Event Extraction by Answering (Almost) Natural Questions
Published 1 January 2020Open access
Xinya Du, Claire Cardie
Citations379
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 work introduces a new paradigm for event extraction by formulating it as a question answering (QA) task, which extracts the event arguments in an end-to-end manner and outperforms prior methods substantially.
Abstract
The problem of event extraction requires detecting the event trigger and extracting its corresponding arguments. Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation. To avoid this issue, we introduce a new paradigm for event extraction by formulating it as a question answering (QA) task that extracts the event arguments in an end-to-end manner. Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (i.e., in a zero-shot learning setting).
Keywords
Computer Science
32,525 Citations2019Jacob Devlin, Ming‐Wei Chang +2 more
A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.
SQuAD: 100,000+ Questions for Machine Comprehension of Text
6,328 Citations2016Pranav Rajpurkar, Jian Zhang +2 more
A strong logistic regression model is built, which achieves an F1 score of 51.0%, a significant improvement over a simple baseline (20%).
Transactions of the Association for Computational LinguisticsNatural Questions: A Benchmark for Question Answering Research
1,994 Citations2019Tom Kwiatkowski, Jennimaria Palomaki +16 more
The Natural Questions corpus, a question answering data set, is presented, introducing robust metrics for the purposes of evaluating question answering systems; demonstrating high human upper bounds on these metrics; and establishing baseline results using competitive methods drawn from related literature.
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.
Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks
929 Citations2015Yubo Chen, Liheng Xu +3 more
A word-representation model to capture meaningful semantic regularities for words and a framework based on a convolutional neural network to capture sentence-level clues are introduced.
Joint Event Extraction via Recurrent Neural Networks
665 Citations2016Thien Huu Nguyen, Kyunghyun Cho +1 more
This work proposes to do event extraction in a joint framework with bidirectional recurrent neural networks, thereby benefiting from the advantages of the two models as well as addressing issues inherent in the existing approaches.
Learning to Ask: Neural Question Generation for Reading Comprehension
638 Citations2017Xinya Du, Junru Shao +1 more
An attention-based sequence learning model for the task and the effect of encoding sentence- vs. paragraph-level information is investigated and results show that the system significantly outperforms the state-of-the-art rule-based system.
Automatically generating extraction patterns from untagged text
620 Citations1996Ellen Riloff
This work has developed a system called AutoSlog-TS that creates dictionaries of extraction patterns using only untagged text, and in experiments with the MUG-4 terrorism domain, created a dictionary of extraction pattern that performed comparably to a dictionary created by autoSlog, using only preclassified texts as input.
A Unified MRC Framework for Named Entity Recognition
607 Citations2020Xiaoya Li, Jingrong Feng +4 more
This paper proposes to formulate the task of NER as a machine reading comprehension (MRC) task, and naturally tackles the entity overlapping issue in nested NER: the extraction of two overlapping entities with different categories requires answering two independent questions.
Joint Event Extraction via Structured Prediction with Global Features
478 Citations2013Qi Li, Heng Ji +1 more
This work proposes a joint framework based on structured prediction which extracts triggers and arguments together so that the local predictions can be mutually improved, and proposes to incorporate global features which explicitly capture the dependencies of multiple triggers and argued.
Event Detection and Domain Adaptation with Convolutional Neural Networks
416 Citations2015Thien Huu Nguyen, Ralph Grishman
Convolutional neural networks that overcome the two fundamental limitations of the traditional feature-based approaches to this task: complicated feature engineering for rich feature sets and error propagation from the preceding stages which generate these features are studied.
Refining Event Extraction through Cross-Document Inference
400 Citations2008Heng Ji, Ralph Grishman
This work designs a simple scheme to conduct cross-document inference for improving the ACE event extraction task, and applies the hypothesis of “One Sense Per Discourse” to information extraction.
FigshareGood Question! Statistical Ranking for Question Generation
399 Citations2018Michael Heilman, Noah A. Smith
This work uses manually written rules to perform a sequence of general purpose syntactic transformations to turn declarative sentences into questions, which are ranked by a logistic regression model trained on a small, tailored dataset consisting of labeled output from the system.
Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
398 Citations2018Xiao Liu, Zhunchen Luo +1 more
This paper proposes a novel Jointly Multiple Events Extraction framework to jointly extract multiple event triggers and arguments by introducing syntactic shortcut arcs to enhance information flow and attention-based graph convolution networks to model graph information.
