Topic memory networks for short text classification

J Zeng, J Li, Y Song, C Gao, MR Lyu, I King - arxiv preprint arxiv …, 2018 - arxiv.org
Many classification models work poorly on short texts due to data sparsity. To address this
issue, we propose topic memory networks for short text classification with a novel topic …

From statistical methods to deep learning, automatic keyphrase prediction: A survey

B **e, J Song, L Shao, S Wu, X Wei, B Yang… - Information Processing …, 2023 - Elsevier
Keyphrase prediction aims to generate phrases (keyphrases) that highly summarizes a
given document. Recently, researchers have conducted in-depth studies on this task from …

Neural keyphrase generation via reinforcement learning with adaptive rewards

HP Chan, W Chen, L Wang, I King - arxiv preprint arxiv:1906.04106, 2019 - arxiv.org
Generating keyphrases that summarize the main points of a document is a fundamental task
in natural language processing. Although existing generative models are capable of …

Summarizing medical conversations via identifying important utterances

Y Song, Y Tian, N Wang, F **a - Proceedings of the 28th …, 2020 - aclanthology.org
Summarization is an important natural language processing (NLP) task in identifying key
information from text. For conversations, the summarization systems need to extract salient …

Topic-aware neural keyphrase generation for social media language

Y Wang, J Li, HP Chan, I King, MR Lyu… - arxiv preprint arxiv …, 2019 - arxiv.org
A huge volume of user-generated content is daily produced on social media. To facilitate
automatic language understanding, we study keyphrase prediction, distilling salient …

Incorporating context-relevant concepts into convolutional neural networks for short text classification

J Xu, Y Cai, X Wu, X Lei, Q Huang, H Leung, Q Li - Neurocomputing, 2020 - Elsevier
Text classification is an important task in natural language processing. Previous text
classification models do not perform well on short texts due to the data sparsity problem. In …

Generative non-autoregressive unsupervised keyphrase extraction with neural topic modeling

X Zhu, Y Lou, J Zhao, W Gao, H Deng - Engineering Applications of …, 2023 - Elsevier
Unsupervised keyphrase extraction (UKE) aims to detect out a set of keyphrases of a
document without using any annotation signal for training the UKE model. Existing UKE …

Keyword extraction: a modern perspective

T Nomoto - SN Computer Science, 2022 - Springer
The goal of keyword extraction is to extract from a text, words, or phrases indicative of what it
is talking about. In this work, we look at keyword extraction from a number of different …

Emotion-infused deep neural network for emotionally resonant conversation

YC Chang, YC Hsing - Applied Soft Computing, 2021 - Elsevier
The widespread development of conversational agents (chatbots) has enabled us to
communicate and collaborate with different forms and functions of robots using natural …

AMFF: A new attention-based multi-feature fusion method for intention recognition

C Liu, X Xu - Knowledge-based systems, 2021 - Elsevier
Intention recognition is based on a dialog between users to identify their real intentions,
which plays a key role in the question answering system. However, the content of a dialog is …