4 papers
Visual Semantic Parsing: From Images to Abstract Meaning Representation
Mohamed Ashraf Abdelsalam, Zhan Shi, Federico Fancellu +4
The success of scene graphs for visual scene understanding has brought attention to the benefits of abstracting a visual input (e.g., image) into a structured representation, where…
Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
Xiaoyu Yang, Xiaodan Zhu, Zhan Shi +1
While recent research on natural language inference has considerably benefited from large annotated datasets, the amount of inference-related knowledge (including commonsense) prov…
Unsupervised Conversation Disentanglement through Co-Training
Hui Liu, Zhan Shi, Xiaodan Zhu
Conversation disentanglement aims to separate intermingled messages into detached sessions, which is a fundamental task in understanding multi-party conversations. Existing work on…
Toward Diverse Text Generation with Inverse Reinforcement Learning
Zhan Shi, Xinchi Chen, Xipeng Qiu +1
Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these m…