Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.9
Fan Yang, Alireza Bagheri Garakani, Yifei Teng, Yanling Gao, Jia Liu, Jingyuan Deng, Yi Sun
In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries. However, resolving phonetic errors is a critical but much overlooked area. The query with phonetic spelling errors tends to appear correct based on pronunciation but is nonetheless inaccurate in spelling (e.g., “bluetooth sound system” vs. “blutut sant sistam”) with numerous noisy forms and sparse occurrences. In this work, we propose a generalized spelling correction system integrating phonetics to address phonetic errors in E-commerce search without additional latency cost. Using India (IN) E-commerce market for illustration, the experiment shows that our proposed phonetic solution significantly improves the F1 score by 9%+ and recall of phonetic errors by 8%+. This phonetic spelling correction system has been deployed to production, currently serving hundreds of millions of customers.
在电子商务搜索中，在处理用户输入的搜索查询时，拼写校正对于为客户找到所需的产品起着重要的作用。然而，语音错误的解决是一个非常重要但又容易被忽视的领域。有语音拼写错误的查询往往在发音上看起来是正确的，但在拼写上却不准确(例如，“bluetooth sound system”与“blutut sant sistam”)，因为有许多嘈杂的形式和稀疏的出现。在这项工作中，我们提出了一个集成语音的通用拼写纠正系统，以解决电子商务搜索中的语音错误，而不增加延迟成本。以印度(IN)电子商务市场为例，实验表明，我们提出的语音解决方案显著提高了F1分数9%+，语音错误召回率8%+。该语音拼写校正系统已部署到生产中，目前服务于数亿客户。
{"title":"Spelling Correction using Phonetics in E-commerce Search","authors":"Fan Yang, Alireza Bagheri Garakani, Yifei Teng, Yanling Gao, Jia Liu, Jingyuan Deng, Yi Sun","doi":"10.18653/v1/2022.ecnlp-1.9","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.9","url":null,"abstract":"In E-commerce search, spelling correction plays an important role to find desired products for customers in processing user-typed search queries. However, resolving phonetic errors is a critical but much overlooked area. The query with phonetic spelling errors tends to appear correct based on pronunciation but is nonetheless inaccurate in spelling (e.g., “bluetooth sound system” vs. “blutut sant sistam”) with numerous noisy forms and sparse occurrences. In this work, we propose a generalized spelling correction system integrating phonetics to address phonetic errors in E-commerce search without additional latency cost. Using India (IN) E-commerce market for illustration, the experiment shows that our proposed phonetic solution significantly improves the F1 score by 9%+ and recall of phonetic errors by 8%+. This phonetic spelling correction system has been deployed to production, currently serving hundreds of millions of customers.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121876270","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.5
B. Dong, Yiyi Wang, Hanbo Sun, Yunji Wang, Alireza Hashemi, Zheng Du
Deep neural network models are especially susceptible to noise in annotated labels. In the real world, annotated data typically contains noise caused by a variety of factors such as task difficulty, annotator experience, and annotator bias. Label quality is critical for label validation tasks; however, correcting for noise by collecting more data is often costly. In this paper, we propose a contrastive meta-learning framework (CML) to address the challenges introduced by noisy annotated data, specifically in the context of natural language processing. CML combines contrastive and meta learning to improve the quality of text feature representations. Meta-learning is also used to generate confidence scores to assess label quality. We demonstrate that a model built on CML-filtered data outperforms a model built on clean data. Furthermore, we perform experiments on deidentified commercial voice assistant datasets and demonstrate that our model outperforms several SOTA approaches.
