Semantic Understanding of Professional Soccer Commentaries

Hannaneh Hajishirzi, Mohammad Rastegari, Ali Farhadi, Jessica K. Hodgins
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:324-333, 2012.

Abstract

This paper presents a novel approach to the problem of semantic parsing via learning the correspondences between complex sentences and rich sets of events. Our main intuition is that correct correspondences tend to occur more frequently. Our model benefits from a discriminative notion of similarity to learn the correspondence between sentence and an event and a ranking machinery that scores the popularity of each correspondence. Our method can discover a group of events (called macro-events) that best describes a sentence. We evaluate our method on our novel dataset of professional soccer commentaries. The empirical results show that our method significantly outperforms the state-of-theart.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-hajishirzi12a, title = {Semantic Understanding of Professional Soccer Commentaries}, author = {Hajishirzi, Hannaneh and Rastegari, Mohammad and Farhadi, Ali and Hodgins, Jessica K.}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {324--333}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/hajishirzi12a/hajishirzi12a.pdf}, url = {https://proceedings.mlr.press/r10/hajishirzi12a.html}, abstract = {This paper presents a novel approach to the problem of semantic parsing via learning the correspondences between complex sentences and rich sets of events. Our main intuition is that correct correspondences tend to occur more frequently. Our model benefits from a discriminative notion of similarity to learn the correspondence between sentence and an event and a ranking machinery that scores the popularity of each correspondence. Our method can discover a group of events (called macro-events) that best describes a sentence. We evaluate our method on our novel dataset of professional soccer commentaries. The empirical results show that our method significantly outperforms the state-of-theart.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Semantic Understanding of Professional Soccer Commentaries %A Hannaneh Hajishirzi %A Mohammad Rastegari %A Ali Farhadi %A Jessica K. Hodgins %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-hajishirzi12a %I PMLR %P 324--333 %U https://proceedings.mlr.press/r10/hajishirzi12a.html %V R10 %X This paper presents a novel approach to the problem of semantic parsing via learning the correspondences between complex sentences and rich sets of events. Our main intuition is that correct correspondences tend to occur more frequently. Our model benefits from a discriminative notion of similarity to learn the correspondence between sentence and an event and a ranking machinery that scores the popularity of each correspondence. Our method can discover a group of events (called macro-events) that best describes a sentence. We evaluate our method on our novel dataset of professional soccer commentaries. The empirical results show that our method significantly outperforms the state-of-theart. %Z Reissued by PMLR on 04 October 2026.
APA
Hajishirzi, H., Rastegari, M., Farhadi, A. & Hodgins, J.K.. (2012). Semantic Understanding of Professional Soccer Commentaries. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:324-333 Available from https://proceedings.mlr.press/r10/hajishirzi12a.html. Reissued by PMLR on 04 October 2026.

Related Material