306 citations · 742 across the 41 of their papers we have counts for
9 papers · 1 filter
Predicting Events in MOBA Games: Prediction, Attribution, and Evaluation
Zelong Yang, Yan Wang, Piji Li +4
The multiplayer online battle arena (MOBA) games have become increasingly popular in recent years. Consequently, many efforts have been devoted to providing pre-game or in-game pre…
Consistency and Coherency Enhanced Story Generation
Wei Wang, Piji Li, Hai-Tao Zheng
Story generation is a challenging task, which demands to maintain consistency of the plots and characters throughout the story. Previous works have shown that GPT2, a large-scale l…
Dialogue Generation on Infrequent Sentence Functions via Structured Meta-Learning
Yifan Gao, Piji Li, Wei Bi +3
Sentence function is an important linguistic feature indicating the communicative purpose in uttering a sentence. Incorporating sentence functions into conversations has shown impr…
Enhancing Dialogue Generation via Multi-Level Contrastive Learning
Xin Li, Piji Li, Yan Wang +2
Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture t…
Exclusive Hierarchical Decoding for Deep Keyphrase Generation
Wang Chen, Hou Pong Chan, Piji Li +1
Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. A new setting is recently introduced into this problem, in which, given a documen…
Salience Estimation with Multi-Attention Learning for Abstractive Text Summarization
Piji Li, Lidong Bing, Zhongyu Wei +1
Attention mechanism plays a dominant role in the sequence generation models and has been used to improve the performance of machine translation and abstractive text summarization.…
SongNet: Rigid Formats Controlled Text Generation
Piji Li, Haisong Zhang, Xiaojiang Liu +1
Neural text generation has made tremendous progress in various tasks. One common characteristic of most of the tasks is that the texts are not restricted to some rigid formats when…
An Empirical Investigation of Pre-Trained Transformer Language Models for Open-Domain Dialogue Generation
Piji Li
We present an empirical investigation of pre-trained Transformer-based auto-regressive language models for the task of open-domain dialogue generation. Training paradigm of pre-tra…
A Neural Topical Expansion Framework for Unstructured Persona-oriented Dialogue Generation
Minghong Xu, Piji Li, Haoran Yang +4
Unstructured Persona-oriented Dialogue Systems (UPDS) has been demonstrated effective in generating persona consistent responses by utilizing predefined natural language user perso…