DIRT @SBT@discovery of inference rules from text

By Dekang Lin, Patrick Pantel. Knowledge Discovery and Data Mining, 2001

568 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

View Paper: https://www.semanticscholar.org/paper/f3f9a848dca0a80ef64987a9dd511ee6b7e19cd1

How researchers see this paper

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

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Estimating Linear Models for Compositional Distributional Semantics (2010, methodology): “Lin and Pantel (2001) propose the pattern distributional hypothesis that extends the distributional hypothesis for speciﬁc patterns, i.e. word sequences representing partial verb phrases.”
A Confidence Model for Syntactically-Motivated Entailment Proofs (2011, methodology): “DIRT (Lin and Pantel, 2001), would be utilized naturally by substitution of a complete sub-tree by another, which cannot be performed by the above tree-edit-distance operations.”
Large Scale Acquisition of Paraphrases for Learning Surface Patterns (2008, methodology): “Lin and Pantel (2001) and Szpektor et al. (2004) proposed methods to obtain entailment templates by using a single monolingual resource.”
From Frequency to Meaning: Vector Space Models of Semantics (2010, methodology): “Lin and Pantel (2001) proposed the extended distributional hypothesis, that patterns that co-occur with similar pairs tend to have similar meanings.”
Semantic Annotation for Textual Entailment Recognition (2012, methodology): “Furthermore, BIUTEE utilizes lexical and lexicalsyntactic rules learned from knowledge resources such as, inter alia, WordNet [12, 25], FrameNet [1], VerbOcean [7], Catvar [15], Lin Similarity [20], and DIRT [21].”
Composition in Distributional Models of Semantics (2010, background): “A different type of semantic space is proposed in Lin and Pantel (2001) (see also Turney and Pantel, 2010).”
Directional distributional similarity for lexical inference (2010, background): “…assumption seems to conform with the idea of feature inclusion, yet Szpektor and Dagan (2008) show that filtering with the directional LEDIR did not improve the performance of the original symmetric discovery of inference rules from text (DIRT) resource (Lin and Pantel 2001) in their evaluation.”
Quantifying Similarity between Relations with Fact Distribution (2019, background): “…is attached in the Appendix F. some redundant relations in KBs. Recently, some efforts are devoted to Open Relation Extraction (Open RE) (Lin and Pantel, 2001; Yao et al., 2011; Marcheggiani and Titov, 2016; ElSahar et al., 2017), aiming to cluster relation patterns into several relation types…”
Robust Textual Inference via Graph Matching (2005, methodology): “Dependency Folding: As in (Lin and Pantel, 2001), we found it useful to fold certain dependencies (such as modifying prepositions) so that modifiers became labels connecting the modifier’s governor and dependent directly.”
Efficient Search for Transformation-based Inference (2012, methodology): “Typical examples for knowledge resources of such rules are DIRT (Lin and Pantel, 2001), and TEASE (Szpektor et al.”
Open question answering over curated and extracted knowledge bases (2014, background): “We follow previous work on mining equivalent relations [19, 29] and count the number of shared argument-pairs between two relation phrases.”
Discrete-State Variational Autoencoders for Joint Discovery and Factorization of Relations (2016, methodology): “This baseline is very similar to the standard unsupervised relation extraction method DIRT (Lin and Pantel, 2001). The HAC cut-off parameter was set to 0.95 based on the development set performance. We used the same feature representation for all the models, including the baselines. We also report r”
Extracting implicit knowledge from text (2009, background): “, X wrote Y if and only if X is the author of Y (Lin and Pantel, 2001; Bhagat, 2009); and common verb-verb relations, e.”
Large-scale Semantic Parsing via Schema Matching and Lexicon Extension (2013, methodology): “For instance, the DIRT system (Lin and Pantel, 2001) uses the mutual information between the (X,Y ) argument pairs for two binary relations to measure the similarity between them, and clusters relations accordingly.”
Learning Answer-Entailing Structures for Machine Comprehension (2015, methodology): “String edit Features: In addition to looking for features on exact word/phrase match, we also add features using two paraphrase databases ParaPara (Chan et al., 2011) and DIRT (Lin and Pantel, 2001).”
Unsupervised Learning of Semantic Relations between Concepts of a Molecular Biology Ontology (2005, background): “…of Protein-Protein interaction " positively-regulate " is equivalent to " activate " , " up-regulate " , " derepress " , " stimulate " etc. Representing relations as dependency paths one can frame this problem straightforwardly as that of finding paraphrases (e.g. as in [Lin and Pantel, 2001]).”
Structured Relation Discovery using Generative Models (2011, methodology): “For example, DIRT (Lin and Pantel, 2001) aims to discover different representations of the same semantic relation, i.e. similar dependency paths.”
A Continuously Growing Dataset of Sentential Paraphrases (2017, background): “for developing machine learning models that identify paraphrases and measure semantic similarities. Non-sentential Paraphrase Data There are other phrasal and syntactic paraphrase data, such as DIRT (Lin and Pantel, 2001), POLY (Grycner et al., 2016), PATTY (Nakashole et al., 2012), DEFIE (Bovi et a”