Papers by Amir Soleimani
NonFactS: NonFactual Summary Generation for Factuality Evaluation in Document Summarization (2023.findings-acl)
Copied to clipboard
| Challenge: | Pre-trained abstractive summarization models generate fluent summaries that are inconsistent with context document and contain nonfactual information. |
| Approach: | They propose a data generation model that synthesizes nonfactual summaries using human annotations. |
| Outcome: | The proposed model can generate nonfactual summaries and generalize to out-of-domain documents. |
NLQuAD: A Non-Factoid Long Question Answering Data Set (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing data sets for document-level question answering are limited in their ability to detect short text and require multiple-sentence descriptive answers and opinions. |
| Approach: | They introduce a new data set with baseline methods for non-factoid long question answering . they compare BERT, RoBERTa, and Longformer models to establish baseline performances . |
| Outcome: | Experimental results show that Longformer outperforms the other architectures but human evaluations show that it is far behind the human upper bound. |