Abstract | ||
---|---|---|
Recent years have shown that graphs are an adequate text representation model for summarization. For this years' TAC up- date summarization challenge, we ex- tended our graph-based summarization system with coreference relations and sen- tence compression. Our results show that using coreference relations did not result in a significant performance gain; sen- tence compression had a negative effect on performance. We participated in the opinion summarization task with our base graph-based system. The measured per- formance of our opinion summarization system was competitive with respect to re- sponsiveness, and poor with respect to lin- guistic quality. |
Year | Venue | Field |
---|---|---|
2008 | TAC | Text graph,Automatic summarization,Graph,Coreference,Information retrieval,Computer science,Sentence compression,Natural language processing,Artificial intelligence |
DocType | Citations | PageRank |
Conference | 4 | 0.39 |
References | Authors | |
11 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Iris Hendrickx | 1 | 285 | 30.91 |
Wauter Bosma | 2 | 97 | 10.83 |