@inproceedings{liu-etal-2021-geo-bert,
title = "Geo-{BERT} Pre-training Model for Query Rewriting in {POI} Search",
author = "Liu, Xiao and
Hu, Juan and
Shen, Qi and
Chen, Huan",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.190",
doi = "10.18653/v1/2021.findings-emnlp.190",
pages = "2209--2214",
abstract = "Query Rewriting (QR) is proposed to solve the problem of the word mismatch between queries and documents in Web search. Existing approaches usually model QR with an end-to-end sequence-to-sequence (seq2seq) model. The state-of-the-art Transformer-based models can effectively learn textual semantics from user session logs, but they often ignore users{'} geographic location information that is crucial for the Point-of-Interest (POI) search of map services. In this paper, we proposed a pre-training model, called Geo-BERT, to integrate semantics and geographic information in the pre-trained representations of POIs. Firstly, we simulate POI distribution in the real world as a graph, in which nodes represent POIs and multiple geographic granularities. Then we use graph representation learning methods to get geographic representations. Finally, we train a BERT-like pre-training model with text and POIs{'} graph embeddings to get an integrated representation of both geographic and semantic information, and apply it in the QR of POI search. The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2021-geo-bert">
<titleInfo>
<title>Geo-BERT Pre-training Model for Query Rewriting in POI Search</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Shen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huan</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Query Rewriting (QR) is proposed to solve the problem of the word mismatch between queries and documents in Web search. Existing approaches usually model QR with an end-to-end sequence-to-sequence (seq2seq) model. The state-of-the-art Transformer-based models can effectively learn textual semantics from user session logs, but they often ignore users’ geographic location information that is crucial for the Point-of-Interest (POI) search of map services. In this paper, we proposed a pre-training model, called Geo-BERT, to integrate semantics and geographic information in the pre-trained representations of POIs. Firstly, we simulate POI distribution in the real world as a graph, in which nodes represent POIs and multiple geographic granularities. Then we use graph representation learning methods to get geographic representations. Finally, we train a BERT-like pre-training model with text and POIs’ graph embeddings to get an integrated representation of both geographic and semantic information, and apply it in the QR of POI search. The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services.</abstract>
<identifier type="citekey">liu-etal-2021-geo-bert</identifier>
<identifier type="doi">10.18653/v1/2021.findings-emnlp.190</identifier>
<location>
<url>https://aclanthology.org/2021.findings-emnlp.190</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>2209</start>
<end>2214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Geo-BERT Pre-training Model for Query Rewriting in POI Search
%A Liu, Xiao
%A Hu, Juan
%A Shen, Qi
%A Chen, Huan
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Findings of the Association for Computational Linguistics: EMNLP 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F liu-etal-2021-geo-bert
%X Query Rewriting (QR) is proposed to solve the problem of the word mismatch between queries and documents in Web search. Existing approaches usually model QR with an end-to-end sequence-to-sequence (seq2seq) model. The state-of-the-art Transformer-based models can effectively learn textual semantics from user session logs, but they often ignore users’ geographic location information that is crucial for the Point-of-Interest (POI) search of map services. In this paper, we proposed a pre-training model, called Geo-BERT, to integrate semantics and geographic information in the pre-trained representations of POIs. Firstly, we simulate POI distribution in the real world as a graph, in which nodes represent POIs and multiple geographic granularities. Then we use graph representation learning methods to get geographic representations. Finally, we train a BERT-like pre-training model with text and POIs’ graph embeddings to get an integrated representation of both geographic and semantic information, and apply it in the QR of POI search. The proposed model achieves excellent accuracy on a wide range of real-world datasets of map services.
%R 10.18653/v1/2021.findings-emnlp.190
%U https://aclanthology.org/2021.findings-emnlp.190
%U https://doi.org/10.18653/v1/2021.findings-emnlp.190
%P 2209-2214
Markdown (Informal)
[Geo-BERT Pre-training Model for Query Rewriting in POI Search](https://aclanthology.org/2021.findings-emnlp.190) (Liu et al., Findings 2021)
ACL