Learning to Rewrite Queries

He, Yunlong; Tang, Jiliang; Ouyang, Hua; Kang, Changsung; Yin, Dawei; Chang, Yi

doi:10.1145/2983323.2983835

Cited by 53 publications

(33 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, such strategies are more likely to cause clicks on highly ranked documents. Further experiments on semantic query changes through generalisation vs. specialisation [10,12] showed that a trend exists toward going from generalisation to specialisation. This behavioural pattern represents a standard building-box strategy while specialisation occurs early in the session.…”

Section: Query Reformulation Understandingmentioning

confidence: 99%

“…Different time gaps have been used including 10-15 min [8], 30 min [4,19] and 90 min [6,9]. In a significant body of work, authors categorised the transitions made from one query to the subsequent queries through syntactic changes [11,12,23,26] and query semantic changes [10,12,33]. Syntactic changes include word substitution, removing, adding and keeping.…”

Section: Query Reformulation Understandingmentioning

confidence: 99%

“…Query reformulation is a critical user behaviour in modern search engines and it is still addressed by a significant amount of research studies [10][11][12]17,23,26,33]. A salient behavioural facet that has been widely captured and analysed by those studies is query history.…”

Section: Introductionmentioning

confidence: 99%

“…While it is well-known that time-based session detection methods fail in revealing tasks [6,19], most of previous research work has employed time-based sessions as the focal units of analysis for understanding query reformulations [10][11][12]26,33]. Other works rather studied users' query reformulations from the task perspective through user studies [15,17,29].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

What Can Task Teach Us About Query Reformulations?

Tamine

Lovón-Melgarejo

Pinel-Sauvagnat

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

A significant amount of prior research has been devoted to understanding query reformulations. The majority of these works rely on time-based sessions which are sequences of contiguous queries segmented using time threshold on users' activities. However, queries are generally issued by users having in mind a particular task, and time-based sessions unfortunately fail in revealing such tasks. In this paper, we are interested in revealing in which extent time-based sessions vs. task-based sessions represent significantly different background contexts to be used in the perspective of better understanding users' query reformulations. Using insights from large-scale search logs, our findings clearly show that task is an additional relevant search unit that helps better understanding user's query reformulation patterns and predicting the next user's query. The findings from our analyses provide potential implications for model design of task-based search engines.

show abstract

Section: Query Reformulation Understandingmentioning

confidence: 99%

Section: Query Reformulation Understandingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

What Can Task Teach Us About Query Reformulations?

Tamine

Lovón-Melgarejo

Pinel-Sauvagnat

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…A hierarchical recurrent encoder-decoder model [38] is introduced to query suggestion. He et al [18] proposed a learning to rewrite framework consisting of a candidate generating phase and a candidate ranking phase for query rewriting. Song et al [37] use an RNN encoder-decoder to translate a natural language query into a keyword query.…”

Section: Query Generationmentioning

confidence: 99%

Domain-Constrained Advertising Keyword Generation

Zhou

Huang

Mao³

et al. 2019

The World Wide Web Conference

View full text Add to dashboard Cite

Advertising (ad for short) keyword suggestion is important for sponsored search to improve online advertising and increase search revenue. There are two common challenges in this task. First, the keyword bidding problem: hot ad keywords are very expensive for most of the advertisers because more advertisers are bidding on more popular keywords, while unpopular keywords are difficult to discover. As a result, most ads have few chances to be presented to the users. Second, the inefficient ad impression issue: a large proportion of search queries, which are unpopular yet relevant to many ad keywords, have no ads presented on their search result pages. Existing retrieval-based or matching-based methods either deteriorate the bidding competition or are unable to suggest novel keywords to cover more queries, which leads to inefficient ad impressions.To address the above issues, this work investigates to use generative neural networks for keyword generation in sponsored search. Given a purchased keyword (a word sequence) as input, our model can generate a set of keywords that are not only relevant to the input but also satisfy the domain constraint which enforces that the domain category of a generated keyword is as expected. Furthermore, a reinforcement learning algorithm is proposed to adaptively utilize domain-specific information in keyword generation. Offline evaluation shows that the proposed model can generate keywords that are diverse, novel, relevant to the source keyword, and accordant with the domain constraint. Online evaluation shows that generative models can improve coverage (COV), click-through rate (CTR), and revenue per mille (RPM) substantially in sponsored search.

show abstract