Employing Personal Word Embeddings for Personalized Search

Yao, Jing; Dou, Zhicheng; Wen, Ji-Rong

doi:10.1145/3397271.3401153

Cited by 32 publications

(21 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The meaning of a word can also vary across extralinguistic contexts such as time (Bybee, 2015;Koch, 2016) and social space (Robinson, 2010(Robinson, , 2012Geeraerts, 2018). To capture these phenomena, various types of dynamic word embeddings have been proposed: diachronic word embeddings for temporal semantic change (Bamler and Mandt, 2017;Rosenfeld and Erk, 2018;Rudolph and Blei, 2018;Yao et al, 2018;Gong et al, 2020) and personalized word embeddings for social semantic variation (Zeng et al, 2017(Zeng et al, , 2018Oba et al, 2019;Welch et al, 2020a,b;Yao et al, 2020). Other studies have demonstrated that performance on a diverse set of tasks can be increased by including temporal (Jaidka et al, 2018;Lukes and Søgaard, 2018) and social information (Amir et al, 2016;Hamilton et al, 2016a;Yang et al, 2016;Yang and Eisenstein, 2017;Hazarika et al, 2018;Mishra et al, 2018;del Tredici et al, 2019b;Li and Goldwasser, 2019;Mishra et al, 2019).…”

Section: Dynamic Word Embeddingsmentioning

confidence: 99%

Dynamic Contextualized Word Embeddings

Hofmann

Pierrehumbert

Schütze

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Static word embeddings that represent words by a single vector cannot capture the variability of word meaning in different linguistic and extralinguistic contexts. Building on prior work on contextualized and dynamic word embeddings, we introduce dynamic contextualized word embeddings that represent words as a function of both linguistic and extralinguistic context. Based on a pretrained language model (PLM), dynamic contextualized word embeddings model time and social space jointly, which makes them attractive for a range of NLP tasks involving semantic variability. We highlight potential application scenarios by means of qualitative and quantitative analyses on four English datasets.

show abstract

Section: Dynamic Word Embeddingsmentioning

confidence: 99%

Dynamic Contextualized Word Embeddings

Hofmann

Pierrehumbert

Schütze

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

show abstract

“…Moreover, methods based on adversarial neural networks [15] and reinforcement learning [37] have also been proposed for enhancing data quality. In addition to these user profile-based methods, Zhou et al [39] and Yao et al [36] argued that the query representation is dynamically changing in different historical contexts. They used the history to learn the embedding of the current query.…”

Section: Related Work 21 Personalized Web Searchmentioning

confidence: 99%

Group based Personalized Search by Integrating Search Behaviour and Friend Network

Zhou

Dou

Wei

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

Self Cite

View full text Add to dashboard Cite

The key to personalized search is to build the user profile based on historical behaviour. To deal with the users who lack historical data, group based personalized models were proposed to incorporate the profiles of similar users when re-ranking the results. However, similar users are mostly found based on simple lexical or topical similarity in search behaviours. In this paper, we propose a neural network enhanced method to highlight similar users in semantic space. Furthermore, we argue that the behaviour-based similar users are still insufficient to understand a new query when user's historical activities are limited. To tackle this issue, we introduce the friend network into personalized search to determine the closeness between users in another way. Since the friendship is often formed based on similar background or interest, there are plenty of personalized signals hidden in the friend network naturally. Specifically, we propose a friend network enhanced personalized search model, which groups the user into multiple friend circles based on search behaviours and friend relations respectively. These two types of friend circles are complementary to construct a more comprehensive group profile for refining the personalization. Experimental results show the significant improvement of our model over existing personalized search models.

show abstract

“…In previous studies, the processing of AOL query logs is not sufficiently clear for the construction of personalized search datasets. The existing personalized search datasets based on AOL query logs in different scales in other papers are almost publicly unavailable [4,5]. It is because there is no complete and clear dataset construction process and no publicly available personalized search dataset, there is a gap to fill in the research field of personalized search.…”

Section: Related Workmentioning

confidence: 99%

“…Some available public datasets, e.g., Yandex 1 and SEARCH17 [3], have no raw text of queries or documents. For another famous data collection, AOL query logs [4,5], there are no publicly available personalized search datasets based.…”

Section: Introductionmentioning

confidence: 99%

AOL4PS: A Large-scale Data Set for Personalized Search

2021

View full text Add to dashboard Cite

Personalized search is a promising way to improve the quality of web search, and it has attracted much attention from both academic and industrial communities. Much of the current related research is based on commercial search engine data, which can not be released publicly for such reasons as privacy protection and information security. This leads to a serious lack of accessible public datasets in this field. The few available datasets though released to the public have not become widely used in academia due to the complexity of the processing process. The lack of datasets together with the difficulties of data processing have brought obstacles to fair comparison and evaluation of personalized search models. In this paper, we constructed a large-scale dataset AOL4PS to evaluate personalized search methods, collected and processed from AOL query logs. We present the complete and detailed data processing and construction process. Specifically, to address the challenges of processing time and storage space demands brought by massive data volumes, we optimized the process of dataset construction and proposed an improved BM25 algorithm. Experiments are performed on AOL4PS with some classic and state-of-the-art personalized search methods, and the experiment results demonstrate that AOL4PS can measure the effect of personalized search models. AOL4PS is publicly available at http://github.com/wanhuaiyu/AOL4PS.

show abstract

Employing Personal Word Embeddings for Personalized Search

Cited by 32 publications

References 19 publications

Dynamic Contextualized Word Embeddings

Dynamic Contextualized Word Embeddings

Group based Personalized Search by Integrating Search Behaviour and Friend Network

AOL4PS: A Large-scale Data Set for Personalized Search

Contact Info

Product

Resources

About