Generative Event Schema Induction with Entity Disambiguation
Published 1 January 2015Open access
Kiem-Hieu Nguyen, Xavier Tannier, Olivier Ferret, Romaric Besançon
Citations65
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper presents a generative model to event schema induction that precisely represents elements other than head words using probabilistic topic distributions and illustrates that such information plays an important role in parameter estimation.
Abstract
Conference of 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 ; Conference Date: 26 July 2015 Through 31 July 2015; Conference Code:114195
Keywords
Computer Science
Journal of Machine Learning ResearchLatent dirichlet allocation
27,049 Citations2003David M. Blei, Andrew Y. Ng +1 more
The Stanford CoreNLP Natural Language Processing Toolkit
7,238 Citations2014Christopher D. Manning, Mihai Surdeanu +4 more
The design and use of the Stanford CoreNLP toolkit is described, an extensible pipeline that provides core natural language analysis, and it is suggested that this follows from a simple, approachable design, straightforward interfaces, the inclusion of robust and good quality analysis components, and not requiring use of a large amount of associated baggage.
Message Understanding Conference-6
1,365 Citations1996Ralph Grishman, Beth Sundheim
MUC-6 introduced several innovations over prior MUCs, most notably in the range of different tasks for which evaluations were conducted and the motivations for the new format.
Unsupervised Learning of Narrative Event Chains
565 Citations2008Nathanael Chambers, Dan Jurafsky
A three step process to learning narrative event chains using unsupervised distributional methods to learn narrative relations between events sharing coreferring arguments and introduces two evaluations: the narrative cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order.
Unsupervised learning of narrative schemas and their participants
410 Citations2009Nathanael Chambers, Dan Jurafsky
An unsupervised system for learning narrative schemas, coherent sequences or sets of events whose arguments are filled with participant semantic roles defined over words to improve on previous results in narrative/frame learning and induce rich frame-specific semantic roles.
Discovering relations among named entities from large corpora
403 Citations2004Takaaki Hasegawa, Satoshi Sekine +1 more
Using one year of newspapers reveals not only that the relations among named entities could be detected with high recall and precision, but also that appropriate labels could be automatically provided for the relations.
Cognitive ScienceLanguage and Memory*
337 Citations1980Roger C. Schank
A theory of MOPs (Memory Organization Packets), which serve as both processors and organizers of information in memory, enables effective categorization of experiences in episodic memory, which in turn enables better predictive understanding of new experiences.
Preemptive information extraction using unrestricted relation discovery
240 Citations2006Yusuke Shinyama, Satoshi Sekine
A technique called Unrestricted Relation Discovery is proposed that discovers all possible relations from texts and presents them as tables in order to extend the boundary of Information Extraction systems.
Template-Based Information Extraction without the Templates
172 Citations2011Nathanael Chambers, Dan Jurafsky
This paper describes an approach to template-based IE that removes this requirement and performs extraction without knowing the template structure in advance, and induces template structure very similar to hand-created gold structure from raw text.
Statistical Script Learning with Multi-Argument Events
146 Citations2014Karl Pichotta, Raymond J. Mooney
Experiments on a large corpus using the task of inferring held-out events and the “narrative cloze evaluation” demonstrate that modeling multi-argument events improves predictive accuracy.
On-demand information extraction
142 Citations2006Satoshi Sekine
On-demand Information Extraction (ODIE) aims to completely eliminate the customization effort, and is reported on on experimental results in which the system created useful tables for many topics, demonstrating the feasibility of this approach.
Learning Script Knowledge with Web Experiments
126 Citations2010Michaela Regneri, Alexander Koller +1 more
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.
Event Schema Induction with a Probabilistic Entity-Driven Model
123 Citations2013Nathanael Chambers
This paper presents the first generative model for schema induction that integrates coreference chains into learning, and matches the pipeline’s performance, and outperforms the HMM by 7 F1 points.
A unified model of phrasal and sentential evidence for information extraction
117 Citations2009Siddharth Patwardhan, Ellen Riloff
A new model for event extraction is presented that jointly considers both the local context around a phrase along with the wider sentential context in a probabilistic framework and performs well in comparison to existing IE systems that rely on local phrasal context.
Empirical Methods in Natural Language ProcessingEffective Information Extraction with Semantic Affinity Patterns and Relevant Regions
112 Citations2007Siddharth Patwardhan, Ellen Riloff
An information extraction system that decouples the tasks of finding relevant regions of text and applying extraction patterns is presented, using a self-trained relevant sentence classifier to identify relevant regions, and using a semantic affinity measure to automatically learn domain-relevant extraction patterns.
