Research map / Label-efficient and robust learning / Domain adaptation and generalization
ExTaSem! Extending, Taxonomizing and Semantifying Domain Terminologies
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use ExTaSem! instead of best TExEval participant (LT3) | taxonomy induction · TExEval 2015 average | edge F-score: 0.28 -> 0.31 | Helped |
| use ExTaSem! instead of LT3 | taxonomy induction · TExEval 2015 Science | edge F-score: .39 -> .29 | Hurt |
| use ExTaSem! instead of INRIASAC | taxonomy induction · TExEval 2015 Chemical | edge F-score: .09 -> .03 | Hurt |
| use ExTaSem! instead of substring-inclusion baseline | taxonomy reconstruction · 100-term expert gold standard Food | CFM: 0.02 -> 0.50 | Helped |
| use ExTaSem! instead of substring-inclusion baseline | taxonomy reconstruction · 100-term expert gold standard Science | CFM: 0.01 -> 0.64 | Helped |
| use ExTaSem! hypernyms instead of WIBI | hypernym extraction · Food | fraction valid: 0.85 -> 0.94 | Helped |
| use ExTaSem! hypernyms instead of WIBI | hypernym extraction · Chemical | fraction valid: 0.75 -> 0.64 | Hurt |
| use ExTaSem! hypernyms instead of WIBI | hypernym extraction · Food | fraction judged best: 0.29 -> 0.91 | Helped |
| use ExTaSem! instead of gold taxonomy structure | taxonomy structure · Food | number of nodes: 1556 -> 3647 | Mixed |
Closest papers by meaning
- Learning Term Embeddings for Lexical Taxonomies (AAAI 2021 · similarity 0.89)
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation (ICML 2025 · similarity 0.84)
- End-to-End Ontology Learning with Large Language Models (NeurIPS 2024 · similarity 0.83)
- Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery (NeurIPS 2025 · similarity 0.82)
- SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches (ICLR 2025 · similarity 0.82)
- UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition (ICLR 2024 · similarity 0.82)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.