Name
Abstract | ||
|---|---|---|
We investigate the influence of information status (IS) on constituent order in German, and integrate our findings into a loglinear surface realisation ranking model. We show that the distribution of pairs of IS categories is strongly asymmetric. Moreover, each category is correlated with morphosyntactic features, which can be automatically detected. We build a loglinear model that incorporates these asymmetries for ranking German string realisations from input LFG F-structures. We show that it achieves a statistically significantly higher BLEU score than the baseline system without these features. |
Year | Venue | Keywords |
|---|---|---|
2009 | ACL/IJCNLP | constituent order,morphosyntactic feature,ranking german string realisation,loglinear model,incorporating information status,baseline system,information status,generation ranking,input lfg f-structures,ranking model,bleu score,loglinear surface realisation,log linear model |
Field | DocType | Volume |
Ranking,Computer science,Realisation,Natural language processing,Artificial intelligence,Log-linear model,Baseline system,Machine learning,German | Conference | P09-1 |
Citations | PageRank | References |
10 | 0.61 | 8 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Aoife Cahill | 1 | 404 | 35.53 |
| Arndt Riester | 2 | 35 | 6.01 |