An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge

Zhiqiang Toh; Wenting Wang; Man Lan; Xiaoli Li

doi:10.1109/ICDMW.2012.66

An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge

Zhiqiang Toh^*, Wenting Wang, Man Lan, Xiaoli Li

^*Corresponding author for this work

Agency for Science, Technology and Research, Singapore

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Scopus citations

Abstract

This paper presents our methodology for CPROD1 Challenge, which is to identify the product mentions from text and then link the product to the entries in the catalog file. Our solution follows 2 steps. First, we use processing pipelines to extract product mentions by incorporating multiple techniques including traditional named entities recognition (NER), regular expression rules and gazetteer-based string matching. Second, we view product linking task into an information retrieval (IR) problem, where the description catalog file is populated into a database. Thus, each product mention acts as a search query and the returned results from catalog entry database serve as the links. The F1 scores of our submission on public and private test data are 24.82% and 16.04%, respectively.

Original language	English
Title of host publication	Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012
Pages	869-871
Number of pages	3
DOIs	https://doi.org/10.1109/ICDMW.2012.66
State	Published - 2012
Externally published	Yes
Event	12th IEEE International Conference on Data Mining Workshops, ICDMW 2012 - Brussels, Belgium Duration: 10 Dec 2012 → 10 Dec 2012

Publication series

Name	Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012

Conference

Conference	12th IEEE International Conference on Data Mining Workshops, ICDMW 2012
Country/Territory	Belgium
City	Brussels
Period	10/12/12 → 10/12/12

Keywords

Named entity recognition
Product disambiguation
Product identification
Product linking

Access to Document

10.1109/ICDMW.2012.66

Cite this

Toh, Z., Wang, W., Lan, M., & Li, X. (2012). An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge. In Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012 (pp. 869-871). Article 6406532 (Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012). https://doi.org/10.1109/ICDMW.2012.66

Toh, Zhiqiang ; Wang, Wenting ; Lan, Man et al. / An NER-based product identification and lucene-based product linking approach to CPROD1 challenge : Description of submission system to CPROD1 Challenge. Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012. 2012. pp. 869-871 (Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012).

@inproceedings{a66fa7447bc847758c980fea7e71d052,

title = "An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge",

abstract = "This paper presents our methodology for CPROD1 Challenge, which is to identify the product mentions from text and then link the product to the entries in the catalog file. Our solution follows 2 steps. First, we use processing pipelines to extract product mentions by incorporating multiple techniques including traditional named entities recognition (NER), regular expression rules and gazetteer-based string matching. Second, we view product linking task into an information retrieval (IR) problem, where the description catalog file is populated into a database. Thus, each product mention acts as a search query and the returned results from catalog entry database serve as the links. The F1 scores of our submission on public and private test data are 24.82\% and 16.04\%, respectively.",

keywords = "Named entity recognition, Product disambiguation, Product identification, Product linking",

author = "Zhiqiang Toh and Wenting Wang and Man Lan and Xiaoli Li",

year = "2012",

doi = "10.1109/ICDMW.2012.66",

language = "英语",

isbn = "9780769549255",

series = "Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012",

pages = "869--871",

booktitle = "Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012",

note = "12th IEEE International Conference on Data Mining Workshops, ICDMW 2012 ; Conference date: 10-12-2012 Through 10-12-2012",

}

Toh, Z, Wang, W, Lan, M & Li, X 2012, An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge. in Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012., 6406532, Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012, pp. 869-871, 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012, Brussels, Belgium, 10/12/12. https://doi.org/10.1109/ICDMW.2012.66

An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge. / Toh, Zhiqiang; Wang, Wenting; Lan, Man et al.
Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012. 2012. p. 869-871 6406532 (Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An NER-based product identification and lucene-based product linking approach to CPROD1 challenge

T2 - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012

AU - Toh, Zhiqiang

AU - Wang, Wenting

AU - Lan, Man

AU - Li, Xiaoli

PY - 2012

Y1 - 2012

N2 - This paper presents our methodology for CPROD1 Challenge, which is to identify the product mentions from text and then link the product to the entries in the catalog file. Our solution follows 2 steps. First, we use processing pipelines to extract product mentions by incorporating multiple techniques including traditional named entities recognition (NER), regular expression rules and gazetteer-based string matching. Second, we view product linking task into an information retrieval (IR) problem, where the description catalog file is populated into a database. Thus, each product mention acts as a search query and the returned results from catalog entry database serve as the links. The F1 scores of our submission on public and private test data are 24.82% and 16.04%, respectively.

AB - This paper presents our methodology for CPROD1 Challenge, which is to identify the product mentions from text and then link the product to the entries in the catalog file. Our solution follows 2 steps. First, we use processing pipelines to extract product mentions by incorporating multiple techniques including traditional named entities recognition (NER), regular expression rules and gazetteer-based string matching. Second, we view product linking task into an information retrieval (IR) problem, where the description catalog file is populated into a database. Thus, each product mention acts as a search query and the returned results from catalog entry database serve as the links. The F1 scores of our submission on public and private test data are 24.82% and 16.04%, respectively.

KW - Named entity recognition

KW - Product disambiguation

KW - Product identification

KW - Product linking

UR - https://www.scopus.com/pages/publications/84873185336

U2 - 10.1109/ICDMW.2012.66

DO - 10.1109/ICDMW.2012.66

M3 - 会议稿件

AN - SCOPUS:84873185336

SN - 9780769549255

T3 - Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012

SP - 869

EP - 871

BT - Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012

Y2 - 10 December 2012 through 10 December 2012

ER -

Toh Z, Wang W, Lan M, Li X. An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge. In Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012. 2012. p. 869-871. 6406532. (Proceedings - 12th IEEE International Conference on Data Mining Workshops, ICDMW 2012). doi: 10.1109/ICDMW.2012.66

An NER-based product identification and lucene-based product linking approach to CPROD1 challenge: Description of submission system to CPROD1 Challenge

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this