{"title":"CML: A Contrastive Meta Learning Method to Estimate Human Label Confidence Scores and Reduce Data Collection Cost","authors":"B. Dong, Yiyi Wang, Hanbo Sun, Yunji Wang, Alireza Hashemi, Zheng Du","doi":"10.18653/v1/2022.ecnlp-1.5","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.5","url":null,"abstract":"Deep neural network models are especially susceptible to noise in annotated labels. In the real world, annotated data typically contains noise caused by a variety of factors such as task difficulty, annotator experience, and annotator bias. Label quality is critical for label validation tasks; however, correcting for noise by collecting more data is often costly. In this paper, we propose a contrastive meta-learning framework (CML) to address the challenges introduced by noisy annotated data, specifically in the context of natural language processing. CML combines contrastive and meta learning to improve the quality of text feature representations. Meta-learning is also used to generate confidence scores to assess label quality. We demonstrate that a model built on CML-filtered data outperforms a model built on clean data. Furthermore, we perform experiments on deidentified commercial voice assistant datasets and demonstrate that our model outperforms several SOTA approaches.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.2
Zeming Wang, Yanyan Zou, Yuejian Fang, Hongshen Chen, Mian Ma, Zhuoye Ding, Bo Long
As the multi-modal e-commerce is thriving, high-quality advertising product copywriting has gain more attentions, which plays a crucial role in the e-commerce recommender, advertising and even search platforms.The advertising product copywriting is able to enhance the user experience by highlighting the product’s characteristics with textual descriptions and thus to improve the likelihood of user click and purchase. Automatically generating product copywriting has attracted noticeable interests from both academic and industrial communities, where existing solutions merely make use of a product’s title and attribute information to generate its corresponding description.However, in addition to the product title and attributes, we observe that there are various auxiliary descriptions created by the shoppers or marketers in the e-commerce platforms (namely human knowledge), which contains valuable information for product copywriting generation, yet always accompanying lots of noises.In this work, we propose a novel solution to automatically generating product copywriting that involves all the title, attributes and denoised auxiliary knowledge.To be specific, we design an end-to-end generation framework equipped with two variational autoencoders that works interactively to select informative human knowledge and generate diverse copywriting.
{"title":"Interactive Latent Knowledge Selection for E-Commerce Product Copywriting Generation","authors":"Zeming Wang, Yanyan Zou, Yuejian Fang, Hongshen Chen, Mian Ma, Zhuoye Ding, Bo Long","doi":"10.18653/v1/2022.ecnlp-1.2","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.2","url":null,"abstract":"As the multi-modal e-commerce is thriving, high-quality advertising product copywriting has gain more attentions, which plays a crucial role in the e-commerce recommender, advertising and even search platforms.The advertising product copywriting is able to enhance the user experience by highlighting the product’s characteristics with textual descriptions and thus to improve the likelihood of user click and purchase. Automatically generating product copywriting has attracted noticeable interests from both academic and industrial communities, where existing solutions merely make use of a product’s title and attribute information to generate its corresponding description.However, in addition to the product title and attributes, we observe that there are various auxiliary descriptions created by the shoppers or marketers in the e-commerce platforms (namely human knowledge), which contains valuable information for product copywriting generation, yet always accompanying lots of noises.In this work, we propose a novel solution to automatically generating product copywriting that involves all the title, attributes and denoised auxiliary knowledge.To be specific, we design an end-to-end generation framework equipped with two variational autoencoders that works interactively to select informative human knowledge and generate diverse copywriting.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129359739","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.29
G. Lavee, Ido Guy
The term lot in is defined to mean an offering that contains a collection of multiple identical items for sale. In a large online marketplace, lot offerings play an important role, allowing buyers and sellers to set price levels to optimally balance supply and demand needs. In spite of their central role, platforms often struggle to identify lot offerings, since explicit lot status identification is frequently not provided by sellers. The ability to identify lot offerings plays a key role in many fundamental tasks, from matching offerings to catalog products, through ranking search results, to providing effective pricing guidance. In this work, we seek to determine the lot status (and lot size) of each offering, in order to facilitate an improved buyer experience, while reducing the friction for sellers posting new offerings. We demonstrate experimentally the ability to accurately classify offerings as lots and predict their lot size using only the offer title, by adapting state-of-the-art natural language techniques to the lot identification problem.
{"title":"Lot or Not: Identifying Multi-Quantity Offerings in E-Commerce","authors":"G. Lavee, Ido Guy","doi":"10.18653/v1/2022.ecnlp-1.29","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.29","url":null,"abstract":"The term lot in is defined to mean an offering that contains a collection of multiple identical items for sale. In a large online marketplace, lot offerings play an important role, allowing buyers and sellers to set price levels to optimally balance supply and demand needs. In spite of their central role, platforms often struggle to identify lot offerings, since explicit lot status identification is frequently not provided by sellers. The ability to identify lot offerings plays a key role in many fundamental tasks, from matching offerings to catalog products, through ranking search results, to providing effective pricing guidance. In this work, we seek to determine the lot status (and lot size) of each offering, in order to facilitate an improved buyer experience, while reducing the friction for sellers posting new offerings. We demonstrate experimentally the ability to accurately classify offerings as lots and predict their lot size using only the offer title, by adapting state-of-the-art natural language techniques to the lot identification problem.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131007564","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.8
Yusuke Shido, Hsien-Chi Liu, Keisuke Umezawa
Automatic monitoring systems for inappropriate user-generated messages have been found to be effective in reducing human operation costs in Consumer to Consumer (C2C) marketplace services, in which customers send messages directly to other customers.We propose a lightweight neural network that takes a conversation as input, which we deployed to a production service.Our results show that the system reduced the human operation costs to less than one-sixth compared to the conventional rule-based monitoring at Mercari.
{"title":"Textual Content Moderation in C2C Marketplace","authors":"Yusuke Shido, Hsien-Chi Liu, Keisuke Umezawa","doi":"10.18653/v1/2022.ecnlp-1.8","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.8","url":null,"abstract":"Automatic monitoring systems for inappropriate user-generated messages have been found to be effective in reducing human operation costs in Consumer to Consumer (C2C) marketplace services, in which customers send messages directly to other customers.We propose a lightweight neural network that takes a conversation as input, which we deployed to a production service.Our results show that the system reduced the human operation costs to less than one-sixth compared to the conventional rule-based monitoring at Mercari.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"259 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123092944","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.16
Wei-Te Chen, Yandi Xia, Keiji Shinzato
Although most studies have treated attribute value extraction (AVE) as named entity recognition, these approaches are not practical in real-world e-commerce platforms because they perform poorly, and require canonicalization of extracted values. Furthermore, since values needed for actual services is static in many attributes, extraction of new values is not always necessary. Given the above, we formalize AVE as extreme multi-label classification (XMC). A major problem in solving AVE as XMC is that the distribution between positive and negative labels for products is heavily imbalanced. To mitigate the negative impact derived from such biased distribution, we propose label masking, a simple and effective method to reduce the number of negative labels in training. We exploit attribute taxonomy designed for e-commerce platforms to determine which labels are negative for products. Experimental results using a dataset collected from a Japanese e-commerce platform demonstrate that the label masking improves micro and macro F_1 scores by 3.38 and 23.20 points, respectively.
{"title":"Extreme Multi-Label Classification with Label Masking for Product Attribute Value Extraction","authors":"Wei-Te Chen, Yandi Xia, Keiji Shinzato","doi":"10.18653/v1/2022.ecnlp-1.16","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.16","url":null,"abstract":"Although most studies have treated attribute value extraction (AVE) as named entity recognition, these approaches are not practical in real-world e-commerce platforms because they perform poorly, and require canonicalization of extracted values. Furthermore, since values needed for actual services is static in many attributes, extraction of new values is not always necessary. Given the above, we formalize AVE as extreme multi-label classification (XMC). A major problem in solving AVE as XMC is that the distribution between positive and negative labels for products is heavily imbalanced. To mitigate the negative impact derived from such biased distribution, we propose label masking, a simple and effective method to reduce the number of negative labels in training. We exploit attribute taxonomy designed for e-commerce platforms to determine which labels are negative for products. Experimental results using a dataset collected from a Japanese e-commerce platform demonstrate that the label masking improves micro and macro F_1 scores by 3.38 and 23.20 points, respectively.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124625209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.6
Alireza Bagheri Garakani, Fan Yang, Wen-Yu Hua, Yetian Chen, Michinari Momma, Jingyuan Deng, Yanling Gao, Yi Sun
Ensuring relevance quality in product search is a critical task as it impacts the customer’s ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term. In this work we leverage a high-precision cross-encoder BERT model for semantic similarity between customer query and products and survey its effectiveness for three ranking applications where offline-generated scores could be used: (1) as an offline metric for estimating relevance quality impact, (2) as a re-ranking feature covering head/torso queries, and (3) as a training objective for optimization. We present results on effectiveness of this strategy for the large e-commerce setting, which has general applicability for choice of other high-precision models and tasks in ranking.
