Name
Abstract | ||
|---|---|---|
We introduce entity post-modifier generation as an instance of collaborative writing task. Given sentence about target entity, the task is to automatically generate post-modifier phrase that provides contextually relevant information about the entity. For example, for the sentence, Barack Obama, _______, supported the #MeToo movement., the phrase a father of two girls is contextually relevant post-modifier. To this end, we build PoMo, post-modifier dataset created automatically from news articles reflecting journalistic need for incorporating entity information that is relevant to particular news event. PoMo consists of more than 231K sentences with post-modifiers and associated facts extracted from Wikidata for around 57K unique entities. We use crowdsourcing to show that modeling contextual relevance is necessary for accurate post-modifier generation. We adapt number of existing generation approaches as baselines for this dataset. Our results show there is large room for improvement in terms of both identifying relevant facts to include (knowing which claims are relevant gives u003e20% improvement in BLEU score), and generating appropriate post-modifier text for the context (providing relevant claims is not sufficient for accurate generation). We conduct an error analysis that suggests promising directions for future research. |
Year | Venue | Field |
|---|---|---|
2019 | arXiv: Computation and Language | Computer science,Artificial intelligence,Natural language processing |
DocType | Volume | Citations |
Journal | abs/1904.03111 | 0 |
PageRank | References | Authors |
0.34 | 0 | 8 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Jun Seok Kang | 1 | 67 | 3.81 |
| Robert L. Logan IV | 2 | 12 | 3.50 |
| Zewei Chu | 3 | 12 | 3.57 |
| Yang Chen | 4 | 0 | 0.68 |
| Dheeru Dua | 5 | 38 | 4.95 |
| Kevin Gimpel | 6 | 1545 | 79.71 |
| Sameer Singh | 7 | 1060 | 71.63 |
| Niranjan Balasubramanian | 8 | 862 | 55.98 |