Enquire One's Parent and Child Before Decision: Fully Exploit
Hierarchical Structure for Self-Supervised Taxonomy Expansion
- URL: http://arxiv.org/abs/2101.11268v1
- Date: Wed, 27 Jan 2021 08:57:47 GMT
- Title: Enquire One's Parent and Child Before Decision: Fully Exploit
Hierarchical Structure for Self-Supervised Taxonomy Expansion
- Authors: Suyuchen Wang, Ruihui Zhao, Xi Chen, Yefeng Zheng and Bang Liu
- Abstract summary: We propose the Hierarchy Expansion Framework (HEF), which fully exploits the hierarchical structure's properties to maximize the coherence of expanded taxonomy.
HEF vastly surpasses the prior state-of-the-art on three benchmark datasets by an average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.
- Score: 17.399482876574407
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Taxonomy is a hierarchically structured knowledge graph that plays a crucial
role in machine intelligence. The taxonomy expansion task aims to find a
position for a new term in an existing taxonomy to capture the emerging
knowledge in the world and keep the taxonomy dynamically updated. Previous
taxonomy expansion solutions neglect valuable information brought by the
hierarchical structure and evaluate the correctness of merely an added edge,
which downgrade the problem to node-pair scoring or mini-path classification.
In this paper, we propose the Hierarchy Expansion Framework (HEF), which fully
exploits the hierarchical structure's properties to maximize the coherence of
expanded taxonomy. HEF makes use of taxonomy's hierarchical structure in
multiple aspects: i) HEF utilizes subtrees containing most relevant nodes as
self-supervision data for a complete comparison of parental and sibling
relations; ii) HEF adopts a coherence modeling module to evaluate the coherence
of a taxonomy's subtree by integrating hypernymy relation detection and several
tree-exclusive features; iii) HEF introduces the Fitting Score for position
selection, which explicitly evaluates both path and level selections and takes
full advantage of parental relations to interchange information for
disambiguation and self-correction. Extensive experiments show that by better
exploiting the hierarchical structure and optimizing taxonomy's coherence, HEF
vastly surpasses the prior state-of-the-art on three benchmark datasets by an
average improvement of 46.7% in accuracy and 32.3% in mean reciprocal rank.
Related papers
- Find Parent then Label Children: A Two-stage Taxonomy Completion Method with Pre-trained Language Model [46.00652942385366]
We propose a two-stage method called ATTEMPT for taxonomy completion.
Our method inserts new concepts into the correct position by finding a parent node and labeling child nodes.
We take advantage of pre-trained language models for hypernym/hyponymy recognition.
arXiv Detail & Related papers (2024-06-25T17:25:02Z) - TaxoEnrich: Self-Supervised Taxonomy Completion via Structure-Semantic
Representations [28.65753036636082]
We propose a new taxonomy completion framework, which effectively leverages both semantic features and structural information in the existing taxonomy.
TaxoEnrich consists of four components: (1) taxonomy-contextualized embedding which incorporates both semantic meanings of concept and taxonomic relations based on powerful pretrained language models; (2) a taxonomy-aware sequential encoder which learns candidate position representations by encoding the structural information of taxonomy.
Experiments on four large real-world datasets from different domains show that TaxoEnrich achieves the best performance among all evaluation metrics and outperforms previous state-of-the-art by a large margin.
arXiv Detail & Related papers (2022-02-10T08:10:43Z) - Taxonomy Enrichment with Text and Graph Vector Representations [61.814256012166794]
We address the problem of taxonomy enrichment which aims at adding new words to the existing taxonomy.
We present a new method that allows achieving high results on this task with little effort.
We achieve state-of-the-art results across different datasets and provide an in-depth error analysis of mistakes.
arXiv Detail & Related papers (2022-01-21T09:01:12Z) - TaxoCom: Topic Taxonomy Completion with Hierarchical Discovery of Novel
Topic Clusters [57.59286394188025]
We propose a novel framework for topic taxonomy completion, named TaxoCom.
TaxoCom discovers novel sub-topic clusters of terms and documents.
Our comprehensive experiments on two real-world datasets demonstrate that TaxoCom not only generates the high-quality topic taxonomy in terms of term coherency and topic coverage.
arXiv Detail & Related papers (2022-01-18T07:07:38Z) - Modeling Heterogeneous Hierarchies with Relation-specific Hyperbolic
Cones [64.75766944882389]
We present ConE (Cone Embedding), a KG embedding model that is able to simultaneously model multiple hierarchical as well as non-hierarchical relations in a knowledge graph.
In particular, ConE uses cone containment constraints in different subspaces of the hyperbolic embedding space to capture multiple heterogeneous hierarchies.
Our approach yields new state-of-the-art Hits@1 of 45.3% on WN18RR and 16.1% on DDB14 (0.231 MRR)
arXiv Detail & Related papers (2021-10-28T07:16:08Z) - Who Should Go First? A Self-Supervised Concept Sorting Model for
Improving Taxonomy Expansion [50.794640012673064]
As data and business scope grow in real applications, existing need to be expanded to incorporate new concepts.
Previous works on taxonomy expansion process the new concepts independently and simultaneously, ignoring the potential relationships among them and the appropriate order of inserting operations.
We propose TaxoOrder, a novel self-supervised framework that simultaneously discovers the local hypernym-hyponym structure among new concepts and decides the order of insertion.
arXiv Detail & Related papers (2021-04-08T11:00:43Z) - Can Taxonomy Help? Improving Semantic Question Matching using Question
Taxonomy [37.57300969050908]
We propose a hybrid technique for semantic question matching.
It uses our proposed two-layered taxonomy for English questions by augmenting state-of-the-art deep learning models with question classes obtained from a deep learning based question.
arXiv Detail & Related papers (2021-01-20T16:23:04Z) - Taxonomy Completion via Triplet Matching Network [18.37146040410778]
We formulate a new task, "taxonomy completion", by discovering both the hypernym and hyponym concepts for a query.
We propose Triplet Matching Network (TMN), to find the appropriate hypernym, hyponym> pairs for a given query concept.
TMN achieves the best performance on both taxonomy completion task and the previous taxonomy expansion task, outperforming existing methods.
arXiv Detail & Related papers (2021-01-06T07:19:55Z) - STEAM: Self-Supervised Taxonomy Expansion with Mini-Paths [53.45704816829921]
We propose a self-supervised taxonomy expansion model named STEAM.
STEAM generates natural self-supervision signals, and formulates a node attachment prediction task.
Experiments show STEAM outperforms state-of-the-art methods for taxonomy expansion by 11.6% in accuracy and 7.0% in mean reciprocal rank.
arXiv Detail & Related papers (2020-06-18T00:32:53Z) - TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced
Graph Neural Network [62.12557274257303]
Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications.
We propose a novel self-supervised framework, named TaxoExpan, which automatically generates a set of query concept, anchor concept> pairs from the existing taxonomy as training data.
We develop two innovative techniques in TaxoExpan: (1) a position-enhanced graph neural network that encodes the local structure of an anchor concept in the existing taxonomy, and (2) a noise-robust training objective that enables the learned model to be insensitive to the label noise in the self-supervision data.
arXiv Detail & Related papers (2020-01-26T21:30:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.