A
Alexander Koller
Researcher at Saarland University
Publications - 141
Citations - 2901
Alexander Koller is an academic researcher from Saarland University. The author has contributed to research in topics: Parsing & Dependency grammar. The author has an hindex of 27, co-authored 125 publications receiving 2399 citations. Previous affiliations of Alexander Koller include Max Planck Society & Columbia University.
Papers
More filters
Proceedings ArticleDOI
Climbing towards NLU: On Meaning, Form, and Understanding in the Age of Data.
Emily M. Bender,Alexander Koller +1 more
TL;DR: It is argued that a system trained only on form has a priori no way to learn meaning, and a clear understanding of the distinction between form and meaning will help guide the field towards better science around natural language understanding.
Proceedings Article
Learning Script Knowledge with Web Experiments
TL;DR: A novel approach to unsupervised learning of the events that make up a script, along with constraints on their temporal ordering, is described, including a graph representation of the script's temporal structure using a multiple sequence alignment algorithm.
Journal ArticleDOI
The Constraint Language for Lambda Structures
TL;DR: This paper presents the Constraint Language for Lambda Structures (CLLS), a first-order language for semantic underspecification that conservatively extends dominance constraints and is interpreted overlambda structures, tree-like structures that encode λ-terms.
Proceedings Article
Report on the second NLG challenge on generating instructions in virtual environments (GIVE-2)
Alexander Koller,Kristina Striegnitz,Andrew Gargett,Donna Byron,Justine Cassell,Robert Dale,Johanna D. Moore,Jon Oberlander +7 more
TL;DR: The second installment of the Challenge on Generating Instructions in Virtual Environments (GIVE-2), a shared task for the NLG community which took place in 2009--10, is described and the results of this evaluation are reported.
Proceedings ArticleDOI
Generation as Dependency Parsing
TL;DR: This work shows how to convert TAG generation problems into dependency parsing problems, which is useful because optimizations in recent dependency parsers based on constraint programming tackle exactly the combinatorics that make generation hard.