Query Expansion for Email Search

Kuzi, Saar; Carmel, David; Libov, Alex; Raviv, Ariel

doi:10.1145/3077136.3080660

Cited by 19 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Creating user models from explicit signals like queries, clicks, likes, social links, etc. [1] or/and rich contents like email histories or desktop data [14,22]. 2.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Personalized Entity Search by Sparse and Scrutable User Profiles

Torbati

Yates

Weikum

2020

Proceedings of the 2020 Conference on Human Information Interaction and Retrieval

View full text Add to dashboard Cite

Prior work on personalizing web search results has focused on considering query-and-click logs to capture users' individual interests. For product search, extensive user histories about purchases and ratings have been exploited. However, for general entity search, such as for books on specific topics or travel destinations with certain features, personalization is largely underexplored. In this paper, we address personalization of book search, as an exemplary case of entity search, by exploiting sparse user profiles obtained through online questionnaires. We devise and compare a variety of re-ranking methods based on language models or neural learning. Our experiments show that even very sparse information about individuals can enhance the effectiveness of the search results.

show abstract

“…Creating user models from explicit signals like queries, clicks, likes, social links, etc. [1] or/and rich contents like email histories or desktop data [14,22]. 2.…”

Section: Related Workmentioning

confidence: 99%

“…[11,39] utilize folksonomy data, like user-provided tags in social bookmarking communities, as a source for expanding a user's queries. [22] personalizes email search via word embeddings learned from email histories. [14] proposes methods for harnessing a user's desktop files (incl.…”

Section: Related Workmentioning

confidence: 99%

Personalized Entity Search by Sparse and Scrutable User Profiles

Torbati

Yates

Weikum

2020

Proceedings of the 2020 Conference on Human Information Interaction and Retrieval

View full text Add to dashboard Cite

show abstract

“…A number of studies specifically focus on improving the content-based relevance signals in email search. Kuzi et al [27] explored several methods to expand the usually short and sparse queries by finding more related terms to improve the relevance results. Li et al [29] studied a more specific synonym expansion problem to improve email search performance.…”

Section: Email Searchmentioning

confidence: 99%

Separate and Attend in Personal Email Search

Karimzadehgan

Zhuang

et al. 2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

In personal email search, user queries often impose different requirements on different aspects of the retrieved emails. For example, the query "my recent flight to the US" requires emails to be ranked based on both textual contents and recency of the email documents, while other queries such as "medical history" do not impose any constraints on the recency of the email. Recent deep learning-to-rank models for personal email search often directly concatenate dense numerical features 1 (e.g., document age) with embedded sparse features (e.g., n-gram embeddings). In this paper, we first show with a set of experiments on synthetic datasets that direct concatenation of dense and sparse features does not lead to the optimal search performance of deep neural ranking models. To effectively incorporate both sparse and dense email features into personal email search ranking, we propose a novel neural model, SepAttn. SepAttn first builds two separate neural models to learn from sparse and dense features respectively, and then applies an attention mechanism at the prediction level to derive the final prediction from these two models. We conduct a comprehensive set of experiments on a large-scale email search dataset, and demonstrate that our SepAttn model consistently improves the search quality over the baseline models.

show abstract

“…For example, many techniques rely on the bipartite query-document click graph to expand the query [19,20,52,64]. Most recently with the success of embedding-based methods and deep learning techniques, query expansion has been further improved by considering terms that are close in the embedding space [22,41,54].…”

Section: Introductionmentioning

confidence: 99%

“…Compared with the large amount of prior work on synonym expansion for web search, the research on synonym expansion for email search is still at a nascent stage [41]. This is despite the fact that a large number of users are relying on email search on a daily basis to access their emails [13,59].…”

Section: Introductionmentioning

confidence: 99%

Multi-view Embedding-based Synonyms for Email Search

Zhang

Bendersky

et al. 2019

Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Synonym expansion is a technique that adds related words to search queries, which may lead to more relevant documents being retrieved, thus improving recall. There is extensive prior work on synonym expansion for web search, however very few studies have tackled its application for email search. Synonym expansion for private corpora like emails poses several unique research challenges. First, the emails are not shared across users, which precludes us from directly employing query-document bipartite graphs, which are standard in web search synonym expansion. Second, user search queries are of personal nature, and may not be generalizable across users. Third, the size of the underlying corpora from which the synonyms may be mined is relatively small (i.e., user's private email inbox) compared to the size of the web corpus. Therefore, in this paper, we propose a solution tailored to the challenges of synonym expansion for email search. We formulate it as a multi-view learning problem, and propose a novel embedding-based model that joins information from multiple sources to obtain the optimal synonym candidates. To demonstrate the effectiveness of the proposed technique, we evaluate our model using both explicit human ratings as well as a live experiment using the Gmail Search service, one of the world's largest email search engines.

show abstract

Query Expansion for Email Search

Cited by 19 publications

References 8 publications

Personalized Entity Search by Sparse and Scrutable User Profiles

Personalized Entity Search by Sparse and Scrutable User Profiles

Separate and Attend in Personal Email Search

Multi-view Embedding-based Synonyms for Email Search

Contact Info

Product

Resources

About