Reading Diary

5 Predicting Terms in Hypo-hypernym Relations with Pre-trained T5. terms

benchmark

It is a collective dataset, developed by industries, and academic groups at well-funded universities, which the community has agreed upon to measure the performance of the models.

Example: We put forward this task as a complementary benchmark for modeling hypernymy, a problem which has traditionally been cast as a binary classification task, taking a pair of candidate words as input [1].

corpus (pl. corpora)

A collection of authentic text or audio organized into datasets.

Example: First, we identified those candidates with at least 50 occurrences in the corpus [2].

hypernym

A term whose referents form a set which includes a subset the referents of a subordinate term.

Example: Crucially, Espinosa-Anke et al. (2016) proposed to frame the problem as Hypernym Discovery, i.e. given the search space of a domain’s vocabulary, and given an input term, discover its best (list of) candidate hypernyms [1].

hyponym

A term designating a subclass of another more general class described by the given word.

Example: After compiling a source corpus and a corresponding vocabulary, we selected a suitable collection of input terms (i.e. hyponyms) to construct the gold standard for each subtask [1].

SOTA (state-of-the-art)

It refers to the best models that can be used for achieving the results in a task.

Example: This is intentional as we aim to promote the development of models that are comparable to the current state-of-the-art [2].