Name
Abstract | ||
|---|---|---|
Automatic abstractive summaries are found to often distort or fabricate facts in the article. This inconsistency between summary and original text has seriously impacted its applicability. We propose a fact-aware summarization model FASum to extract and integrate factual relations into the summary generation process via graph attention. We then design a factual corrector model FC to automatically correct factual errors from summaries generated by existing systems. Empirical results show that the fact-aware summarization can produce abstractive summaries with higher factual consistency compared with existing systems, and the correction model improves the factual consistency of given summaries via modifying only a few keywords. |
Year | Venue | DocType |
|---|---|---|
2021 | NAACL-HLT | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
7 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Chenguang Zhu | 1 | 328 | 22.92 |
| William Hinthorn | 2 | 0 | 0.34 |
| Ruochen Xu | 3 | 14 | 6.64 |
| Qingkai Zeng | 4 | 23 | 6.82 |
| Michael Zeng | 5 | 4 | 6.85 |
| Xuedong Huang | 6 | 1390 | 283.19 |
| Meng Jiang | 7 | 0 | 0.34 |