In natural language generation, different generation tasks often interact with each other in a complex way, which is hard to capture in the pipeline architecture described by Reit...
Our aim of participating in this year’s High Accuracy Retrieval from Documents (HARD) track is to explore the possibility of developing an automated HARD retrieval model by leve...
After retrieval, this simple strategy yield to an important improvement of the average precision: from 17.02 up to 35.80. Task II. Our approach is based on argumentative structurin...