From Word Embeddings to Item Recommendation

Özsoy, Makbule Gülçin

doi:10.48550/arxiv.1601.01356

Cited by 10 publications

(18 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are venue recommendation systems which use word/document embedding techniques in the literature. Ozsoy et al [21] made an analogy in between "sentences and all check-ins per user" and "words and individual check-ins" and employed Doc2Vec to make venue recommendations. Manotumruksa et al [15] made venue recommendations by inferring the vector space representations of venues.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Utilizing FastText for Venue Recommendation

Ozsoy

2020

Preprint

Self Cite

View full text Add to dashboard Cite

Venue recommendation systems model the past interactions (i.e., check-ins) of the users and recommend venues. Traditional recommendation systems employ collaborative filtering, content-based filtering or matrix factorization. Recently, vector space embedding and deep learning algorithms are also used for recommendation. In this work, I propose a method for recommending top-k venues by utilizing the sequentiality feature of check-ins and a recent vector space embedding method, namely the FastText. Our proposed method; forms groups of check-ins, learns the vector space representations of the venues and utilizes the learned embeddings to make venue recommendations. I measure the performance of the proposed method using a Foursquare check-in dataset.The results show that the proposed method performs better than the state-of-the-art methods.

show abstract

Section: Related Workmentioning

confidence: 99%

“…The embedding techniques, Word2Vec [18] and Doc2Vec [10] are frequently used for making recommendations, e.g. [21], [15], [35], [30]. Although these techniques are powerful at learning the semantic relations among venues and users, a newer method named FastText [2] can be more performant to represent the venues.…”

Section: Introductionmentioning

confidence: 99%

Utilizing FastText for Venue Recommendation

Ozsoy

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Word embeddings have been successfully employed in many NLP and Information Retrieval (IR) tasks. For example, word embedding vectors are applied in information retrieval (Ganguly et al 2015), recommendation systems (Ozsoy 2016), text classification (Ge and Moh 2017), etc.…”

Section: Word Embeddingmentioning

confidence: 99%

Contextual Compositionality Detection with External Knowledge Bases and Word Embeddings

Wang

Lima³

et al. 2019

Companion Proceedings of the 2019 World Wide Web Conference

View full text Add to dashboard Cite

When the meaning of a phrase cannot be inferred from the individual meanings of its words (e.g., hot dog), that phrase is said to be non-compositional. Automatic compositionality detection in multiword phrases is critical in any application of semantic processing, such as search engines [9]; failing to detect non-compositional phrases can hurt system effectiveness notably. Existing research treats phrases as either compositional or non-compositional in a deterministic manner. In this paper, we operationalize the viewpoint that compositionality is contextual rather than deterministic, i.e., that whether a phrase is compositional or non-compositional depends on its context. For example, the phrase "green card" is compositional when referring to a green colored card, whereas it is non-compositional when meaning permanent residence authorization. We address the challenge of detecting this type of contextual compositionality as follows: given a multi-word phrase, we enrich the word embedding representing its semantics with evidence about its global context (terms it often collocates with) as well as its local context (narratives where that phrase is used, which we call usage scenarios). We further extend this representation with information extracted from external knowledge bases. The resulting representation incorporates both localized context and more general usage of the phrase and allows to detect its compositionality in a non-deterministic and contextual way. Empirical evaluation of our model on a dataset of phrase compositionality 1 , manually collected by crowdsourcing contextual compositionality assessments, shows that our model outperforms state-of-the-art baselines notably on detecting phrase compositionality.

show abstract

“…Barkan et al [2] demonstrated that learning latent embeddings, using W 2V , for items can enable the inferring of item-to-item relations even in the absence of user information. Similar approach is also used by Ozsoy et al [22]. However, these models use W 2V to learn the item embeddings which treat each user session separately and there is no connection between the context in di erent sessions.…”

Section: Related Workmentioning

confidence: 99%

BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations

Patra,

Samosvat,

Roizner

et al. 2017

Preprint

View full text Add to dashboard Cite

Recommenders have become widely popular in recent years because of their broader applicability in many e-commerce applications. These applications rely on recommenders for generating advertisements for various o ers or providing content recommendations. However, the quality of the generated recommendations depends on user features (like demography, temporality), o er features (like popularity, price), and user-o er features (like implicit or explicit feedback). Current state-of-the-art recommenders do not explore such diverse features concurrently while generating the recommendations.In this paper, we rst introduce the notion of T which enables us to capture the above-mentioned features and thus incorporate users' online behaviour through statistical aggregates of di erent features (demography, temporality, popularity, price). We also show how to capture o er-to-o er relations, based on their consumption sequence, leveraging neural embeddings for offers in our O 2V algorithm. We then introduce B J , a novel recommender which integrates the T along with the neural embeddings using M N , an e cient distributed implementation of gradient boosted decision tree, to improve the recommendation quality signi cantly. We provide an in-depth evaluation of B J on Yandex's dataset, collecting online behaviour from tens of millions of online users, to demonstrate the practicality of B J in terms of recommendation quality as well as scalability.

show abstract

From Word Embeddings to Item Recommendation

Cited by 10 publications

References 12 publications

Utilizing FastText for Venue Recommendation

Utilizing FastText for Venue Recommendation

Contextual Compositionality Detection with External Knowledge Bases and Word Embeddings

BoostJet: Towards Combining Statistical Aggregates with Neural Embeddings for Recommendations

Contact Info

Product

Resources

About