WordNet organizes the relation between terms and synsets, and a term may have many meanings, which is called polysemous term. As a result, the relation between terms and synsets is many-to-many relationship and wrong term-synset relation can occur in WordNet, which caused overload. 

Polysemy

There are large amount of term-synset pairs in WordNet, which caused underload.

Missing Senses, Lemmas and Relations

Lexicon quality challenges can be either a overload work or underload. Overload means it has some inappropriate senses, lemmas, or relations and produce overload components in LSR. Underwork means it has some missing senses, lemmas or connections. There are some specific challenges: 

1)	Polysemy

2)	Missing Senses, Lemmas and Relations


University of Notre Dame

Lexical Semantic Resources (LSRs) is a lexical database that organizes the relation between synsets via lexical and semantic relations. 

Lexical Semantic Resources (LSRs)

Khalilia, H., Freihat, A. A., & Giunchiglia, F. (2021). The Quality of Lexical Semantic Resources: A Survey. In Proceedings of The Fourth International Conference on Natural Language and Speech Processing (ICNLSP 2021) (pp. 117-129).

The Quality of Lexical Semantic Resources: A Survey

A synset consists of lemmas (a word in dictionary form), gloss (a sentance that describes the synset), and synset examples. For example, “person, individual, someone,
somebody, mortal, soul” are lemmas of a synset, and "a human being" is the gloss, and "there are too much for one person to do" is a synset example.

Synset

LSR Quality Challenges

A good LSR depends on synset correctness and completeness, and also depends on the connectivity degree of the synset with other synsets in the semantic network. There are different evaluation methods for each part of the LSR:

1)	Synset Lemmas Evaluation Methods

2)	Synset Gloss Evaluation Methods

3)	Synset Relations Evaluation Methods


Learn Before

Related

Learn After