Taxonomy Induction Using Hypernym Subsequences

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

et al. 2018

We present a novel end-to-end reinforcement learning approach to automatic taxonomy induction from a set of terms. While prior methods treat the problem as a two-phase task (i.e., detecting hypernymy pairs followed by organizing these pairs into a tree-structured hierarchy), we argue that such two-phase methods may suffer from error propagation, and cannot effectively optimize metrics that capture the holistic structure of a taxonomy. In our approach, the representations of term pairs are learned using multiple sources of information and used to determine which term to select and where to place it on the taxonomy via a policy network. All components are trained in an end-to-end manner with cumulative rewards, measured by a holistic tree metric over the training taxonomies. Experiments on two public datasets of different domains show that our approach outperforms prior state-ofthe-art taxonomy induction methods up to 19.6% on ancestor F1. 1

Section: Resultsmentioning

confidence: 99%

“…The optimal taxonomy is also found by the MST. Gupta et al (2017) extract hypernym subsequences based on hypernym pairs, and regard the task of taxonomy induction as an instance of the minimum-cost flow problem.…”

Section: Taxonomy Inductionmentioning

confidence: 99%

End-to-End Reinforcement Learning for Automatic Taxonomy Induction

Mao

Ren

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

et al. 2018

“…For the second hypernymy organization step, most methods formulate it as a graph optimization problem. They first build a noisy hypernymy graph using hypernymy pairs extracted and then derive the output taxonomy as a particular tree or DAG structure (e.g., maximum spanning tree [5,35], optimal branching [49], and minimum-cost flow [14]) from the hypernymy graph. Finally, there are some methods that leverage entity set expansion techniques [40,62] to incrementally construct a taxonomy either from scratch or from a tiny seed taxonomy.…”

Section: Related Workmentioning

confidence: 99%

TaxoExpan: Self-supervised Taxonomy Expansion with Position-Enhanced Graph Neural Network

Proceedings of the Web Conference 2020

Xiong

et al. 2020

Taxonomies consist of machine-interpretable semantics and provide valuable knowledge for many web applications. For example, online retailers (e.g., Amazon and eBay) use taxonomies for product recommendation, and web search engines (e.g., Google and Bing) leverage taxonomies to enhance query understanding. Enormous efforts have been made on constructing taxonomies either manually or semi-automatically. However, with the fast-growing volume of web content, existing taxonomies will become outdated and fail to capture emerging knowledge. Therefore, in many applications, dynamic expansions of an existing taxonomy are in great demand. In this paper, we study how to expand an existing taxonomy by adding a set of new concepts. 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. Using such self-supervision data, TaxoExpan learns a model to predict whether a query concept is the direct hyponym of an anchor concept. 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. Extensive experiments on three large-scale datasets from different domains demonstrate both the effectiveness and the efficiency of TaxoExpan for taxonomy expansion.

“…Bansal et al [3] build a factor graph to model hypernymy relations and regard taxonomy induction as a structured learning problem, which can be inferred with loop belief propagation. Recently, Gupta et al [9] propose to build the initial graph using hypernym subsequence (instead of single hypernym pair) and model taxonomy induction as a minimum-cost flow problem [26]. Comparing with these methods, our approach leverages the weak supervision in "seed" taxonomy and builds a task-specific taxonomy in which two terms can hold a non-hypernymy relation.…”

Section: Taxonomy Constructionmentioning

confidence: 99%

HiExpan

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

Lei

et al. 2018

Taxonomies are of great value to many knowledge-rich applications. As the manual taxonomy curation costs enormous human effects, automatic taxonomy construction is in great demand. However, most existing automatic taxonomy construction methods can only build hypernymy taxonomies wherein each edge is limited to expressing the "is-a" relation. Such a restriction limits their applicability to more diverse real-world tasks where the parent-child may carry different relations. In this paper, we aim to construct a task-guided taxonomy from a domain-specific corpus, and allow users to input a "seed" taxonomy, serving as the task guidance. We propose an expansion-based taxonomy construction framework, namely HiExpan, which automatically generates key term list from the corpus and iteratively grows the seed taxonomy. Specifically, HiExpan views all children under each taxonomy node forming a coherent set and builds the taxonomy by recursively expanding all these sets. Furthermore, HiExpan incorporates a weakly-supervised relation extraction module to extract the initial children of a newlyexpanded node and adjusts the taxonomy tree by optimizing its global structure. Our experiments on three real datasets from different domains demonstrate the effectiveness of HiExpan for building task-guided taxonomies.