The FrameNet (FN) project, developed at ICSI since 1997, was the first lexical resource based on Frame Semantics, and documents contemporary English. It has inspired related projects in roughly a dozen other languages, which, while based on frame semantics, have evolved somewhat independently. Multilingual FrameNet (MLFN) is an attempt to find alignments between them all. The degree to which these projects have adhered to Berkeley FrameNet frames and the data release on which they are based varies, complicating the alignment problem. To minimize the resources needed to accomplish the task, we will rely mainly on machine learning to produce the alignments. We describe the various projects and their history, and how we intend to use tools from the fields of machine translation and document classification to introduce a new relation of similarity between frames, combining structural and distributional similarity, and how this will contribute to the unification of the FrameNet projects, while allowing them to continue to evolve independently.
@InProceedings{GILARDI18.11, author = {Luca Gilardi and Collin Baker}, title = {Learning to Align across Languages: Toward Multilingual FrameNet}, booktitle = {Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)}, year = {2018}, month = {may}, date = {7-12}, location = {Miyazaki, Japan}, editor = {Tiago Timponi Torrent and Lars Borin and Collin F. Baker}, publisher = {European Language Resources Association (ELRA)}, address = {Paris, France}, isbn = {979-10-95546-04-7}, language = {english} }
Summary of the paper