Long Product Name Product Code Recognition Task

A Long Product Name Product Code Recognition Task is a entity mention recognition task whose input is a long product name and whose target type is product code.

• Context:
  • It can support a Product Record Record Linkage Task.
• Example(s):
  • [math]\displaystyle{ f }[/math]("Canon VIXIA HFS10 HD Dual Flash Memory w/32GB Internal Memory & 10x Optical Zoom - 2009 MODEL") ⇒ “Canon VIXIA HFS10 HD Dual Flash Memory w/32GB Internal Memory & 10x Optical Zoom - 2009 MODEL"
  • [math]\displaystyle{ f }[/math]("Canon VIXIA HF S10 32GB HIGH DEF CAMCORDER + 8GB CARD + CANON WIDE LENS + BOX") ⇒ “Canon VIXIA HF S10 32GB HIGH DEF CAMCORDER + 8GB CARD + CANON WIDE LENS + BOX"
  • [math]\displaystyle{ f }[/math]("Pro Digital Hard Lens Hood For The Canon VIXIA HF S10, HF S100 Flash Memory Camcorders") ⇒ “Pro Digital Hard Lens Hood For The Canon VIXIA HF S10, HF S100 Flash Memory Camcorders"
• Counter-Example(s):
  • a Product Name Entity Recognition Task.
  • a Product Record Record Linkage Task.
  • a Long Product Name Semantic Parsing Task.
  • a Product Code Normalization Task.
• See: Product Brand, Product Feature, Product Term Dictionary.

---

---

References

2014

• (Melli, 2014) ⇒ Gabor Melli. (2014). “Shallow Semantic Parsing of Product Offering Titles (for Better Automatic Hyperlink Insertion).” In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ISBN:978-1-4503-2956-9 doi:10.1145/2623330.2623343

2012

• (Köpcke et al., 2012) ⇒ Hanna Köpcke, Andreas Thor, Stefan Thomas, and Erhard Rahm. (2012). “Tailoring Entity Resolution for Matching Product Offers.” In: Proceedings of the 15th International Conference on Extending Database Technology. doi:10.1145/2247596.2247662
  • QUOTE: The extraction of the product code of the offered product is non-trivial as the title and the description of the product offer contain several unstructured information. Furthermore, accessory products may also contain multiple product codes, e.g., one for the accessory itself and one for the target product. Product code extraction is a special case of product attribute extraction that identifies attribute-value pairs out of unstructured textual descriptions (e.g., Ghani et al., 2006). However, such approaches typically require labeled (tagged) training data whereas our focused product code extraction does not need any training data but employs the rich knowledge of search engines.

---