SemEval-2016 Task 13: Taxonomy Extraction Evaluation (TExEval-2)

Abstract

This paper describes the second edition of the shared task on Taxonomy Extraction Evaluation organised as part of SemEval 2016. This task aims to extract hypernym-hyponym relations between a given list of domain-specific terms and then to construct a domain taxonomy based on them. TExEval-2 introduced a multilingual setting for this task, covering four different languages including English, Dutch, Italian and French from domains as diverse as environment, food and science. A total of 62 runs submitted by 5 different teams were evaluated using structural measures, by comparison with gold standard taxonomies and by manual quality assessment of novel relations.

NUIG-UNLP at SemEval-2016 Task 13: A Simple Word Embedding-based Approach for Taxonomy Extraction

“…and categorisation (i.i.) for the English taxonomy construction, and fifth on the overall ranking (see Bordea et al (2016) for further details on the evaluation metrics).…”

SemEval-2018 Task 9: Hypernym Discovery

“…The UMBC corpus is considerably large and contains information from many and diverse domains. This corpus presents additional challenges and different sources of information with respect to the corpora used in previous tasks, such as Wikipedia in the SemEval 2016 task on taxonomy extraction (Bordea et al, 2016). In fact, the encyclopedic nature of Wikipedia has been exploited in a wide variety of works (Ponzetto and Strube, 2007;Flati et al, 2016;Gupta et al, 2016), and differs substantially from the web-based corpus we put forward here.…”

Taxonomy Induction Using Hypernym Subsequences

“…4 Validation set is excluded from the test set. 5 We used a weighting function (i.e., step function with cut-off at 50% of the height of the subsequence) to favor terms at lower heights as they are usually more domain-specific. It has been used to find the optimal solution in applications like the transportation problem [17], where the goal is to find the cheapest paths to send commodities from a group of facilities to the customers via a transportation network.…”

“…More recently, Bordea et al [4,5] introduced the first shared tasks on open-domain Taxonomy Extraction, thus providing a common ground for evaluation. INRIASAC, the top system in 2015 task, uses features based on substrings and co-occurrence statistics [8] whereas TAXI, the top system in 2016 task, uses lexico-syntactic patterns, substrings and focused crawling [28].…”

“…However, such manually constructed taxonomies suffer from low coverage [15] and are unavailable for specific domains or languages. Therefore, in recent years, there has been substantial interest in extending existing taxonomies automatically or building new ones [4,5,19,34,38,40].…”