@inproceedings{pujari-etal-2022-three,
title = "Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping",
author = {Pujari, Subhash and
Str{\"o}tgen, Jannik and
Giereth, Mark and
Gertz, Michael and
Friedrich, Annemarie},
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.791",
doi = "10.18653/v1/2022.emnlp-main.791",
pages = "11498--11513",
abstract = "Patent Landscaping, one of the central tasks of intellectual property management, includes selecting and grouping patents according to user-defined technical or application-oriented criteria. While recent transformer-based models have been shown to be effective for classifying patents into taxonomies such as CPC or IPC, there is yet little research on how to support real-world Patent Landscape Studies (PLSs) using natural language processing methods. With this paper, we release three labeled datasets for PLS-oriented classification tasks covering two diverse domains. We provide a qualitative analysis and report detailed corpus statistics. Most research on neural models for patents has been restricted to leveraging titles and abstracts. We compare strong neural and non-neural baselines, proposing a novel model that takes into account textual information from the patents{'} full texts as well as embeddings created based on the patents{'} CPC labels. We find that for PLS-oriented classification tasks, going beyond title and abstract is crucial, CPC labels are an effective source of information, and combining all features yields the best results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pujari-etal-2022-three">
<titleInfo>
<title>Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping</title>
</titleInfo>
<name type="personal">
<namePart type="given">Subhash</namePart>
<namePart type="family">Pujari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jannik</namePart>
<namePart type="family">Strötgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Giereth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gertz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annemarie</namePart>
<namePart type="family">Friedrich</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</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Patent Landscaping, one of the central tasks of intellectual property management, includes selecting and grouping patents according to user-defined technical or application-oriented criteria. While recent transformer-based models have been shown to be effective for classifying patents into taxonomies such as CPC or IPC, there is yet little research on how to support real-world Patent Landscape Studies (PLSs) using natural language processing methods. With this paper, we release three labeled datasets for PLS-oriented classification tasks covering two diverse domains. We provide a qualitative analysis and report detailed corpus statistics. Most research on neural models for patents has been restricted to leveraging titles and abstracts. We compare strong neural and non-neural baselines, proposing a novel model that takes into account textual information from the patents’ full texts as well as embeddings created based on the patents’ CPC labels. We find that for PLS-oriented classification tasks, going beyond title and abstract is crucial, CPC labels are an effective source of information, and combining all features yields the best results.</abstract>
<identifier type="citekey">pujari-etal-2022-three</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.791</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.791</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>11498</start>
<end>11513</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping
%A Pujari, Subhash
%A Strötgen, Jannik
%A Giereth, Mark
%A Gertz, Michael
%A Friedrich, Annemarie
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F pujari-etal-2022-three
%X Patent Landscaping, one of the central tasks of intellectual property management, includes selecting and grouping patents according to user-defined technical or application-oriented criteria. While recent transformer-based models have been shown to be effective for classifying patents into taxonomies such as CPC or IPC, there is yet little research on how to support real-world Patent Landscape Studies (PLSs) using natural language processing methods. With this paper, we release three labeled datasets for PLS-oriented classification tasks covering two diverse domains. We provide a qualitative analysis and report detailed corpus statistics. Most research on neural models for patents has been restricted to leveraging titles and abstracts. We compare strong neural and non-neural baselines, proposing a novel model that takes into account textual information from the patents’ full texts as well as embeddings created based on the patents’ CPC labels. We find that for PLS-oriented classification tasks, going beyond title and abstract is crucial, CPC labels are an effective source of information, and combining all features yields the best results.
%R 10.18653/v1/2022.emnlp-main.791
%U https://aclanthology.org/2022.emnlp-main.791
%U https://doi.org/10.18653/v1/2022.emnlp-main.791
%P 11498-11513
Markdown (Informal)
[Three Real-World Datasets and Neural Computational Models for Classification Tasks in Patent Landscaping](https://aclanthology.org/2022.emnlp-main.791) (Pujari et al., EMNLP 2022)
ACL