Hypernym detection using strict partial order networks
AssigneeInternational Business Machines Corporation
InventorsSarthak Dash, Alfio Massimiliano Gliozzo, Md Faisal Mahbub Chowdhury
Life of this patent
Estimating the term…
Abstract
One embodiment of the present invention provides a method comprising receiving a text corpus, and generating a first list of triples based on the text corpus. Each triple of the first list comprises a first term representing a candidate hyponym, a second term representing a candidate hypernym, and a frequency value indicative of a number of times a hypernymy relation is observed between the candidate hyponym and the candidate hypernym in the text corpus. The method further comprises training a neural network for hypernym induction based on the first list. The trained neural network is a strict partial order network (SPON) model.
Claims20
A method comprising:
- receiving a list of candidate hyponym-hypernym pairs extracted from a text corpus, wherein each candidate hyponym-hypernym pair comprises a pair of terms representing a candidate hyponym and a candidate hypernym;
- modifying the list to add or remove at least one candidate hyponym-hypernym pair;
- and
- training, via machine learning, a neural network for hypernym induction based on the modified list and frequency information indicative of a number of times a hypernymy relation is observed between a candidate hyponym and a candidate hypernym of each candidate hyponym-hypernym pair of the modified list, wherein the trained neural network is a strict partial order network (SPON).
A system comprising:
- at least one processor;
- and
- a non-transitory processor-readable memory device storing instructions that when executed by the at least one processor causes the at least one processor to perform operations including:
- receiving a list of candidate hyponym-hypernym pairs extracted from a text corpus, wherein each candidate hyponym-hypernym pair comprises a pair of terms representing a candidate hyponym and a candidate hypernym;
- modifying the list to add or remove at least one candidate hyponym-hypernym pair;
- and
- training, via machine learning, a neural network for hypernym induction based on the modified list and frequency information indicative of a number of times a hypernymy relation is observed between a candidate hyponym and a candidate hypernym of each candidate hyponym-hypernym pair of the modified list, wherein the trained neural network is a strict partial order network (SPON).
A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
- receive a list of candidate hyponym-hypernym pairs extracted from a text corpus, wherein each candidate hyponym-hypernym pair comprises a pair of terms representing a candidate hyponym and a candidate hypernym;
- modify the list to add or remove at least one candidate hyponym-hypernym pair;
- and
- train, via machine learning, a neural network for hypernym induction based on the modified list and frequency information indicative of a number of times a hypernymy relation is observed between a candidate hyponym and a candidate hypernym of each candidate hyponym-hypernym pair of the modified list, wherein the trained neural network is a strict partial order network (SPON).
Dependencies are inferred from the claim text.