Generating Coherent Event Schemas at Scale
111 Citations2013Niranjan Balasubramanian, Stephen Soderland +2 more
This work presents a novel approach to inducing open-domain event schemas that overcomes limitations of Chambers and Jurafsky's (2009) schemas and uses cooccurrence statistics of semantically typed relational triples, which it calls Rel-grams (relational n- grams).
arXiv (Cornell University)Probabilistic Frame Induction
84 Citations2013Jackie Chi Kit Cheung, Hoifung Poon +1 more
This paper proposes the first probabilistic approach to frame induction, which incorporates frames, events, and participants as latent topics and learns those frame and event transitions that best explain the text.
Clustering for unsupervised relation identification
63 Citations2007Benjamin Rosenfeld, Ronen Feldman
A clustering evaluation metric is developed, specifically adapted for the relation identification task, and it is found that using both kinds of features with the best of the algorithms produces very high-precision results, significantly improving over the previous work.
Inducing Neural Models of Script Knowledge
62 Citations2014Ashutosh Modi, Ivan Titov
This work induces common sense knowledge about prototypical sequence of events in the form of graphs based on distributed representations of predicates and their arguments, and then these representations are used to predict prototypical event orderings.
Automatic creation of domain templates
51 Citations2006Elena Filatova, Vasileios Hatzivassiloglou +1 more
This work proposes a novel methodology for corpus analysis based on cross-examination of several document collections representing different instances of the same domain and shows that this methodology can be used for automatic domain template creation.
A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge
49 Citations2014Lea Frermann, Ivan Titov +1 more
A hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities is presented and substantially outperforms a state-of-the-Art method on the event ordering task.
Empirical Methods in Natural Language ProcessingExtreme Extraction -- Machine Reading in a Week
27 Citations2011Marjorie Freedman, Lance Ramshaw +5 more
It is shown that while the recall of the handwritten rules surpasses that of the learning system, the learned system is able to improve the overall recall and F1.
Unsupervised Discovery of Event Scenarios from Texts
26 Citations2008Cosmin A. Bejan
A new unsupervised learning approach for discovering event scenarios from texts that uses the Latent Dirichlet Allocation probabilistic model to automatically learn the probability distribution of events corresponding to event scenarios.
Unsupervised Relation Extraction From Web Documents.
26 Citations2008Kathrin Eichler, Holmer Hemsen +1 more
In this paper, preliminary evaluation results of these components are presented and an overview is given of possible enhancements to improve the relation extraction and clustering components of the IDEX system.
Incremental topic representations
23 Citations2004Sanda M. Harabagiu
Two incremental enhancements of the topic signatures introduced by Lin and Hovy are described, the first of which considers topic representations in terms of relevant topic relations instead of relevant terms and the second based on ranking the topic themes.
Third message understanding evaluation and conference (MUC-3)
19 Citations1991Beth Sundheim
The Naval Ocean Systems Center is conducting the third in a series of evaluations of English text analysis systems, finding that task-oriented tests enable straightforward comparisons among systems and provide useful quantitative data on the state of the art in text understanding.
Text Segmentation and Graph-based Method for Template Filling in Information Extraction
14 Citations2011Ludovic Jean‐Louis, Romaric Besançon +1 more
A twostep approach for template filling is proposed: first, an event-based segmentation is performed to select the parts of the text related to the target event; then, a graph-based method is applied to choose the most relevant entities in these parts for characterizing the event.
Lecture notes in computer scienceAn Information Extraction Customizer
7 Citations2014Ralph Grishman, Yifan He
This work has developed a toolset which is able to analyze a corpus and aid the user in building the specifications of the entity and relation types.
Modeling Context in Scenario Template Creation
5 Citations2008Long Qiu, Min‐Yen Kan +1 more
HAL (Le Centre pour la Communication Scientifique Directe)An Aggregation Procedure for Building Episodic Memory
4 Citations1997Olivier Ferret, Brigitte Grau
A system, MLK (Memorization for Learning Knowledge), that organizes specific situations in an episodic memory by aggregating the similar ones in a single unit and leads to a progressive enrichment and generalization of the overall situations and of their specific features.
Unsupervised relation learning for event-focused question-answering and domain modelling
1 Citations2008Kathleen McKeown, Elena Filatova
A formal model for efficient information packaging that is based on mapping the information selection task onto the set cover complexity problem and outline and implement information selection algorithms that are provably optimal polynomial-time approximations for information selection tasks that have a limit on the output size.