Multi-Task Learning for Personal Search Ranking with Query Clustering
Abstract
User needs vary significantly across different tasks, and therefore
their queries will also vary significantly in their expressiveness
and semantics. Many studies have been proposed
to model such query diversity by obtaining query types and
building query-dependent ranking models. To obtain query
types, these studies typically require either a labeled query
dataset or clicks from multiple users aggregated over the
same document. These techniques, however, are not applicable
when manual query labeling is not viable, and aggregated
clicks are unavailable due to the private nature of the document
collection, e.g., in personal search scenarios. Therefore,
in this paper, we study the problem of how to obtain query
type in an unsupervised fashion and how to leverage this information
using query-dependent ranking models in personal
search. We first develop a hierarchical clustering algorithm
based on truncated SVD and varimax rotation to obtain
coarse-to-fine query types. Then, we propose three query-dependent
ranking models, including two neural models that
leverage query type information as additional features, and
one novel multi-task neural model that is trained to simultaneously
rank documents and predict query types. We evaluate
our ranking models using the click data collected from one of
the world’s largest personal search engines. The experiments
demonstrate that the proposed multi-task model can significantly
outperform the baseline neural models, which either
do not incorporate query type information or just simply
feed query type as an additional feature. To the best of our
knowledge, this is the first successful application of query-dependent
multi-task learning in personal search ranking.
their queries will also vary significantly in their expressiveness
and semantics. Many studies have been proposed
to model such query diversity by obtaining query types and
building query-dependent ranking models. To obtain query
types, these studies typically require either a labeled query
dataset or clicks from multiple users aggregated over the
same document. These techniques, however, are not applicable
when manual query labeling is not viable, and aggregated
clicks are unavailable due to the private nature of the document
collection, e.g., in personal search scenarios. Therefore,
in this paper, we study the problem of how to obtain query
type in an unsupervised fashion and how to leverage this information
using query-dependent ranking models in personal
search. We first develop a hierarchical clustering algorithm
based on truncated SVD and varimax rotation to obtain
coarse-to-fine query types. Then, we propose three query-dependent
ranking models, including two neural models that
leverage query type information as additional features, and
one novel multi-task neural model that is trained to simultaneously
rank documents and predict query types. We evaluate
our ranking models using the click data collected from one of
the world’s largest personal search engines. The experiments
demonstrate that the proposed multi-task model can significantly
outperform the baseline neural models, which either
do not incorporate query type information or just simply
feed query type as an additional feature. To the best of our
knowledge, this is the first successful application of query-dependent
multi-task learning in personal search ranking.
Research Areas
