Papers by Andrew Cattle
Recognizing Humour using Word Associations and Humour Anchor Extraction (C18-1)
Copied to clipboard
| Challenge: | Using humour anchors to improve the performance of humor recognition and interpretation is difficult for computers. |
| Approach: | They propose to use word associations to improve humour recognition models by using humor anchors to improve the performance of semantic features. |
| Outcome: | The proposed models improve the performance of humour recognition and interpretation tasks. |
Embedding Lexical Features via Tensor Decomposition for Small Sample Humor Recognition (D19-1)
Copied to clipboard
| Challenge: | Existing methods for humor recognition require a large amount of training data with labels to learn effective features. |
| Approach: | They propose a tensor embedding method that can extract lexical humor features for continuous humor recognition by using word-word co-occurrence to encode contextual content of documents, and then decompose the tenor to get corresponding vector representations. |
| Outcome: | The proposed method achieves a distance of 0.887 on a global humor ranking task, comparable to the top performing systems from SemEval 2017 Task 6B, but without the need for any external training corpus. |