A Joint Neural Model for Information Extraction with Global Features
376 Citations2020Ying Lin, Heng Ji +2 more
A joint neural framework that aims to extract the globally optimal IE result as a graph from an input sentence and can be easily applied to new languages or trained in a multilingual manner, as OneIE does not use any language-specific feature.
arXiv (Cornell University)The Natural Language Decathlon: Multitask Learning as Question Answering
338 Citations2018Bryan McCann, Nitish Shirish Keskar +2 more
Presented on August 28, 2018 at 12:15 p.m. in the Pettit Microelectronics Research Center, Room 102 A/B.
Proceedings of the AAAI Conference on Artificial IntelligenceJointly Extracting Event Triggers and Arguments by Dependency-Bridge RNN and Tensor-Based Argument Interaction
255 Citations2018Lei Sha, Feng Qian +2 more
A novel dependency bridge recurrent neural network (dbRNN) is proposed that simultaneously applying tree structure and sequence structure in RNN brings much better performance than only uses sequential RNN.
Computational LinguisticsSyntactic Processing Using the Generalized Perceptron and Beam Search
214 Citations2011Yue Zhang, Stephen Clark
It is argued that the conceptual and computational simplicity of the framework, together with its language-independent nature, make it a competitive choice for a range of syntactic processing tasks and one that should be considered for comparison by developers of alternative approaches.
Joint Extraction of Events and Entities within a Document Context
214 Citations2016Bishan Yang, Tom M. Mitchell
This paper proposes a novel approach that models the dependencies among variables of events, entities, and their relations, and performs joint inference of these variables across a document to enable access to document-level contextual information and facilitate context-aware predictions.
Broad-coverage sense disambiguation and information extraction with a supersense sequence tagger
211 Citations2006Massimiliano Ciaramita, Yasemin Altün
This paper casts the problem of supersense tagging as a sequential labeling task and investigate it empirically with a discriminatively-trained Hidden Markov Model.
Zero-Shot Transfer Learning for Event Extraction
178 Citations2018Lifu Huang, Heng Ji +4 more
A transferable architecture of structural and compositional neural networks is designed to jointly represent and map event mentions and types into a shared semantic space and can select, for each event mention, the event type which is semantically closest in this space as its type.
Automatic factual question generation from text
177 Citations2011Noah A. Smith, Michael Heilman
This research supports the idea that natural language processing can help teachers efficiently create instructional content by automating the creation of specific type of assessment item and provides solutions to some of the major challenges in question generation.
Overview of the fourth message understanding evaluation and conference
133 Citations1992Beth Sundheim
The Fourth Message Understanding Conference (MUC-4) is the latest in a series of conferences that concern the evaluation of natural language processing (NLP) systems and reports on progress made both in the development of systems capable of analyzing relatively short English texts and in the definition of a rigorous performance evaluation methodology.
Proceedings of the AAAI Conference on Artificial IntelligenceOne for All: Neural Joint Modeling of Entities and Events
128 Citations2019Trung Minh Nguyen, Thien Huu Nguyen
This work proposes a novel model to jointly perform predictions for entity mentions, event triggers and arguments based on the shared hidden representations from deep learning, leading to the state-of-the-art performance for event extraction.
Data IntelligenceJoint Entity and Event Extraction with Generative Adversarial Imitation Learning
110 Citations2019Tongtao Zhang, Heng Ji +1 more
This work proposes a new framework for entity and event extraction based on generative adversarial imitation learning—an inverse reinforcement learning method using a generatives adversarial network (GAN).
Document-Level Event Role Filler Extraction using Multi-Granularity Contextualized Encoding
99 Citations2020Xinya Du, Claire Cardie
This work proposes a novel multi-granularity reader to dynamically aggregate information captured by neural representations learned at different levels of granularity, and evaluates the models on the MUC-4 event extraction dataset, showing that the best system performs substantially better than prior work.
Extracting Entities and Events as a Single Task Using a Transition-Based Neural Model
71 Citations2019Junchi Zhang, Yanxia Qin +3 more
This work builds a first model to this end using a neural transition-based framework, incrementally predicting complex joint structures in a state-transition process, and shows the benefits of the joint model, which gives the best result in the literature.
Peeling Back the Layers: Detecting Event Role Fillers in Secondary Contexts
40 Citations2011Ruihong Huang, Ellen Riloff
This work proposes a multi-layered event extraction architecture that progressively "zooms in" on relevant information that performs better than previous systems on the MUC-4 event extraction data set.