Predicting Latent Structured Intents from Shopping Queries
Abstract
In online shopping, users usually express their intent through
search queries. However, these queries are usually in a rather
ambiguous form instead of being accurate. For example, it is
more likely (and easier) for users to write a query like “high end
bike” than “21 speed carbon frames jamis road bike”. It
is challenging to interpret these ambiguous queries and thus
search result accuracy suffers. A user oftentimes needs to go
through the frustrating process of refining search queries or
self-teaching from possibly unstructured information. However,
shopping is indeed a structured domain, that is composed
of category hierarchy, brands, product lines, features,
etc. It would have been much better if a shopping site could
understand users’ intent through this structure, present organized/structured
information, or even find items with the
right categories, brands or features for them.
In this paper we study the problem of inferring the latent
intent from unstructured queries and mapping them to
structured attributes. We present a novel framework that
jointly learns this knowledge from user consumption behaviors
and product metadata. We present a hybrid Long Short term
Memory (LSTM) joint model that is accurate and robust,
even though user queries are noisy and product catalog
is rapidly growing. Our study is conducted on a large-scale
dataset from Google Shopping, that is composed of millions
of items and user queries along with their click responses.
Extensive qualitative and quantitative evaluation shows that
the proposed model is more accurate, concise, and robust
than multiple possible alternatives.
search queries. However, these queries are usually in a rather
ambiguous form instead of being accurate. For example, it is
more likely (and easier) for users to write a query like “high end
bike” than “21 speed carbon frames jamis road bike”. It
is challenging to interpret these ambiguous queries and thus
search result accuracy suffers. A user oftentimes needs to go
through the frustrating process of refining search queries or
self-teaching from possibly unstructured information. However,
shopping is indeed a structured domain, that is composed
of category hierarchy, brands, product lines, features,
etc. It would have been much better if a shopping site could
understand users’ intent through this structure, present organized/structured
information, or even find items with the
right categories, brands or features for them.
In this paper we study the problem of inferring the latent
intent from unstructured queries and mapping them to
structured attributes. We present a novel framework that
jointly learns this knowledge from user consumption behaviors
and product metadata. We present a hybrid Long Short term
Memory (LSTM) joint model that is accurate and robust,
even though user queries are noisy and product catalog
is rapidly growing. Our study is conducted on a large-scale
dataset from Google Shopping, that is composed of millions
of items and user queries along with their click responses.
Extensive qualitative and quantitative evaluation shows that
the proposed model is more accurate, concise, and robust
than multiple possible alternatives.
Research Areas
