Browse State-of-the-Art › Hypernym Discovery

Hypernym Discovery

8 papers with code · 3 benchmarks · 1 dataset archive 2025-07-28

Natural Language Processing

Given a corpus and a target term (hyponym), the task of hypernym discovery consists of extracting a set of its most appropriate hypernyms from the corpus. For example, for the input word “dog”, some valid hypernyms would be “canine”, “mammal” or “animal”.

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

1 dataset whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Papers archive 2025-07-28

archive papers tagged: 33 · with a code link: 8 · where Syntology ran a sample: 0 (0 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology

Show: all tagged papersonly where code ran: none of the 33 tagged papers has a Syntology run on record

Page 1 of 1: papers 1 to 33 of 33, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.

Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.

  • 3 Apr 2018 3 repositories listed
    Learning graph representations via low-dimensional embeddings that preserve relevant network properties is an important class of problems in machine learning.
  • 8 Feb 2025 1 repository listed
    Compared to existing domain LLMs based on newly collected large-scale domain-specific corpora, our OntoTune, which relies on the existing, long-term developed ontology and LLM itself, significantly reduces data…
  • 14 Mar 2024 1 repository listed
    It achieves 11 SotA results, 4 top-2 results out of 16 tasks for the Taxonomy Enrichment, Hypernym Discovery, Taxonomy Construction, and Lexical Entailment tasks.
  • 6 Oct 2022 1 repository listed
    Grasping the commonsense properties of everyday concepts is an important prerequisite to language understanding.
  • 14 Dec 2021 1 repository listed
    Predicting lexical-semantic relations between word pairs has successfully been accomplished by pre-trained neural language models.
  • 12 Dec 2020 1 repository listed
    We describe our submission to the CogALex-VI shared task on the identification of multilingual paradigmatic relations building on XLM-RoBERTa (XLM-R), a robustly optimized and multilingual BERT model.
  • 1 Jun 2018 1 repository listed
    This report describes the system developed by the CRIM team for the hypernym discovery task at SemEval 2018.
  • 14 Dec 2016 1 repository listed
    The fundamental role of hypernymy in NLP has motivated the development of many methods for the automatic identification of this relation, most of which rely on word distribution.
  • Probing Pretrained Language Models with Hierarchy Properties
    15 Dec 2023 0 repositories listed
    Since Pretrained Language Models (PLMs) are the cornerstone of the most recent Information Retrieval (IR) models, the way they encode semantic knowledge is particularly important.
  • HyperBox: A Supervised Approach for Hypernym Discovery using Box Embeddings
    5 Apr 2022 0 repositories listed
    For this task, we use the dataset published for SemEval 2018 Shared Task on Hypernym Discovery.
  • Analyzing BERT’s Knowledge of Hypernymy via Prompting
    1 Nov 2021 0 repositories listed
    The high performance of large pretrained language models (LLMs) such as BERT on NLP tasks has prompted questions about BERT’s linguistic capabilities, and how they differ from humans’.
  • Hypernym Discovery via a Recurrent Mapping Model
    1 Aug 2021 0 repositories listed
  • Document Structure aware Relational Graph Convolutional Networks for Ontology Population
    27 Apr 2021 0 repositories listed
    Ontologies comprising of concepts, their attributes, and relationships are used in many knowledge based AI systems.
  • Meemi: A Simple Method for Post-processing and Integrating Cross-lingual Word Embeddings
    16 Oct 2019 0 repositories listed
    While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual embeddings define a multilingual space where word embeddings from two or more languages are…
  • The Effectiveness of Simple Hybrid Systems for Hypernym Discovery
    1 Jul 2019 0 repositories listed
    Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods.
  • Document Structure Measure for Hypernym discovery
    30 Nov 2018 0 repositories listed
    Hypernym discovery is the problem of finding terms that have is-a relationship with a given term.
  • Learning Scalar Adjective Intensity from Paraphrases
    1 Oct 2018 0 repositories listed
    Adjectives like “warm”, “hot”, and “scalding” all describe temperature but differ in intensity.
  • 1 Jun 2018 0 repositories listed
    This paper describes 300-sparsians’s participation in SemEval-2018 Task 9: Hypernym Discovery, with a system based on sparse coding and a formal concept hierarchy obtained from word embeddings.
  • 1 Jun 2018 0 repositories listed
    This paper describes a simple but competitive unsupervised system for hypernym discovery.
  • 1 Jun 2018 0 repositories listed
    This paper presents the participation of Apollo’s team in the SemEval-2018 Task 9 “Hypernym Discovery”, Subtask 1: “General-Purpose Hypernym Discovery”, which tries to produce a ranked list of hypernyms for a specific…
  • 1 Jun 2018 0 repositories listed
    In this paper, we present our proposed system (EXPR) to participate in the hypernym discovery task of SemEval 2018.
  • 1 Jun 2018 0 repositories listed
    Hypernym discovery aims to discover the hypernym word sets given a hyponym word and proper corpus.
  • 1 Jun 2018 0 repositories listed
    This paper describes the SemEval 2018 Shared Task on Hypernym Discovery.
  • UMDuluth-CS8761 at SemEval-2018 Task9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
    1 Jun 2018 0 repositories listed
    Hypernym Discovery is the task of identifying potential hypernyms for a given term.
  • 26 May 2018 0 repositories listed
    This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a…
  • UMDuluth-CS8761 at SemEval-2018 Task 9: Hypernym Discovery using Hearst Patterns, Co-occurrence frequencies and Word Embeddings
    25 May 2018 0 repositories listed
    Hypernym Discovery is the task of identifying potential hypernyms for a given term.
  • Tel(s)-Telle(s)-Signs: Highly Accurate Automatic Crosslingual Hypernym Discovery
    1 May 2018 0 repositories listed
  • Distributional Inclusion Vector Embedding for Unsupervised Hypernymy Detection
    2 Oct 2017 0 repositories listed
    Modeling hypernymy, such as poodle is-a dog, is an important generalization aid to many NLP tasks, such as entailment, coreference, relation extraction, and question answering.
  • BabelDomains: Large-Scale Domain Labeling of Lexical Resources
    1 Apr 2017 0 repositories listed
    In this paper we present BabelDomains, a unified resource which provides lexical items with information about domains of knowledge.
  • 1 Nov 2016 0 repositories listed
  • Weakly Supervised Definition Extraction
    1 Sep 2015 0 repositories listed
  • Towards Linked Hypernyms Dataset 2.0: complementing DBpedia with hypernym discovery
    1 May 2014 0 repositories listed
  • Exploiting Multiple Sources for Open-Domain Hypernym Discovery
    1 Oct 2013 0 repositories listed

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections