Standard

Traversing semantically annotated qeries for task-oriented qery recommendation. / Câmara, Arthur; Santos, Rodrygo L.T.

RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery (ACM), 2019. p. 511-515.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Câmara, A & Santos, RLT 2019, Traversing semantically annotated qeries for task-oriented qery recommendation. in RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery (ACM), pp. 511-515, 13th ACM Conference on Recommender Systems, RecSys 2019, Copenhagen, Denmark, 16/09/19. https://doi.org/10.1145/3298689.3346994

APA

Câmara, A., & Santos, R. L. T. (2019). Traversing semantically annotated qeries for task-oriented qery recommendation. In RecSys 2019 - 13th ACM Conference on Recommender Systems (pp. 511-515). Association for Computing Machinery (ACM). https://doi.org/10.1145/3298689.3346994

Vancouver

Câmara A, Santos RLT. Traversing semantically annotated qeries for task-oriented qery recommendation. In RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery (ACM). 2019. p. 511-515 https://doi.org/10.1145/3298689.3346994

Author

Câmara, Arthur ; Santos, Rodrygo L.T. / Traversing semantically annotated qeries for task-oriented qery recommendation. RecSys 2019 - 13th ACM Conference on Recommender Systems. Association for Computing Machinery (ACM), 2019. pp. 511-515

BibTeX

@inproceedings{74e4854473544ce6b2db1db936e39e38,
title = "Traversing semantically annotated qeries for task-oriented qery recommendation",
abstract = "As search systems gradually turn into intelligent personal assistants, users increasingly resort to a search engine to accomplish a complex task, such as planning a trip, renting an apartment, or investing in stocks. A key challenge for the search engine is to understand the user's underlying task given a sample query like “tickets to Panama”, “studios in los angeles”, or “spotify stocks”, and to suggest other queries to help the user complete the task. In this paper, we investigate several strategies for query recommendation by traversing a semantically annotated query log using a mixture of explicit and latent representations of entire queries and of query segments. Our results demonstrate the efectiveness of these strategies in terms of utility and diversity, as well as their complementarity, with signifcant improvements compared to state-of-the-art query recommendation baselines adapted for this task.",
keywords = "Query embeddings, Query recommendations, Task understanding",
author = "Arthur C{\^a}mara and Santos, {Rodrygo L.T.}",
year = "2019",
month = "9",
day = "10",
doi = "10.1145/3298689.3346994",
language = "English",
pages = "511--515",
booktitle = "RecSys 2019 - 13th ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery (ACM)",
address = "United States",

}

RIS

TY - GEN

T1 - Traversing semantically annotated qeries for task-oriented qery recommendation

AU - Câmara, Arthur

AU - Santos, Rodrygo L.T.

PY - 2019/9/10

Y1 - 2019/9/10

N2 - As search systems gradually turn into intelligent personal assistants, users increasingly resort to a search engine to accomplish a complex task, such as planning a trip, renting an apartment, or investing in stocks. A key challenge for the search engine is to understand the user's underlying task given a sample query like “tickets to Panama”, “studios in los angeles”, or “spotify stocks”, and to suggest other queries to help the user complete the task. In this paper, we investigate several strategies for query recommendation by traversing a semantically annotated query log using a mixture of explicit and latent representations of entire queries and of query segments. Our results demonstrate the efectiveness of these strategies in terms of utility and diversity, as well as their complementarity, with signifcant improvements compared to state-of-the-art query recommendation baselines adapted for this task.

AB - As search systems gradually turn into intelligent personal assistants, users increasingly resort to a search engine to accomplish a complex task, such as planning a trip, renting an apartment, or investing in stocks. A key challenge for the search engine is to understand the user's underlying task given a sample query like “tickets to Panama”, “studios in los angeles”, or “spotify stocks”, and to suggest other queries to help the user complete the task. In this paper, we investigate several strategies for query recommendation by traversing a semantically annotated query log using a mixture of explicit and latent representations of entire queries and of query segments. Our results demonstrate the efectiveness of these strategies in terms of utility and diversity, as well as their complementarity, with signifcant improvements compared to state-of-the-art query recommendation baselines adapted for this task.

KW - Query embeddings

KW - Query recommendations

KW - Task understanding

UR - http://www.scopus.com/inward/record.url?scp=85073370842&partnerID=8YFLogxK

U2 - 10.1145/3298689.3346994

DO - 10.1145/3298689.3346994

M3 - Conference contribution

SP - 511

EP - 515

BT - RecSys 2019 - 13th ACM Conference on Recommender Systems

PB - Association for Computing Machinery (ACM)

ER -

ID: 62482931