Papers by Huijuan Xu
Syntax Controlled Knowledge Graph-to-Text Generation with Order and Semantic Consistency (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing knowledge graph-to-text generation methods focus on sequence-to sequence generation, but the linearized order of KG is obtained through a heuristic search without data-driven optimization. |
| Approach: | They propose to generate easy-to-understand sentences from the knowledge graph . they incorporate part-of-speech syntactic tags to constrain the positions to copy words from the KG and employ a semantic context scoring function to evaluate the semantic fitness for each word in its local context. |
| Outcome: | The proposed method achieves state-of-the-art on two datasets, WebNLG and DART, and achieves high consistency. |
Disentangled Action Recognition with Knowledge Bases (2022.naacl-main)
Copied to clipboard
| Challenge: | a new method for compositional action recognition is proposed to address the problem of zero-shot learning. |
| Approach: | They propose a method to generalize compositional action recognition models to new verbs and nouns . they use knowledge graphs to extract disentangled feature representations for verbs, noun and type constraint . |
| Outcome: | The proposed approach improves generalization ability of the compositional action recognition model to novel verbs and nouns that are unseen during training time. |