Ultra-Fine Entity Typing

We introduce a new entity typing task: given a sentence with an entity mention, the goal is to predict a set of free-form phrases (e.g. skyscraper, songwriter, or criminal) that describe appropriate types for the target entity. This formulation allows us to use a new type of distant supervision at large scale: head words, which indicate the type of the noun phrases they appear in. We show that these ultra-fine types can be crowd-sourced, and introduce new evaluation sets that are much more diverse and fine-grained than existing benchmarks. We present a model that can predict open types, and is trained using a multitask objective that pools our new head-word supervision with prior supervision from entity linking. Experimental results demonstrate that our model is effective in predicting entity types at varying granularity; it achieves state of the art performance on an existing fine-grained entity typing benchmark, and sets baselines for our newly-introduced datasets. Our data and model can be downloaded from: this http URL

[1]  George A. Miller,et al.  WordNet: A Lexical Database for English , 1995, HLT.

[2]  Eneko Agirre,et al.  Selectional Preferences for Semantic Role Classification , 2013, CL.

[3]  Heike Adel,et al.  Noise Mitigation for Neural Entity Typing and Relation Extraction , 2016, EACL.

[4]  Andrew McCallum,et al.  Finer Grained Entity Typing with TypeNet , 2017, AKBC@NIPS.

[5]  Mudhakar Srivatsa,et al.  Improving Semantic Parsing via Answer Type Inference , 2016, EMNLP.

[6]  Hinrich Schütze,et al.  End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification , 2017, EACL.

[7]  Nevena Lazic,et al.  Embedding Methods for Fine Grained Entity Type Classification , 2015, ACL.

[8]  Gerhard Weikum,et al.  FINET: Context-Aware Fine-Grained Named Entity Typing , 2015, EMNLP.

[9]  Oren Etzioni,et al.  Named Entity Recognition in Tweets: An Experimental Study , 2011, EMNLP.

[10]  Rahul Gupta,et al.  Knowledge base completion via search-based question answering , 2014, WWW.

[11]  Ashish Anand,et al.  Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings , 2017, EACL.

[12]  Patrick Pantel,et al.  ISP: Learning Inferential Selectional Preferences , 2007, NAACL.

[13]  Heng Ji,et al.  CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases , 2016, WWW.

[14]  Gerhard Weikum,et al.  HYENA: Hierarchical Type Classification for Entity Names , 2012, COLING.

[15]  Nevena Lazic,et al.  Context-Dependent Fine-Grained Entity Type Tagging , 2014, ArXiv.

[16]  Dan Roth,et al.  Entity Linking via Joint Encoding of Types, Descriptions, and Context , 2017, EMNLP.

[17]  Kentaro Inui,et al.  An Attentive Neural Architecture for Fine-grained Entity Type Classification , 2016, AKBC@NAACL-HLT.

[18]  Dan Klein,et al.  A Joint Model for Entity Analysis: Coreference, Typing, and Linking , 2014, TACL.

[19]  Luke S. Zettlemoyer,et al.  End-to-end Neural Coreference Resolution , 2017, EMNLP.

[20]  Krisztian Balog,et al.  Hierarchical target type identification for entity-oriented queries , 2012, CIKM.

[21]  Hinrich Schütze,et al.  Corpus-level Fine-grained Entity Typing Using Contextual Information , 2015, EMNLP.

[22]  Dan Klein,et al.  Fine-Grained Entity Typing with High-Multiplicity Assignments , 2017, ACL.

[23]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[24]  Mitchell P. Marcus,et al.  OntoNotes: The 90% Solution , 2006, NAACL.

[25]  Daniel S. Weld,et al.  Fine-Grained Entity Recognition , 2012, AAAI.

[26]  Fernando Pereira,et al.  Wikilinks: A Large-scale Cross-Document Coreference Corpus Labeled via Links to Wikipedia , 2012 .

[27]  Olivier Raiman,et al.  DeepType: Multilingual Entity Linking by Neural Type System Evolution , 2018, AAAI.

[28]  Tim Van de Cruys,et al.  A Neural Network Approach to Selectional Preference Acquisition , 2014, EMNLP.

[29]  Heng Ji,et al.  Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding , 2016, KDD.

[30]  Ramesh Nallapati,et al.  Multi-instance Multi-label Learning for Relation Extraction , 2012, EMNLP.

[31]  Andrew McCallum,et al.  Universal schema for entity type prediction , 2013, AKBC '13.

[32]  P. Resnik Selectional constraints: an information-theoretic model and its computational realization , 1996, Cognition.

[33]  Hong Sun,et al.  A Hybrid Neural Model for Type Classification of Entity Mentions , 2015, IJCAI.