| Abstract | This paper presents Unsupervised Lexical Frame Induction, Task 2 of the International
Workshop on Semantic Evaluation in 2019. Given a set of prespecified syntactic forms in
context, the task requires that verbs and their arguments be clustered to resemble semantic
frame structures. Results are useful in identifying polysemous words, i.e., those whose
frame structures are not easily distinguished, as well as discerning semantic relations of the
arguments. Evaluation of unsupervised frame induction methods fell into two tracks: Task
A) Verb Clustering based on FrameNet 1.7; and B) Argument Clustering, with B.1) based
on FrameNet’s core frame elements, and B.2) on VerbNet 3.2 semantic roles. The shared
task attracted nine teams, of whom three reported promising results. This paper describes
the task and its data, reports on methods and resources that these systems used, and offers acomparison to human annotation.
|
| Acknowledgment | This research was funded by DFG - SFB991. We
thank Timm Lichte, Rainer Oswald, Curt Anderson,
and Kurt Erbach. We also thank the LDC for
its generous support, and the NVIDIA Corporation
for the Titan Xp GPU used in this work.
|
