Limits...
Harmony Search Algorithm for Word Sense Disambiguation.

Abed SA, Tiun S, Omar N - PLoS ONE (2015)

Bottom Line: Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods.In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words.The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.

View Article: PubMed Central - PubMed

Affiliation: Knowledge Technology Research Group (KT), Centre for Artificial Intelligent (CAIT), Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia.

ABSTRACT
Word Sense Disambiguation (WSD) is the task of determining which sense of an ambiguous word (word with multiple meanings) is chosen in a particular use of that word, by considering its context. A sentence is considered ambiguous if it contains ambiguous word(s). Practically, any sentence that has been classified as ambiguous usually has multiple interpretations, but just one of them presents the correct interpretation. We propose an unsupervised method that exploits knowledge based approaches for word sense disambiguation using Harmony Search Algorithm (HSA) based on a Stanford dependencies generator (HSDG). The role of the dependency generator is to parse sentences to obtain their dependency relations. Whereas, the goal of using the HSA is to maximize the overall semantic similarity of the set of parsed words. HSA invokes a combination of semantic similarity and relatedness measurements, i.e., Jiang and Conrath (jcn) and an adapted Lesk algorithm, to perform the HSA fitness function. Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods. In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words. The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.

No MeSH data available.


An example of generating typed dependencies.“The dog scratched its back on the bark of the tree”.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4589330&req=5

pone.0136614.g002: An example of generating typed dependencies.“The dog scratched its back on the bark of the tree”.

Mentions: Practically, the process of generating typed dependencies has two phases. The first phase is dependency extraction; where the Stanford parser [32] is used to parse the sentence. The head of each part of the sentence is then identified, which is the semantic head of the part, rather than the syntactic head. This method of generating typed dependencies prefers the heads to be the content words, and have auxiliaries, complementisers, etc., depend on them. The second phase is dependency typing; which labels the extracted pair (head and dependent words) with a grammatical relation. For the purpose of illustrating the head and dependent words, in the context of generating typed dependencies, we pass an example sentence “The dog scratched its back on the bark of the tree” to the Stanford dependencies generator [31] (as shown in Fig 2).


Harmony Search Algorithm for Word Sense Disambiguation.

Abed SA, Tiun S, Omar N - PLoS ONE (2015)

An example of generating typed dependencies.“The dog scratched its back on the bark of the tree”.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4589330&req=5

pone.0136614.g002: An example of generating typed dependencies.“The dog scratched its back on the bark of the tree”.
Mentions: Practically, the process of generating typed dependencies has two phases. The first phase is dependency extraction; where the Stanford parser [32] is used to parse the sentence. The head of each part of the sentence is then identified, which is the semantic head of the part, rather than the syntactic head. This method of generating typed dependencies prefers the heads to be the content words, and have auxiliaries, complementisers, etc., depend on them. The second phase is dependency typing; which labels the extracted pair (head and dependent words) with a grammatical relation. For the purpose of illustrating the head and dependent words, in the context of generating typed dependencies, we pass an example sentence “The dog scratched its back on the bark of the tree” to the Stanford dependencies generator [31] (as shown in Fig 2).

Bottom Line: Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods.In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words.The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.

View Article: PubMed Central - PubMed

Affiliation: Knowledge Technology Research Group (KT), Centre for Artificial Intelligent (CAIT), Universiti Kebangsaan Malaysia, 43600 UKM Bangi, Selangor, Malaysia.

ABSTRACT
Word Sense Disambiguation (WSD) is the task of determining which sense of an ambiguous word (word with multiple meanings) is chosen in a particular use of that word, by considering its context. A sentence is considered ambiguous if it contains ambiguous word(s). Practically, any sentence that has been classified as ambiguous usually has multiple interpretations, but just one of them presents the correct interpretation. We propose an unsupervised method that exploits knowledge based approaches for word sense disambiguation using Harmony Search Algorithm (HSA) based on a Stanford dependencies generator (HSDG). The role of the dependency generator is to parse sentences to obtain their dependency relations. Whereas, the goal of using the HSA is to maximize the overall semantic similarity of the set of parsed words. HSA invokes a combination of semantic similarity and relatedness measurements, i.e., Jiang and Conrath (jcn) and an adapted Lesk algorithm, to perform the HSA fitness function. Our proposed method was experimented on benchmark datasets, which yielded results comparable to the state-of-the-art WSD methods. In order to evaluate the effectiveness of the dependency generator, we perform the same methodology without the parser, but with a window of words. The empirical results demonstrate that the proposed method is able to produce effective solutions for most instances of the datasets used.

No MeSH data available.