T
Tian Lan
Researcher at Beijing Institute of Technology
Publications - 36
Citations - 157
Tian Lan is an academic researcher from Beijing Institute of Technology. The author has contributed to research in topics: Computer science & Context (language use). The author has an hindex of 2, co-authored 11 publications receiving 22 citations.
Papers
More filters
Journal ArticleDOI
Language Models Can See: Plugging Visual Controls in Text Generation
TL;DR: A training-free framework for plugging in visual controls in the generation process and enabling LMs to perform multimodal tasks (e.g., image captioning) in a zero-shot manner, which outperforms the state-of-the-art method by notable margins with a nearly 27 times decoding speedup.
Journal ArticleDOI
PONE: A Novel Automatic Evaluation Metric for Open-domain Generative Dialogue Systems
TL;DR: This paper proposes a novel and feasible learning-based metric that can significantly improve the correlation with human judgments by using augmented POsitive samples and valuable NEgative samples, called PONE.
Journal ArticleDOI
Food recommendation with graph convolutional network
TL;DR: This work proposes a novel model Food recommendation with Graph Convolutional Network (FGCN), which exploits ingredient-ingredient, ingredient-recipe, and recipe-user relations deeply and could alleviate the sparsity issue in food recommendation.
Proceedings ArticleDOI
Multi-Objective Reinforcement Learning with Non-Linear Scalarization
TL;DR: This paper considers the problem of MORL where multiple objectives are combined using a non-linear scalarization, and proposes a solution using steady-state occupancy measures and long-term average rewards to maximize the scalarized objective.
Posted Content
PONE: A Novel Automatic Evaluation Metric for Open-Domain Generative Dialogue Systems
TL;DR: This article proposed a learning-based metric that can significantly improve the correlation with human judgments by using augmented POsitive samples and valuable NEgative samples, called PONE, which significantly outperforms the state-of-the-art learningbased evaluation methods with an average correlation improvement of 13.18%.