Large-scale Generative Query Autocompletion

Maxwell, David; Bailey, Peter; Hawking, David

doi:10.1145/3166072.3166083

Cited by 14 publications

(7 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the future, we plan to improve the performance of PrefXMRtree models by exploring label space augmentation techniques and using partial prefixes for generating auto-complete suggestions [25,27]. We also plan to use dense embeddings for representing contextual information such as previous queries, the user-profile, or time to further improve the performance of PrefXMRtree models for the task of query auto-completion.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Session-Aware Query Auto-completion using Extreme Multi-Label Ranking

Yadav

Sen

Hill

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Query auto-completion (QAC) is a fundamental feature in search engines where the task is to suggest plausible completions of a prefix typed in the search bar. Previous queries in the user session can provide useful context for the user's intent and can be leveraged to suggest auto-completions that are more relevant while adhering to the user's prefix. Such session-aware QACs can be generated by recent sequence-to-sequence deep learning models; however, these generative approaches often do not meet the stringent latency requirements of responding to each user keystroke. Moreover, these generative approaches pose the risk of showing nonsensical queries. One can pre-compute a relatively small subset of relevant queries for common prefixes and rank them based on the context. However, such an approach fails when no relevant queries for the current context are present in the pre-computed set.

show abstract

Section: Discussionmentioning

confidence: 99%

“…gestions[25,27] but we leave that to future work and compare all the models on test data restricted to cases where the ground-truth label (next query) is present in training data, and analyse the effect of prefix length and label frequency on performance of all models.…”

mentioning

confidence: 99%

Session-Aware Query Auto-completion using Extreme Multi-Label Ranking

Yadav

Sen

Hill

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

show abstract

“…In the future, we plan to improve the performance of PrefXMRtree models by exploring label space augmentation techniques and using partial prefixes for generating auto-complete suggestions [29,31]. We also plan to use dense embeddings for representing contextual information such as previous queries, the user-profile, or time to further improve the performance of PrefXMRtree models for the task of query auto-completion.…”

Section: Discussionmentioning

confidence: 99%

“…Hence, for the remaining test data points, PrefXMRtree models and MFQ cannot generate correct suggestions, while the generative seq2seq models are sometimes able to. The performance of PrefXMRtree can be improved by augmenting the label space to improve coverage and/or using a partial prefix for generating suggestions [29,31] but we leave that to future work and compare all the models on test data restricted to cases where the groundtruth label (next query) is present in training data, and analyse the effect of prefix length and label frequency on performance of all models.…”

Section: Comparison With Other Baselinesmentioning

confidence: 99%

Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Yadav,

Sen,

Hill

et al. 2020

Preprint

View full text Add to dashboard Cite

Query auto-completion is a fundamental feature in search engines where the task is to suggest plausible completions of a prefix typed in the search bar. Previous queries in the user session can provide useful context for the user's intent and can be leveraged to suggest auto-completions that are more relevant while adhering to the user's prefix. Such session-aware query auto-completions can be generated by recent sequence-to-sequence deep learning models; however, these generative approaches often do not meet the stringent latency requirements of responding to each user keystroke. Moreover, there is a danger of showing non-sensical queries in a generative approach. One solution to the latter problem is to only show queries as auto-completions that have been seen by the search system in the recent past. However, a typical commercial search system might see tens of millions of queries, and it is challenging to search through this enormous set while maintaining latencies as low as 20 milliseconds. One can pre-compute a relatively small subset of relevant queries for common prefixes and rank them based on the context. However, such an approach would fail if no relevant queries for the current context are present in the pre-computed set.In this paper, we provide a solution to this problem: we take the novel approach of modeling session-aware query auto-completion as an eXtreme Multi-Label Ranking (XMR) problem where the input is the previous query in the session and the user's current prefix, while the output space is the set of tens of millions of queries entered by users in the recent past. We adapt a popular XMR algorithm for this purpose by proposing several modifications to the key steps in the algorithm. The proposed modifications yield a 230% improvement in terms of Mean Reciprocal Rank over the baseline XMR approach on a public search logs dataset. Our approach meets the stringent latency requirements for auto-complete systems while leveraging session information in making suggestions. We show that session context leads to significant improvements in the quality of query auto-completions; in particular, for short prefixes with up

show abstract

“…A QAC system retrieves a candidate set matching the partial query P, drawing from a target string collection, with strings in the target collection having an associated score. Query Auto Completion systems typically match P against past queries from a log; or, in the absence of logs, they can also be synthesized [14,40]. Methods of ranking the candidates include static popularity [9], search context [9,29], forecast popularity [15], personalized ranking parameters [15,29,42], and diversity [16].…”

Section: Introductionmentioning

confidence: 99%

Generation of Synthetic Query Auto Completion Logs

Krishnan

Moffat

Zobel

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Privacy concerns can prohibit research access to large-scale commercial query logs. Here we focus on generation of a synthetic log from a publicly available dataset, suitable for evaluation of query auto completion (QAC) systems. The synthetic log contains plausible string sequences reflecting how users enter their queries in a QAC interface. Properties that would influence experimental outcomes are compared between a synthetic log and a real QAC log through a set of side-byside experiments, and confirm the applicability of the generated log for benchmarking the performance of QAC methods.

show abstract

Large-scale Generative Query Autocompletion

Cited by 14 publications

References 30 publications

Session-Aware Query Auto-completion using Extreme Multi-Label Ranking

Session-Aware Query Auto-completion using Extreme Multi-Label Ranking

Session-Aware Query Auto-completion using Extreme Multi-label Ranking

Generation of Synthetic Query Auto Completion Logs

Contact Info

Product

Resources

About