Machine Reading of Historical Events

Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.

[1]  Mark Steedman,et al.  Lexical Event Ordering with an Edge-Factored Model , 2015, NAACL.

[2]  Adam Jatowt,et al.  Estimating document focus time , 2013, CIKM.

[3]  James Pustejovsky,et al.  SemEval-2013 Task 1: TempEval-3: Evaluating Time Expressions, Events, and Temporal Relations , 2013, *SEMEVAL.

[4]  Roi Reichart,et al.  Neural Structural Correspondence Learning for Domain Adaptation , 2016, CoNLL.

[5]  Klaus Berberich,et al.  Diversifying Search Results Using Time , 2015 .

[6]  Christopher D. Manning,et al.  Learning Constraints for Consistent Timeline Extraction , 2012, EMNLP.

[7]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[8]  Gerhard Weikum,et al.  As Time Goes By: Comprehensive Tagging of Textual Phrases with Temporal Scopes , 2016, WWW.

[9]  H. Wool.  THE RELATION BETWEEN MEASURES OF CORRELATION IN THE UNIVERSE OF SAMPLE PERMUTATIONS , 1944 .

[10]  Klaus Berberich,et al.  Estimating Event Focus Time Using Neural Word Embeddings , 2017, CIKM.

[11]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[12]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[13]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[14]  Jian Zhang,et al.  SQuAD: 100,000+ Questions for Machine Comprehension of Text , 2016, EMNLP.

[15]  Jian Sun,et al.  Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[16]  Oren Etzioni,et al.  Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge , 2018, ArXiv.

[17]  Jürgen Schmidhuber,et al.  Bidirectional LSTM Networks for Improved Phoneme Classification and Recognition , 2005, ICANN.

[18]  Luke S. Zettlemoyer,et al.  AllenNLP: A Deep Semantic Natural Language Processing Platform , 2018, ArXiv.

[19]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[20]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[21]  Ido Dagan,et al.  Creating a Large Benchmark for Open Information Extraction , 2016, EMNLP.

[22]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[23]  Eneko Agirre,et al.  SemEval-2015 Task 4: TimeLine: Cross-Document Event Ordering , 2015, *SEMEVAL.

[24]  Marie-Francine Moens,et al.  Temporal Information Extraction by Predicting Relative Time-lines , 2018, EMNLP.

[25]  M. Kendall.  A NEW MEASURE OF RANK CORRELATION , 1938 .

[26]  Domenico Ursino,et al.  Leveraging linked entities to estimate focus time of short texts , 2018, IDEAS.

[27]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[28]  Razvan C. Bunescu,et al.  Using Encyclopedic Knowledge for Named entity Disambiguation , 2006, EACL.

[29]  M. Kendall.  The treatment of ties in ranking problems. , 1945, Biometrika.