Connecting the Dots: Event Graph Schema Induction with Path Language Modeling. Li, M., Zeng, Q., Lin, Y., Cho, K., Ji, H., May, J., Chambers, N., & Voss, C. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 684–695, Online, November, 2020. Association for Computational Linguistics. Paper abstract bibtex Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.
@inproceedings{li-etal-2020-connecting,
title = "Connecting the Dots: Event Graph Schema Induction with Path Language Modeling",
author = "Li, Manling and
Zeng, Qi and
Lin, Ying and
Cho, Kyunghyun and
Ji, Heng and
May, Jonathan and
Chambers, Nathanael and
Voss, Clare",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://www.aclweb.org/anthology/2020.emnlp-main.50",
pages = "684--695",
abstract = "Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.",
}
Downloads: 0
{"_id":"hJZmcGm4R8y2CpLKs","bibbaseid":"li-zeng-lin-cho-ji-may-chambers-voss-connectingthedotseventgraphschemainductionwithpathlanguagemodeling-2020","author_short":["Li, M.","Zeng, Q.","Lin, Y.","Cho, K.","Ji, H.","May, J.","Chambers, N.","Voss, C."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","title":"Connecting the Dots: Event Graph Schema Induction with Path Language Modeling","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Manling"],"suffixes":[]},{"propositions":[],"lastnames":["Zeng"],"firstnames":["Qi"],"suffixes":[]},{"propositions":[],"lastnames":["Lin"],"firstnames":["Ying"],"suffixes":[]},{"propositions":[],"lastnames":["Cho"],"firstnames":["Kyunghyun"],"suffixes":[]},{"propositions":[],"lastnames":["Ji"],"firstnames":["Heng"],"suffixes":[]},{"propositions":[],"lastnames":["May"],"firstnames":["Jonathan"],"suffixes":[]},{"propositions":[],"lastnames":["Chambers"],"firstnames":["Nathanael"],"suffixes":[]},{"propositions":[],"lastnames":["Voss"],"firstnames":["Clare"],"suffixes":[]}],"booktitle":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","month":"November","year":"2020","address":"Online","publisher":"Association for Computational Linguistics","url":"https://www.aclweb.org/anthology/2020.emnlp-main.50","pages":"684–695","abstract":"Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.","bibtex":"@inproceedings{li-etal-2020-connecting,\n title = \"Connecting the Dots: Event Graph Schema Induction with Path Language Modeling\",\n author = \"Li, Manling and\n Zeng, Qi and\n Lin, Ying and\n Cho, Kyunghyun and\n Ji, Heng and\n May, Jonathan and\n Chambers, Nathanael and\n Voss, Clare\",\n booktitle = \"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)\",\n month = nov,\n year = \"2020\",\n address = \"Online\",\n publisher = \"Association for Computational Linguistics\",\n url = \"https://www.aclweb.org/anthology/2020.emnlp-main.50\",\n pages = \"684--695\",\n abstract = \"Event schemas can guide our understanding and ability to make predictions with respect to what might happen next. We propose a new Event Graph Schema, where two event types are connected through multiple paths involving entities that fill important roles in a coherent story. We then introduce Path Language Model, an auto-regressive language model trained on event-event paths, and select salient and coherent paths to probabilistically construct these graph schemas. We design two evaluation metrics, instance coverage and instance coherence, to evaluate the quality of graph schema induction, by checking when coherent event instances are covered by the schema graph. Intrinsic evaluations show that our approach is highly effective at inducing salient and coherent schemas. Extrinsic evaluations show the induced schema repository provides significant improvement to downstream end-to-end Information Extraction over a state-of-the-art joint neural extraction model, when used as additional global features to unfold instance graphs.\",\n}\n\n","author_short":["Li, M.","Zeng, Q.","Lin, Y.","Cho, K.","Ji, H.","May, J.","Chambers, N.","Voss, C."],"key":"li-etal-2020-connecting","id":"li-etal-2020-connecting","bibbaseid":"li-zeng-lin-cho-ji-may-chambers-voss-connectingthedotseventgraphschemainductionwithpathlanguagemodeling-2020","role":"author","urls":{"Paper":"https://www.aclweb.org/anthology/2020.emnlp-main.50"},"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://jonmay.github.io/webpage/cutelabname/cutelabname.bib","dataSources":["ZdhKtP2cSp3Aki2ge","X5WBAKQabka5TW5z7","hbZSwot2msWk92m5B","fcWjcoAgajPvXWcp7","GvHfaAWP6AfN6oLQE","j3Qzx9HAAC6WtJDHS","5eM3sAccSEpjSDHHQ"],"keywords":[],"search_terms":["connecting","dots","event","graph","schema","induction","path","language","modeling","li","zeng","lin","cho","ji","may","chambers","voss"],"title":"Connecting the Dots: Event Graph Schema Induction with Path Language Modeling","year":2020}