fix

content/publication/2020emnlp-regularizing/index.md

@@ -2,7 +2,7 @@
 title: "Regularizing Dialogue Generation by Imitating Implicit Scenarios"
 date: 2020-11-16
 publishDate: 2020-09-30T15:30:29.981130Z
-authors: ["Shaoxiong Feng", "admin", "Hongshen Chen", "Bin Sun", "Kan li", "Xu Sun"]
+authors: ["Shaoxiong Feng", "admin", "Hongshen Chen", "Bin Sun", "Kan Li", "Xu Sun"]
 publication_types: ["1"]
 abstract: "Human dialogues are scenario-based and appropriate responses generally relate to the latent context knowledge entailed by the specific scenario. To enable responses that are more meaningful and context-specific, we propose to improve generative dialogue systems from the scenario perspective, where both dialogue history and future conversation are taken into account to implicitly reconstruct the scenario knowledge. More importantly, the conversation scenarios are further internalized using imitation learning framework, where the conventional dialogue model that has no access to future conversations is effectively regularized by transferring the scenario knowledge contained in hierarchical supervising signals from the scenario-based dialogue model, so that the future conversation is not required in actual inference. Extensive evaluations show that our approach significantly outperforms state-of-the-art baselines on diversity and relevance, and expresses scenario-specific knowledge."
 

content/publication/2021naacl-careful/index.md

@@ -2,7 +2,7 @@
 # Documentation: https://sourcethemes.com/academic/docs/managing-content/
 
 title: "Be Careful about Poisoned Word Embeddings: Exploring the Vulnerability of the Embedding Layers in NLP Models"
-authors: ["Wenkai Yang", "Lei Li", "Zhiyuan Zhang", "admin", "Xu Sun", "Qun Liu"]
+authors: ["Wenkai Yang", "Lei Li", "Zhiyuan Zhang", "admin", "Xu Sun", "Bin He"]
 date: 2021-06-06
 doi: ""