{"title":"Improving Relevance Quality in Product Search using High-Precision Query-Product Semantic Similarity","authors":"Alireza Bagheri Garakani, Fan Yang, Wen-Yu Hua, Yetian Chen, Michinari Momma, Jingyuan Deng, Yanling Gao, Yi Sun","doi":"10.18653/v1/2022.ecnlp-1.6","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.6","url":null,"abstract":"Ensuring relevance quality in product search is a critical task as it impacts the customer’s ability to find intended products in the short-term as well as the general perception and trust of the e-commerce system in the long term. In this work we leverage a high-precision cross-encoder BERT model for semantic similarity between customer query and products and survey its effectiveness for three ranking applications where offline-generated scores could be used: (1) as an offline metric for estimating relevance quality impact, (2) as a re-ranking feature covering head/torso queries, and (3) as a training objective for optimization. We present results on effectiveness of this strategy for the large e-commerce setting, which has general applicability for choice of other high-precision models and tasks in ranking.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122333724","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.3
Yang Liu, Varnith Chordia, Hua Li, Siavash Fazeli Dehkordy, Yifei Sun, Vincent Gao, Na Zhang
In a leading e-commerce business, we receive hundreds of millions of customer feedback from different text communication channels such as product reviews. The feedback can contain rich information regarding customers’ dissatisfaction in the quality of goods and services. To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text. We identify issues at two levels: coarse grained (L-Coarse) and fine grained (L-Granular). We formulate this multi-level product issue identification problem as a seq2seq language generation problem. Specifically, we utilize transformer-based seq2seq models due to their versatility and strong transfer-learning capability. We demonstrate that our approach is label efficient and outperforms the traditional approach such as multi-class multi-label classification formulation. Based on human evaluation, our fine-tuned model achieves 82.1% and 95.4% human-level performance for L-Coarse and L-Granular issue identification, respectively. Furthermore, our experiments illustrate that the model can generalize to identify unseen L-Granular issues.
{"title":"Leveraging Seq2seq Language Generation for Multi-level Product Issue Identification","authors":"Yang Liu, Varnith Chordia, Hua Li, Siavash Fazeli Dehkordy, Yifei Sun, Vincent Gao, Na Zhang","doi":"10.18653/v1/2022.ecnlp-1.3","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.3","url":null,"abstract":"In a leading e-commerce business, we receive hundreds of millions of customer feedback from different text communication channels such as product reviews. The feedback can contain rich information regarding customers’ dissatisfaction in the quality of goods and services. To harness such information to better serve customers, in this paper, we created a machine learning approach to automatically identify product issues and uncover root causes from the customer feedback text. We identify issues at two levels: coarse grained (L-Coarse) and fine grained (L-Granular). We formulate this multi-level product issue identification problem as a seq2seq language generation problem. Specifically, we utilize transformer-based seq2seq models due to their versatility and strong transfer-learning capability. We demonstrate that our approach is label efficient and outperforms the traditional approach such as multi-class multi-label classification formulation. Based on human evaluation, our fine-tuned model achieves 82.1% and 95.4% human-level performance for L-Coarse and L-Granular issue identification, respectively. Furthermore, our experiments illustrate that the model can generalize to identify unseen L-Granular issues.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"105 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114223453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Many e-commerce websites provide Product-related Question Answering (PQA) platform where potential customers can ask questions related to a product, and other consumers can post an answer to that question based on their experience. Recently, there has been a growing interest in providing automated responses to product questions. In this paper, we investigate the suitability of the generative approach for PQA. We use state-of-the-art generative models proposed by Deng et al.(2020) and Lu et al.(2020) for this purpose. On closer examination, we find several drawbacks in this approach: (1) input reviews are not always utilized significantly for answer generation, (2) the performance of the models is abysmal while answering the numerical questions, (3) many of the generated answers contain phrases like “I do not know” which are taken from the reference answer in training data, and these answers do not convey any information to the customer. Although these approaches achieve a high ROUGE score, it does not reflect upon these shortcomings of the generated answers. We hope that our analysis will lead to more rigorous PQA approaches, and future research will focus on addressing these shortcomings in PQA.
