Generating Questions from Wikidata Triples

no code implementations • LREC 2022 • Kelvin Han, Thiago castro Ferreira, Claire Gardent

Question generation from knowledge bases (or knowledge base question generation, KBQG) is the task of generating questions from structured database information, typically in the form of triples representing facts.

Knowledge Base Question Answering Question Generation +1

Comparing PTB and UD information for PDTB discourseconnective identification

no code implementations • JEPTALNRECITAL 2020 • Kelvin Han, Phyllicia Leavitt, Srilakshmi Balard

Our work on the automatic detection of English discourse connectives in the Penn Discourse Treebank (PDTB) shows that syntactic information from the Universal Dependencies (UD) framework is a viable alternative to that from the Penn Treebank (PTB) framework.

Discourse Parsing POS +1

Exploring the Combination of Contextual Word Embeddings and Knowledge Graph Embeddings

no code implementations • 17 Apr 2020 • Lea Dieudonat, Kelvin Han, Phyllicia Leavitt, Esteban Marquer

``Classical'' word embeddings, such as Word2Vec, have been shown to capture the semantics of words based on their distributional properties.

Entity Typing Knowledge Graph Embeddings +1