Query Reformulation in E-Commerce Search

Hirsch, Sharon; Guy, Ido; Nus, Alexander; Dagan, Arnon; Kurland, Oren

doi:10.1145/3397271.3401065

Cited by 26 publications

(9 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The gen./specialization and aspect change transformations fall into the former type, whereas all other categories fall into the latter. We highlight here that unlike previous categorizations that describe how users revise queries in e-commerce [3,26], how to generate better queries to substitute the original query [28], how users reformulate queries in a session [27], we study here how to categorize query variations for the same information need which is a related but different problem.…”

Section: Uqv Taxonomymentioning

confidence: 99%

Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators

Penha¹,

Câmara²,

Hauff³

2021

Preprint

View full text Add to dashboard Cite

Heavily pre-trained transformers for language modelling, such as BERT, have shown to be remarkably effective for Information Retrieval (IR) tasks. IR benchmarks evaluate the effectiveness of (neural) ranking models based on the premise that a single query is used to instantiate the underlying information need. However, previous research has shown that (I) queries generated by users for a fixed information need are extremely variable and, in particular, (II) neural models are brittle and often easily make mistakes when tested with adversarial examples, i.e. examples with minimal modifications that do not change its label. Motivated by those observations we aim to answer the following question with our work: how robust are retrieval pipelines with respect to different variations in queries that do not change the queries' semantics? In order to obtain queries that are representative of users' querying variability, we first created a taxonomy based on the manual annotation of transformations occurring in a dataset (specifically UQV100) of user created query variations. For example, from the query 'cures for a bald spot' to the variation 'cures for baldness' we are applying a paraphrasing transformation that replaces words with synonyms. For each syntax-changing category of our taxonomy, we employ different automatic methods that when applied to a query generate a query variation. We conduct experiments on two datasets (TREC-DL-2019 and ANTIQUE) and create a total of 2430 query variations from 243 topics across both datasets. Our experimental results for two different IR tasks reveal that retrieval pipelines are not robust to query variations that maintain the content the same, with effectiveness drops of ∼20% on average when compared with the original query as provided in the datasets. Our findings indicate that further work is required to make retrieval pipelines with neural ranking models more robust and that IR collections should include query variations, e.g. using the methods proposed here, for a single information need to better understand models capabilities. The code and datasets are available at https://github.com/Guzpenha/query_variation_generators.

show abstract

Section: Uqv Taxonomymentioning

confidence: 99%

Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators

Penha¹,

Câmara²,

Hauff³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…There exists an unsupervised approach for query suggestion in e-commerce domain where the query similarity scores are calculated based on popularity and purchase-efficiency of queries [13]. Other works focus on query re-writing among which Shing et al provide an unsupervised approach [31], and Hirsch et al [15] focus on whether a user will reformulate a query, Aritra et al [19] generate synonyms for query rewriting, and Xiao et al [37] focuses on dataset generation to reduce the gap between user query and product listings. We adopted spherical text embedding based query representation in this work.…”

Section: Related Workmentioning

confidence: 99%

ORDSIM: Ordinal Regression for E-Commerce Query Similarity Prediction

Kabir¹,

Hasan²,

Mandal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Query similarity prediction task is generally solved by regression based models with square loss. Such a model is agnostic of absolute similarity values and it penalizes the regression error at all ranges of similarity values at the same scale. However, to boost e-commerce platform's monetization, it is important to predict high-level similarity more accurately than low-level similarity, as highly similar queries retrieves items according to user-intents, whereas moderately similar item retrieves related items, which may not lead to a purchase. Regression models fail to customize its loss function to concentrate around the high-similarity band, resulting poor performance in query similarity prediction task. We address the above challenge by considering the query prediction as an ordinal regression problem, and thereby propose a model, ORDSIM (ORDinal Regression for SIMilarity Prediction). ORDSIM exploits variable-width buckets to model ordinal loss, which penalizes errors in high-level similarity harshly, and thus enable the regression model to obtain better prediction results for high similarity values. We evaluate ORDSIM on a dataset of over 10 millions e-commerce queries from eBay platform and show that ORDSIM achieves substantially smaller prediction error compared to the competing regression methods on this dataset.

show abstract

“…Manchanda et al [10] also divided e-commerce query transitions into five categories, including transition from a general to a specific intent and transition from an incomplete to a complete query. Hirsch et al [2] analyzed the characteristics of the three reformulation types for e-commerce queries: add, remove, and replace. Unlike the above studies, we specifically focus on the problem of turning a zero-hit query into a successful one to enable product purchase.…”

Section: Related Workmentioning

confidence: 99%

How Do Users Revise Zero-Hit Product Search Queries?

Amemiya

Manabe²,

Fujita³

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A product search on an e-commerce site can return zero hits for several reasons. One major reason is that a user's query may not be appropriately expressed for locating existing products. To enable successful product purchase, an ideal e-commerce site should automatically revise the user query to avoid zero hits. We investigate what kinds of query revision strategies turn a zero-hit query into a successful query, by analyzing data from a major Japanese e-commerce site. Our analysis shows that about 99% of zero-hit queries can be turned into successful queries that lead to product purchase by term dropping (27%), term replacement (29%), rephrasing (17%), and typo correction (26%). The results suggest that an automatic rewriter for avoiding zero-hit product queries may be able to achieve satisfactory coverage and accuracy by focusing on the above four revision strategies.

show abstract

Query Reformulation in E-Commerce Search

Cited by 26 publications

References 37 publications

Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators

Evaluating the Robustness of Retrieval Pipelines with Query Variation Generators

ORDSIM: Ordinal Regression for E-Commerce Query Similarity Prediction

How Do Users Revise Zero-Hit Product Search Queries?

Contact Info

Product

Resources

About