Papers by Robert Ross
Language-Driven Region Pointer Advancement for Controllable Image Captioning (2020.coling-main)
Copied to clipboard
| Challenge: | Controllable Image Captioning is a recent sub-task of Image Captions wherein constraints are placed on which regions in an image should be described in the generated natural language caption. |
| Approach: | They propose a method for predicting the timing of region pointer advancement by treating the advancement step as a natural part of the language structure via a NEXT-token. |
| Outcome: | The proposed method agrees with ground-truth timing in the Flickr30k Entities test data with a precision of 86.55% and a recall of 97.92%. |
AxCell: Automatic Extraction of Results from Machine Learning Papers (2020.emnlp-main)
Copied to clipboard
Marcin Kardas, Piotr Czapla, Pontus Stenetorp, Sebastian Ruder, Sebastian Riedel, Ross Taylor, Robert Stojnic
| Challenge: | AxCell is an automatic machine learning pipeline for extracting results from papers . it uses a table segmentation subtask to learn relevant structural knowledge that aids extraction. |
| Approach: | They propose to use a table segmentation subtask to learn relevant structural knowledge that aids extraction. |
| Outcome: | The proposed approach improves state of the art for results extraction and can be used for semi-automated results extraction in production. |