Young, V Pandelea, F Xue… - Artificial intelligence review, 2023 - Springer
Dialogue systems are a popular natural language processing (NLP) task as it is promising in
real-life applications. It is also a complicated task since many NLP tasks deserving study are …

Cline: Contrastive learning with semantic negative examples for natural language understanding

D Wang, N Ding, P Li, HT Zheng - arXiv preprint arXiv:2107.00440, 2021 - arxiv.org
Despite pre-trained language models have proven useful for learning high-quality semantic
representations, these models are still vulnerable to simple perturbations. Recent works …

Positive, negative and neutral: Modeling implicit feedback in session-based news recommendation

S Gong, KQ Zhu - Proceedings of the 45th international ACM SIGIR …, 2022 - dl.acm.org
News recommendation for anonymous readers is a useful but challenging task for many
news portals, where interactions between readers and articles are limited within a temporary …

Open-domain dialogue generation: What we can do, cannot do, and should do next

K Kann, A Ebrahimi, J Koh, S Dudy… - Proceedings of the 4th …, 2022 - par.nsf.gov
Human–computer conversation has long been an interest of artificial intelligence and
natural language processing research. Recent years have seen a dramatic improvement in …

Dialogue response selection with hierarchical curriculum learning

Y Su, D Cai, Q Zhou, Z Lin, S Baker, Y Cao… - arXiv preprint arXiv …, 2020 - arxiv.org
We study the learning of a matching model for dialogue response selection. Motivated by the
recent finding that models trained with random negative samples are not ideal in real-world …

[PDF][PDF] A Survey on Response Selection for Retrieval-based Dialogues.

C Tao, J Feng, R Yan, W Wu, D Jiang - IJCAI, 2021 - academia.edu
Building an intelligent dialogue system capable of naturally and coherently conversing with
humans has been a long-standing goal of artificial intelligence. In the past decade, with the …

Synthesizing adversarial negative responses for robust response ranking and evaluation

P Gupta, Y Tsvetkov, JP Bigham - arXiv preprint arXiv:2106.05894, 2021 - arxiv.org
Open-domain neural dialogue models have achieved high performance in response ranking
and evaluation tasks. These tasks are formulated as a binary classification of responses …

Persona-Guided Planning for Controlling the Protagonist's Persona in Story Generation

Z Zhang, J Wen, J Guan, M Huang - arXiv preprint arXiv:2204.10703, 2022 - arxiv.org
Endowing the protagonist with a specific personality is essential for writing an engaging
story. In this paper, we aim to control the protagonist's persona in story generation, ie …

Intent-calibrated Self-training for Answer Selection in Open-domain Dialogues

W Deng, J Pei, Z Ren, Z Chen, P Ren - Transactions of the …, 2023 - direct.mit.edu
Answer selection in open-domain dialogues aims to select an accurate answer from
candidates. The recent success of answer selection models hinges on training with large …