Characteristics of document similarity measures for compliance analysis

Sayeed, Asad; Sarkar, Surojit; Deng, Yu; Hosn, Rafah; Mahindru, Ruchi; Rajamani, Nithya

doi:10.1145/1645953.1646106

Cited by 9 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This has the effect that the vectors are normalized to unit length and only the angle, more precisely the cosine of the angle, between the vectors accounts for their similarity. In the proposed technique, Cosine Similarity [17][18] is used to calculate the semantic similarity between two documents (articles) using the following equation:…”

Section: Semantic Similarity Computationmentioning

confidence: 99%

HSWS

Youssif

Ghalwash

Amer

2011

Proceedings of the International Conference on Management of Emergent Digital EcoSystems

View full text Add to dashboard Cite

With the tremendous growth of information availability to users through the Web, search engines come to play ever a more critical role. However, search engines retrieve vast amount of information that is far larger than an individual capability of processing. Also enormous amount of such information are not related to user search query. The semantic web provides a promising approach to enhance the search operation. Ontologies can capture concepts for any topic to enable machines to deal with data semantically. In this paper, a proposed technique called HSWS (Hybrid Semantic Web Search) is used to automatically generate ontology concepts for any topic by extracting semantic relationships between concepts from information sources that represent such topic; the resultant ontology concepts is used to re-rank results returned by a search engine for such topic. A new relevancy measure is proposed to rank retrieved documents. The new relevancy measure depends on the degree of semantic similarity between concepts extracted from web pages resulted from query on a topic and indexed ontology concepts that represents the topic. The proposed technique is fully unsupervised; it doesn"t require any type of training. HSWS outperforms semantic similarity state-of-the-art methods and webbased methods. The proposed technique shows the highest Pearson correlation coefficient to human judgments (0.888) compared to other similarity methods.

show abstract

Section: Semantic Similarity Computationmentioning

confidence: 99%

HSWS

Youssif

Ghalwash

Amer

2011

Proceedings of the International Conference on Management of Emergent Digital EcoSystems

View full text Add to dashboard Cite

show abstract

“…Minakov et al [35] report contract template creation from the automatic clustering and semantic analysis of a collection of 25000 insurance documents in an insurance company. Sayeed et al [42] develop a system for contract template complaince based on document similarity.…”

mentioning

confidence: 99%

A corpus of Australian contract language

Curtotti

McCreath

2011

Proceedings of the 13th International Conference on Artificial Intelligence and Law

View full text Add to dashboard Cite

Written contracts are a fundamental framework for economic and cooperative transactions in society. Little work has been reported on the application of natural language processing or corpus linguistics to contracts. In this paper we report the design, profiling and initial analysis of a corpus of Australian contract language. This corpus enables a quantitative and qualitative characterisation of Australian contract language as an input to the development of contract drafting tools. Profiling of the corpus is consistent with its suitability for use in language engineering applications. We provide descriptive statistics for the corpus and show that document length and document vocabulary size approximate to log normal distributions. The corpus conforms to Zipf's law and comparative type to token ratios are consistent with lower term sparsity (an expectation for legal language). We highlight distinctive term usage in Australian contract language. Results derived from the corpus indicate a longer prepositional phrase depth in sentences in contract rules extracted from the corpus, as compared to other corpora.

show abstract

Which of the book recommendation sections is the most similar to the user selections in LibraryThing?

Momeni

Pashootanizadeh

Kaedi

2023

GKMC

View full text Add to dashboard Cite

Purpose This study aims to determine the most similar set of recommendation books to the user selections in LibraryThing. Design/methodology/approach For this purpose, 30,000 tags related to History on the LibraryThing have been selected. Their tags and the tags of the related recommended books were extracted from three different recommendations sections on LibraryThing. Then, four similarity criteria of Jaccard coefficient, Cosine similarity, Dice coefficient and Pearson correlation coefficient were used to calculate the similarity between the tags. To determine the most similar recommended section, the best similarity criterion had to be determined first. So, a researcher-made questionnaire was provided to History experts. Findings The results showed that the Jaccard coefficient, with a frequency of 32.81, is the best similarity criterion from the point of view of History experts. Besides, the degree of similarity in LibraryThing recommendations section according to this criterion is equal to 0.256, in the section of books with similar library subjects and classifications is 0.163 and in the Member recommendations section is 0.152. Based on the findings of this study, the LibraryThing recommendations section has succeeded in introducing the most similar books to the selected book compared to the other two sections. Originality/value To the best of the authors’ knowledge, itis for the first time, three sections of LibraryThing recommendations are compared by four different similarity criteria to show which sections would be more beneficial for the user browsing. The results showed that machine recommendations work better than humans.

show abstract

Characteristics of document similarity measures for compliance analysis

Cited by 9 publications

References 14 publications

HSWS

HSWS

A corpus of Australian contract language

Which of the book recommendation sections is the most similar to the user selections in LibraryThing?

Contact Info

Product

Resources

About