We introduce a novel task, zero-shot video captioning, that aims at describing out-of-domain videos of unseen activities. We propose a principled Topic-Aware Mixture of Experts (TAMoE) model for zero-shot video captioning, which learns to compose different experts based on different topic embeddings, implicitly transferring the knowledge learned from seen activities to unseen ones (AAAI 2019). [Code] [Paper]
We aim at predicting new facts under a challenging setting where only one training instance is available. We propose a one-shot relational learning framework, which utilizes the knowledge extracted by embedding models and learns a matching metric by considering both the learned embeddings and one-hop graph structures (EMNLP 2018). [Code] [Paper]
We present WikiHow, a dataset of more than 230,000 article and summary pairs extracted and constructed from an online knowledge base written by different human authors. The articles span a wide range of topics and therefore represent high diversity styles. [Data] [Paper]
With globalization, the need for providing cross-lingual customer support becomes more urgent than ever. However, cross-lingual support poses great challenges - it requires a large amount of additional annotated data from native speakers. In order to bypass the expensive human annotation and achieve the first step towards the ultimate goal of building a universal dialog system, we set out to build a cross-lingual state tracking framework (EMNLP 2018). [Code] [Paper]
We propose a novel scheduled policy optimization mechanism which dynamically schedules demonstration learning and reinforcement learning and addresses the discrepancy between training and inference in sequence decoding (IJCAI-ECAI 2018). [Code] [Paper]
We exploit the generating emotional language of leveraging Twitter data that are naturally labeled with emojis. We investigate several conditional variational autoencoders training on conversations, which allow us to use emojis to control the emotion of the generated text (ACL 2018). [Code] [Paper]
We propose an Adversarial REward Learning (AREL) framework to learn an implicit reward function from human demonstrations, and then optimize policy search with the learned reward function (ACL 2018). [Code] [Paper]
We propose generative models for three types of extra-grammatical word formation phenomena abounding in English slang: Blends, Clippings, and Reduplicatives (NAACL-HLT 2018). [Code] [Paper]
We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models (NAACL-HLT 2018). [Code] [Paper]
We describe a novel reinforcement learning framework for learning multi-hop relational paths: we use a policy-based agent with continuous states based on knowledge graph embeddings, which reasons in a KG vector space by sampling the most promising relation to extend its path (EMNLP 2017). [Code] [Paper]