Comparison of Numeral Strings Interpretation: Rule-Based and Feature-Based N-Gram Methods

Min, Kyongho; Wilson, William H.

doi:10.1007/11941439_152

Cited by 1 publication

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…"at 2:30pm") in order. In this paper, the size of total data was tripled compared to [14]. Table 5 shows the performance using word trigrams (i.e.…”

Section: Resultsmentioning

confidence: 99%

“…Table 6 shows the performance comparison between rule-based methods [13] and bigrams [14] and our current results with trigrams and pentagrams. The system in [13] was based on a manually generated rule-based method and the system in [14] was based on an automatically generated tabular feature-based method based on two types of bigrams (2L1R0 and 2L0R1). The current systems were based on word trigrams (3L1R1), and word pentagrams (5L2R2).…”

Section: Resultsmentioning

confidence: 99%

“…However, there is no system that interprets numeral strings systematically; they are frequently treated as either numerals or nominal entities. In this paper, we discussed two N-gram methods and compared their performance with a manually obtained rulebased method [13] and a word bigrams method [14]. The word trigrams method with five features performs better than rule-based and word bigrams methods in terms of the F-measurement ratio.…”

Section: Discussionmentioning

confidence: 99%

“…al. [13], [14] studied a manually generated rulebased numeral-string interpretation method and also a system based on automaticallygenerated bigrams constraints.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Effectiveness of Methods for Syntactic and Semantic Recognition of Numeral Strings: Tradeoffs Between Number of Features and Length of Word N-Grams

Min

Wilson

Kang

AI 2007: Advances in Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

Abstract. This paper describes and compares the use of methods based on Ngrams (specifically trigrams and pentagrams), together with five features, to recognise the syntactic and semantic categories of numeral strings representing money, number, date, etc., in texts. The system employs three interpretation processes: word N-grams construction with a tokeniser; rule-based processing of numeral strings; and N-gram-based classification. We extracted numeral strings from 1,111 online newspaper articles. For numeral strings interpretation, we chose 112 (10%) of 1,111 articles to provide unseen test data (1,278 numeral strings), and used the remaining 999 articles to provide 11,525 numeral strings for use in extracting N-gram-based constraints to disambiguate meanings of the numeral strings. The word trigrams method resulted in 83.8% precision, 81.2% recall ratio, and 82.5% in F-measurement ratio. The word pentagrams method resulted in 86.6% precision, 82.9% recall ratio, and 84.7% in F-measurement ratio.

show abstract

“…"at 2:30pm") in order. In this paper, the size of total data was tripled compared to [14]. Table 5 shows the performance using word trigrams (i.e.…”

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

“…al. [13], [14] studied a manually generated rulebased numeral-string interpretation method and also a system based on automaticallygenerated bigrams constraints.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations