PATTY: A Taxonomy of Relational Patterns with Semantic Types

By Ndapandula Nakashole, Gerhard Weikum, Fabian M. Suchanek. Conference on Empirical Methods in Natural Language Processing, 2012

442 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/b162c99873c929447bb7ff48d454867aa83f375c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Mohit Bansal
2. Zhiyuan Liu
3. Yejin Choi
4. Xu Han
5. Percy Liang
6. Yoshua Bengio
7. Yi Tay
8. Luke S. Zettlemoyer

Citations in the corpus

• Machine Translation Detection from Monolingual Web-Text (2013, background): “…(Nie et al., 1999; Shi et al., 2006; Ishisaka et al., 2009; Jiang et al., 2009) corpus that can be used for training statistical models for NLP tools, as well as for building a large-scale knowledge-base (Suchanek et al., 2007; Zhu et al., 2009; Fader et al., 2011; Nakashole et al., 2012).”
• Biperpedia: An Ontology for Search Applications (2014, methodology): “In this respect, Biperpedia is very similar to the Patty System [20].”
• A Review of Relational Machine Learning for Knowledge Graphs (2015, background): “Unstructured Yes Knowledge Vault [28], NELL [6], PATTY [29], PROSPERA [30], DeepDive/Elementary [31]”
• Core techniques of question answering systems over knowledge bases: a survey (2017, unknown): “This is used in the pattern library PATTY (Nakashole et al. 2012 Figure 7.”
• Natural Language Questions for the Web of Data (2012, unknown): “For relations, Nakashole et al. (2012) released PATTY, a large taxonomy of patterns with semantic types.”
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, methodology): “, 2010), more formats of patterns (Nakashole et al., 2012; Jiang et al., 2017), and more efficient ways of extraction (Zheng et al.”
• Retrieving Textual Evidence for Knowledge Graph Facts (2019, methodology): “To do this, ROXXI makes use of textual patterns available in PATTY [20] to rank these documents using a language modeling based approach.”
• Language-Aware Truth Assessment of Fact Candidates (2014, methodology): “Our phrase typing method is similar to prior work on typing relational phrases (Nakashole et al., 2012).”
• COMET: Commonsense Transformers for Automatic Knowledge Graph Construction (2019, background): “…extracting semi-structured text (Suchanek et al., 2007; Hoffart et al., 2013; Auer et al., 2007; Bollacker et al., 2008) and unstructured text (Dong et al., 2014; Carlson et al., 2010; Nakashole et al., 2011, 2012; Niu, 2012) into relational schemas that can be queried for downstream applications.”
• Multilingual Question Answering over Linked Data (QALD-3): Lab Overview (2013, unknown): “Resources CASIA Intui2 SWIP RTV WordNet [4] + + - Wikipedia - + - + PATTY(8) [12] + - - Tools CASIA Intui2 SWIP RTV WS4J (WordNet Similarity for Java)(9) - + - Chaos parser [2] - - - + MaltParser [13] - - + Stanford CoreNLP [9] + + - Jena ARQ query engine - + - Lucene(10) - - - + LARQ (Lucene + ARQ)”
• Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, background): “PATTY first extracts binary relations between entities from the web.”
• Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules (2021, methodology): “…(Suchanek et al., 2007; Hoffart et al., 2013; Auer et al., 2007) and unstructured (Dong et al., 2014; Carlson et al., 2010; Mitchell et al., 2018; Nakashole et al., 2012) text extraction, COMET uses transfer learning to adapt language models to generate knowledge graph tuples by learning on…”
• NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction (2020, methodology): “In addition to KBs, labeling rules are also important means of representing domain knowledge [25], which can be automatically mined from large corpora [14, 21].”
• PPDB: The Paraphrase Database (2013, background): “…will explore extensions to PPDB to include aspects of related large-scale resources such as lexical-semantic hierarchies (Snow et al., 2006), textual inference rules (Berant et al., 2011), relational patterns (Nakashole et al., 2012), and (lexical) conceptual networks (Navigli and Ponzetto, 2012).”
• Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations (2016, background): “, 2007; Banko and Etzioni, 2008) or cluster the patterns (sometimes in context-sensitive way) to form relations (Lin and Pantel, 2001; Yao et al., 2011; Nakashole et al., 2012; Yao et al., 2012).”
• ExFaKT: A Framework for Explaining Facts over Knowledge Graphs and Text (2019, methodology): “, verbalization) using paraphrasing dictionaries for relations such as PATTY [26] and entity-mentions dictionaries for entity name aliases.”