Learning Syntactic Patterns for Automatic Hypernym Discovery

By Rion Snow, Dan Jurafsky, Andrew Y. Ng. Neural Information Processing Systems, 2004

838 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/e703e928bc07900527c368db2428d0d5c57148c2

How researchers see this paper

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

Citations in the corpus

PPDB 2.0: Better paraphrase ranking, fine-grained entailment relations, word embeddings, and style classification (2015, background): “Work that is relevant to our classiﬁcation of semantic entailment types to each paraphrase, includes learning directionality of inference rules (Bhagat et al., 2007; Berant et al., 2011) and learning hypernyms rather than paraphrases (Snow et al., 2004).”
pair2vec: Compositional Word-Pair Embeddings for Cross-Sentence Inference (2018, methodology): “Mining Textual Patterns There is extensive literature on mining textual patterns to predict relations between words (Hearst, 1992; Snow et al., 2005; Turney, 2005; Riedel et al., 2013; Van de Cruys, 2014; Toutanova et al., 2015; Shwartz and Dagan, 2016).”
Extracting implicit knowledge from text (2009, methodology): “, a dog is-a animal), which have been known for years to be amenable to automatic extraction (Hearst, 1992; Snow et al., 2005).”
Open Information Extraction Using Wikipedia (2010, methodology): “Snow et al. (Snow et al., 2005) utilize WordNet to learn dependency path patterns for extracting the hypernym relation from text.”
Learning New Facts From Knowledge Bases With Neural Tensor Networks and Semantic Word Vectors (2013, background): “tion answering (Siri), information retrieval (Google Knowledge Graph), or generally providing inference over structured knowledge to users. Much work has focused on extending existing knowledge bases [5, 6, 2] using patterns or classiﬁers applied to large corpora. We introduce a model that can accur”
Characterizing the Errors of Data-Driven Dependency Parsing Models (2007, background): “Syntactic dependency graphs have recently gained a wide interest in the computational linguistics community and have been successfully employed for many problems ranging from machine translation (Ding and Palmer, 2004) to ontology construction (Snow et al., 2004).”
Learning Semantic Hierarchies via Word Embeddings (2014, methodology): “Following the method for discovering patterns automatically (Snow et al., 2005), McNamee et al. (2008) apply the same method to extract hy-pernyms of entities in order to improve the performance of a question answering system.”
Glen, Glenda or Glendale: Unsupervised and Semi-supervised Learning of English Noun Gender (2009, methodology): “Our approach was directly inﬂuenced by the hypernym-extractor of Snow et al. (2005) and we provided an analogous summary in Section 1.”
Conditional Generation and Snapshot Learning in Neural Dialogue Systems (2016, background): “Snapshot learning can be viewed as a special form of weak supervision (also known as distant- or self supervision) (Craven and Kumlien, 1999; Snow et al., 2004), in which supervision signals are heuristically labelled by matching unlabelled corpora with entities or attributes in a structured databas”
Robust Textual Inference via Graph Matching (2005, methodology): “This approach has been successfully used to characterize semantic relationships such as hypernyms (Snow et al., 2004).”
Simple Coreference Resolution with Rich Syntactic and Semantic Features (2009, methodology): “Rather than opt to manually create a set of these coreference patterns as in Hearst (1992), we instead opt to automatically extract these patterns from large corpora as in Snow et al. (2004) and Phillips and Riloff (2007).”
Unsupervised named-entity extraction from the Web: An experimental study (2005, background): “Similarly, richer language models have been used to learn lexico-syntactic patterns that identify examples of the hyponym relation [40].”
On the Systematicity of Probing Contextualized Word Representations: The Case of Hypernymy in BERT (2020, background): “They have long been studied as a core NLP objective in their own right through tasks requiring the identiﬁcation of hypernyms (Hearst, 1992; Snow et al., 2005, 2006), and as components for use in downstream NLP tasks, such as recognizing textual entailment (RTE), metaphor detection, text generation…”
Reading The Web with Learned Syntactic-Semantic Inference Rules (2012, methodology): “The idea of using sequences of dependency edges as features for relation extraction was explored by Snow et al. (2005) and Suchanek et al. (2006).”
Latent Intention Dialogue Models (2017, background): “In addition, self-supervised learning (Snow et al., 2004) (or distant, weak supervision) as a simple way to generate automatic labels by heuristics is popular in many NLP tasks and has been applied to memory networks (Hill et al., 2016) and neural dialogue systems (Wen et al., 2016) recently.”
The Tradeoffs Between Open and Traditional Relation Extraction (2008, methodology): “…extraction patterns is used to seed a bootstrapping process that automatically acquires additional patterns for is-a or part-whole relations (Etzioni et al., 2005; Snow et al., 2005; Girju et al., 2006), It is quite natural then to consider whether the same can be done for all binary relationships.”
Augmenting FrameNet Via PPDB (2014, background): “…from smaller sized collections was higher than the 5 It is worth noting that substituting a larger automatically derived WordNet (as derived in Snow et al. (2004)) could improve the recall of some of the methods which automatically learn a mapping from FrameNet frames to WordNet synsets.”