Hierarchical topic mining via joint spherical tree and text embedding
Mining a set of meaningful topics organized into a hierarchy is intuitively appealing since
topic correlations are ubiquitous in massive text corpora. To account for potential …
topic correlations are ubiquitous in massive text corpora. To account for potential …
TaxoExpan: Self-supervised taxonomy expansion with position-enhanced graph neural network
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for
many web applications. For example, online retailers (eg, Amazon and eBay) use …
many web applications. For example, online retailers (eg, Amazon and eBay) use …
Self-supervised euphemism detection and identification for content moderation
Fringe groups and organizations have a long history of using euphemisms—ordinary-
sounding words with a secret meaning—to conceal what they are discussing. Nowadays …
sounding words with a secret meaning—to conceal what they are discussing. Nowadays …
Multilingual knowledge graph completion via ensemble knowledge transfer
Predicting missing facts in a knowledge graph (KG) is a crucial task in knowledge base
construction and reasoning, and it has been the subject of much research in recent works …
construction and reasoning, and it has been the subject of much research in recent works …
MESED: A multi-modal entity set expansion dataset with fine-grained semantic classes and hard negative entities
The Entity Set Expansion (ESE) task aims to expand a handful of seed entities with new
entities belonging to the same semantic class. Conventional ESE methods are based on …
entities belonging to the same semantic class. Conventional ESE methods are based on …
Hiexpan: Task-guided taxonomy construction by hierarchical tree expansion
Taxonomies are of great value to many knowledge-rich applications. As the manual
taxonomy curation costs enormous human effects, automatic taxonomy construction is in …
taxonomy curation costs enormous human effects, automatic taxonomy construction is in …
Empower entity set expansion via language model probing
Entity set expansion, aiming at expanding a small seed entity set with new entities belonging
to the same semantic class, is a critical task that benefits many downstream NLP and IR …
to the same semantic class, is a critical task that benefits many downstream NLP and IR …
Contrastive learning with hard negative entities for entity set expansion
Entity Set Expansion (ESE) is a promising task which aims to expand entities of the target
semantic class described by a small seed entity set. Various NLP and IR applications will …
semantic class described by a small seed entity set. Various NLP and IR applications will …
Corel: Seed-guided topical taxonomy construction by concept learning and relation transferring
Taxonomy is not only a fundamental form of knowledge representation, but also crucial to
vast knowledge-rich applications, such as question answering and web search. Most …
vast knowledge-rich applications, such as question answering and web search. Most …
Chain-of-layer: Iteratively prompting large language models for taxonomy induction from limited examples
Automatic taxonomy induction is crucial for web search, recommendation systems, and
question answering. Manual curation of taxonomies is expensive in terms of human effort …
question answering. Manual curation of taxonomies is expensive in terms of human effort …