{"title":"Investigating the Generative Approach for Question Answering in E-Commerce","authors":"Kalyani Roy, Vineeth Balapanuru, Tapas Nayak, Pawan Goyal","doi":"10.18653/v1/2022.ecnlp-1.24","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.24","url":null,"abstract":"Many e-commerce websites provide Product-related Question Answering (PQA) platform where potential customers can ask questions related to a product, and other consumers can post an answer to that question based on their experience. Recently, there has been a growing interest in providing automated responses to product questions. In this paper, we investigate the suitability of the generative approach for PQA. We use state-of-the-art generative models proposed by Deng et al.(2020) and Lu et al.(2020) for this purpose. On closer examination, we find several drawbacks in this approach: (1) input reviews are not always utilized significantly for answer generation, (2) the performance of the models is abysmal while answering the numerical questions, (3) many of the generated answers contain phrases like “I do not know” which are taken from the reference answer in training data, and these answers do not convey any information to the customer. Although these approaches achieve a high ROUGE score, it does not reflect upon these shortcomings of the generated answers. We hope that our analysis will lead to more rigorous PQA approaches, and future research will focus on addressing these shortcomings in PQA.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133646768","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 1900-01-01DOI: 10.18653/v1/2022.ecnlp-1.17
Lvxing Zhu, Hao Chen, Chao Wei, Weiru Zhang
Query classification is a fundamental task in an e-commerce search engine, which assigns one or multiple predefined product categories in response to each search query. Taking click-through logs as training data in deep learning methods is a common and effective approach for query classification. However, the frequency distribution of queries typically has long-tail property, which means that there are few logs for most of the queries. The lack of reliable user feedback information results in worse performance of long-tail queries compared with frequent queries. To solve the above problem, we propose a novel method that leverages an auxiliary module to enhance the representations of long-tail queries by taking advantage of reliable supervised information of variant frequent queries. The long-tail queries are guided by the contrastive loss to obtain category-aligned representations in the auxiliary module, where the variant frequent queries serve as anchors in the representation space. We train our model with real-world click data from AliExpress and conduct evaluation on both offline labeled data and online AB test. The results and further analysis demonstrate the effectiveness of our proposed method.
{"title":"Enhanced Representation with Contrastive Loss for Long-Tail Query Classification in e-commerce","authors":"Lvxing Zhu, Hao Chen, Chao Wei, Weiru Zhang","doi":"10.18653/v1/2022.ecnlp-1.17","DOIUrl":"https://doi.org/10.18653/v1/2022.ecnlp-1.17","url":null,"abstract":"Query classification is a fundamental task in an e-commerce search engine, which assigns one or multiple predefined product categories in response to each search query. Taking click-through logs as training data in deep learning methods is a common and effective approach for query classification. However, the frequency distribution of queries typically has long-tail property, which means that there are few logs for most of the queries. The lack of reliable user feedback information results in worse performance of long-tail queries compared with frequent queries. To solve the above problem, we propose a novel method that leverages an auxiliary module to enhance the representations of long-tail queries by taking advantage of reliable supervised information of variant frequent queries. The long-tail queries are guided by the contrastive loss to obtain category-aligned representations in the auxiliary module, where the variant frequent queries serve as anchors in the representation space. We train our model with real-world click data from AliExpress and conduct evaluation on both offline labeled data and online AB test. The results and further analysis demonstrate the effectiveness of our proposed method.","PeriodicalId":384006,"journal":{"name":"Proceedings of The Fifth Workshop on e-Commerce and NLP (ECNLP 5)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126953141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：