@inproceedings{fuchs-etal-2022-yet,
title = "Is it out yet? Automatic Future Product Releases Extraction from Web Data",
author = "Fuchs, Gilad and
Ben-shaul, Ido and
Mandelbrod, Matan",
editor = "Li, Yunyao and
Lazaridou, Angeliki",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-industry.27",
doi = "10.18653/v1/2022.emnlp-industry.27",
pages = "263--271",
abstract = "Identifying the release of new products and their predicted demand in advance is highly valuable for E-Commerce marketplaces and retailers. The information of an upcoming product release is used for inventory management, marketing campaigns and pre-order suggestions. Often, the announcement of an upcoming product release is widely available in multiple web pages such as blogs, chats or news articles. However, to the best of our knowledge, an automatic system to extract future product releases from web data has not been presented. In this work we describe an ML-powered multi-stage pipeline to automatically identify future product releases and rank their predicted demand from unstructured pages across the whole web. Our pipeline includes a novel Longformer-based model which uses a global attention mechanism guided by pre-calculated Named Entity Recognition predictions related to product releases. The model training data is based on a new corpus of 30K web pages manually annotated to identify future product releases. We made the dataset openly available at \url{https://doi.org/10.5281/zenodo.6894770}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fuchs-etal-2022-yet">
<titleInfo>
<title>Is it out yet? Automatic Future Product Releases Extraction from Web Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gilad</namePart>
<namePart type="family">Fuchs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ido</namePart>
<namePart type="family">Ben-shaul</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matan</namePart>
<namePart type="family">Mandelbrod</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Angeliki</namePart>
<namePart type="family">Lazaridou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Identifying the release of new products and their predicted demand in advance is highly valuable for E-Commerce marketplaces and retailers. The information of an upcoming product release is used for inventory management, marketing campaigns and pre-order suggestions. Often, the announcement of an upcoming product release is widely available in multiple web pages such as blogs, chats or news articles. However, to the best of our knowledge, an automatic system to extract future product releases from web data has not been presented. In this work we describe an ML-powered multi-stage pipeline to automatically identify future product releases and rank their predicted demand from unstructured pages across the whole web. Our pipeline includes a novel Longformer-based model which uses a global attention mechanism guided by pre-calculated Named Entity Recognition predictions related to product releases. The model training data is based on a new corpus of 30K web pages manually annotated to identify future product releases. We made the dataset openly available at https://doi.org/10.5281/zenodo.6894770.</abstract>
<identifier type="citekey">fuchs-etal-2022-yet</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-industry.27</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-industry.27</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>263</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Is it out yet? Automatic Future Product Releases Extraction from Web Data
%A Fuchs, Gilad
%A Ben-shaul, Ido
%A Mandelbrod, Matan
%Y Li, Yunyao
%Y Lazaridou, Angeliki
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F fuchs-etal-2022-yet
%X Identifying the release of new products and their predicted demand in advance is highly valuable for E-Commerce marketplaces and retailers. The information of an upcoming product release is used for inventory management, marketing campaigns and pre-order suggestions. Often, the announcement of an upcoming product release is widely available in multiple web pages such as blogs, chats or news articles. However, to the best of our knowledge, an automatic system to extract future product releases from web data has not been presented. In this work we describe an ML-powered multi-stage pipeline to automatically identify future product releases and rank their predicted demand from unstructured pages across the whole web. Our pipeline includes a novel Longformer-based model which uses a global attention mechanism guided by pre-calculated Named Entity Recognition predictions related to product releases. The model training data is based on a new corpus of 30K web pages manually annotated to identify future product releases. We made the dataset openly available at https://doi.org/10.5281/zenodo.6894770.
%R 10.18653/v1/2022.emnlp-industry.27
%U https://aclanthology.org/2022.emnlp-industry.27
%U https://doi.org/10.18653/v1/2022.emnlp-industry.27
%P 263-271
Markdown (Informal)
[Is it out yet? Automatic Future Product Releases Extraction from Web Data](https://aclanthology.org/2022.emnlp-industry.27) (Fuchs et al., EMNLP 2022)
ACL