Text: now in 2D! A framework for lexical expansion with contextual similarity

Biemann, Chris; Riedl, Martin

doi:10.15398/jlm.v1i1.60

Cited by 83 publications

(77 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative approaches are e.g., graph-based algorithms (Biemann and Riedl, 2013) or ranking functions from information retrieval (Claveau et al, 2014).…”

Section: Distributional Semanticsmentioning

confidence: 99%

Exploring Diachronic Lexical Semantics with JeSemE

Hellrich¹,

Hahn²

2017

Proceedings of ACL 2017, System Demonstrations

View full text Add to dashboard Cite

Recent advances in distributional semantics combined with the availability of large-scale diachronic corpora offer new research avenues for the Digital Humanities. JESEME, the Jena Semantic Explorer, renders assistance to a non-technical audience to investigate diachronic semantic topics. JESEME runs as a website with query options and interactive visualizations of results, as well as a REST API for access to the underlying diachronic data sets.

show abstract

“…Alternative approaches are e.g., graph-based algorithms (Biemann and Riedl, 2013) or ranking functions from information retrieval (Claveau et al, 2014).…”

Section: Distributional Semanticsmentioning

confidence: 99%

Exploring Diachronic Lexical Semantics with JeSemE

Hellrich¹,

Hahn²

2017

Proceedings of ACL 2017, System Demonstrations

View full text Add to dashboard Cite

show abstract

“…To this end, we use the linked disambiguated distributional KBs from 1 , which are built in three steps: 1) Learning a JoBimText model. Initially, a sense inventory is created from a large text collection using the pipeline of the JoBimText project (Biemann and Riedl, 2013). 2 The resulting structure contains disambiguated protoconcepts (i.e., senses), their similar and related terms, as well as aggregated contextual clues per proto-concept.…”

Section: Resources Usedmentioning

confidence: 99%

The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links

Faralli

Panchenko

Biemann

et al. 2017

Proceedings of the 15th Conference of the European Chapter of The Association for Computational Linguistics: Volume 1

Self Cite

View full text Add to dashboard Cite

In this paper, we present ContrastMedium, an algorithm that transforms noisy semantic networks into full-fledged, clean taxonomies. ContrastMedium is able to identify the embedded taxonomy structure from a noisy knowledge graph without explicit human supervision such as, for instance, a set of manually selected input root and leaf concepts. This is achieved by leveraging structural information from a companion reference taxonomy, to which the input knowledge graph is linked (either automatically or manually). When used in conjunction with methods for hypernym acquisition and knowledge base linking, our methodology provides a complete solution for end-to-end taxonomy induction. We conduct experiments using automatically acquired knowledge graphs, as well as a SemEval benchmark, and show that our method is able to achieve high performance on the task of taxonomy induction.

show abstract

“…1) Learning a JoBimText model: initially, we automatically create a sense inventory from a large text collection using the pipeline of the JoBimText project [2,22] 1 . The resulting structure contains disambiguated proto-concepts (i.e.…”

Section: Building a Hybrid Aligned Resourcementioning

confidence: 99%

“…Following [2], we apply a holing operation where each observation in the text is split into a term and its context. The 1000 most significant contexts per term, as determined by the LMI significance measure [8], serve as a representation for the term, and term similarity is defined as the number of common contexts.…”

Section: Learning a Jobimtext Modelmentioning

confidence: 99%

Linked Disambiguated Distributional Semantic Networks

Faralli

Panchenko

Biemann

et al. 2016

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Abstract. We present a new hybrid lexical knowledge base that combines the contextual information of distributional models with the conciseness and precision of manually constructed lexical networks. The computation of our countbased distributional model includes the induction of word senses for single-word and multi-word terms, the disambiguation of word similarity lists, taxonomic relations extracted by patterns and context clues for disambiguation in context. In contrast to dense vector representations, our resource is human readable and interpretable, and thus can be easily embedded within the Semantic Web ecosystem.

show abstract

Text: now in 2D! A framework for lexical expansion with contextual similarity

Abstract: Keywords: distributional semantics, lexical expansion, contextual similarity, lexical substitution, computational semantics [ 58 ] [ 59 ] [ 61 ]

Cited by 83 publications

References 46 publications

Exploring Diachronic Lexical Semantics with JeSemE

Exploring Diachronic Lexical Semantics with JeSemE

The ContrastMedium Algorithm: Taxonomy Induction From Noisy Knowledge Graphs With Just A Few Links

Linked Disambiguated Distributional Semantic Networks

Contact Info

Product

Resources

About