Optimizing query rewrites for keyword-based advertising

Malekian, Azarakhsh; Chang, C.; Kumar, Ravi; Wang, Grant

doi:10.1145/1386790.1386793

Cited by 12 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We evaluate LR-ID-63 on 1% traffic of our e-commerce platform. The baseline is a graph covering method similar to [9], which has been shown very effective on our platform, outperforming lots of conventionally incorporated methods such as Simrank++ in [6]. Table 6 summarizes the average metric lift rates.…”

Section: Online Metrics and Experimental Resultsmentioning

confidence: 99%

“…Only a few of works study this problem. Malekian et al [9] proposes a combinatorial framework for optimizing query rewriting, taking the relevance and budget constraints of ads into account. They regard rewriting as a graph covering problem on a graph of queries, keywords, and ads, and select keywords for each query, so that the benefit of the ads adjacent to the rewrites is maximized subject to ad system and budget constraints.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Beyond Keywords and Relevance

Yan

Lin

et al. 2018

Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18

View full text Add to dashboard Cite

On most sponsored search platforms, advertisers bid on some keywords for their advertisements (ads). Given a search request, ad retrieval module rewrites the query into bidding keywords, and uses these keywords as keys to select Top N ads through inverted indexes. In this way, an ad will not be retrieved even if queries are related when the advertiser does not bid on corresponding keywords. Moreover, most ad retrieval approaches regard rewriting and ad-selecting as two separated tasks, and focus on boosting relevance between search queries and ads. Recently, in ecommerce sponsored search more and more personalized information has been introduced, such as user profiles, long-time and real-time clicks. Personalized information makes ad retrieval able to employ more elements (e.g. real-time clicks) as search signals and retrieval keys, however it makes ad retrieval more difficult to measure ads retrieved through different signals. To address these problems, we propose a novel ad retrieval framework beyond keywords and relevance in e-commerce sponsored search. Firstly, we employ historical ad click data to initialize a hierarchical network representing signals, keys and ads, in which personalized information is introduced. Then we train a model on top of the hierarchical network by learning the weights of edges. Finally we select the best edges according to the model, boosting RPM/CTR. Experimental results on our e-commerce platform demonstrate that our ad retrieval framework achieves good performance. 1

show abstract

Section: Online Metrics and Experimental Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Beyond Keywords and Relevance

Yan

Lin

et al. 2018

Proceedings of the 2018 World Wide Web Conference on World Wide Web - WWW '18

View full text Add to dashboard Cite

show abstract

“…RQRF is deployed on a real-world commercial search engine to serve ads as part of A/B testing. The traditional statistic-based memory model from (Malekian et al 2008) is used as the control model and RQRF as the treatment. The flight tests are conducted for a period of one month.…”

Section: Methodsmentioning

confidence: 99%

“…More comprehensive works are based on graphs. For example, (Malekian et al 2008) formulates a family of graph covering problems whose goals are to suggest a subset of ads with the maximum benefit by suggesting rewrites for a given query. However, these models also have shortcomings: (1) Each query is regarded as a non-splittable graph node, which hinders the full understanding of queries.…”

Section: Introductionmentioning

confidence: 99%

RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search (Student Abstract)

Chen

Xiao

Gao

et al. 2020

AAAI

View full text Add to dashboard Cite

Sponsored search optimizes revenue and relevance, which is estimated by Revenue Per Mille (RPM). Existing sponsored search models are all based on traditional statistical models, which have poor RPM performance when queries follow a heavy-tailed distribution. Here, we propose an RPMoriented Query Rewriting Framework (RQRF) which outputs related bid keywords that can yield high RPM. RQRF embeds both queries and bid keywords to vectors in the same implicit space, converting the rewriting probability between each query and keyword to the distance between the two vectors. For label construction, we propose an RPM-oriented sample construction method, labeling keywords based on whether or not they can lead to high RPM. Extensive experiments are conducted to evaluate performance of RQRF. In a one month large-scale real-world traffic of e-commerce sponsored search system, the proposed model significantly outperforms traditional baseline.

show abstract

“…Most sponsored search systems use query rewriting technique [18] to alleviate this problem, within which several query rewrites would be used as alternative queries to retrieve keywords. As is illustrated in Figure 1, the keyword retrieval process usually comprises three stages:…”

Section: Merged Keywordmentioning

confidence: 99%

An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain

Lian,

Chen,

et al. 2019

Preprint

View full text Add to dashboard Cite

In this paper, we present a generative retrieval method for sponsored search engine, which uses neural machine translation (NMT) to generate keywords directly from query. This method is completely end-to-end, which skips query rewriting and relevance judging phases in traditional retrieval systems. Different from standard machine translation, the target space in the retrieval setting is a constrained closed set, where only committed keywords should be generated. We present a Trie-based pruning technique in beam search to address this problem. The biggest challenge in deploying this method into a real industrial environment is the latency impact of running the decoder. Self-normalized training coupled with Trie-based dynamic pruning dramatically reduces the inference time, yielding a speedup of more than 20 times. We also devise an mixed online-offline serving architecture to reduce the latency and CPU consumption. To encourage the NMT to generate new keywords uncovered by the existing system, training data is carefully * Muchenxuan Tong works now at Didi Chuxing.† Ying Li works now at Ant Finance. ‡ Ying Cao works now at Microsoft. § Yang Yu works now at aelf.io.

show abstract

Optimizing query rewrites for keyword-based advertising

Cited by 12 publications

References 18 publications

Beyond Keywords and Relevance

Beyond Keywords and Relevance

RPM-Oriented Query Rewriting Framework for E-commerce Keyword-Based Sponsored Search (Student Abstract)

An end-to-end Generative Retrieval Method for Sponsored Search Engine --Decoding Efficiently into a Closed Target Domain

Contact Info

Product

Resources

About