From Stanford University's Computer Science mavens via arXiv.org:
Abel L Peirson V, E Meltem Tolunay
(Submitted on 8 Jun 2018)
We introduce a novel meme generation system, which given any image can produce a humorous and relevant caption. Furthermore, the system can be conditioned on not only an image but also a user-defined label relating to the meme template, giving a handle to the user on meme content. The system uses a pretrained Inception-v3 network to return an image embedding which is passed to an attention-based deep-layer LSTM model producing the caption - inspired by the widely recognised Show and Tell Model. We implement a modified beam search to encourage diversity in the captions. We evaluate the quality of our model using perplexity and human assessment on both the quality of memes generated and whether they can be differentiated from real ones. Our model produces original memes that cannot on the whole be differentiated from real ones.
| Comments: | Stanford CS 224n Project |
| Subjects: | Computation and Language (cs.CL); Learning (cs.LG) |
| Cite as: | arXiv:1806.04510 [cs.CL] |
| (or arXiv:1806.04510v1 [cs.CL] for this version) |
arXiv download page (9 page PDF)
