Attention-based mixture density recurrent networks for history-based recommendation

Cho, Kyunghyun; Wen, Musen

doi:10.1145/3326937.3341254

Cited by 7 publications

(4 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also a difficult baseline to beat in terms of generating user engagement, given that these are items the user has engaged with recently. The works of Song et al [28] and Wang et al [29] show approaches similar to RVI to be strong baseline methods, outperforming CF-based methods.…”

Section: Offline Evaluationmentioning

confidence: 99%

Personalized Embedding-based e-Commerce Recommendations at eBay

Brovman¹,

Madhvanath²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Recommender systems are an essential component of e-commerce marketplaces, helping consumers navigate massive amounts of inventory and find what they need or love. In this paper, we present an approach for generating personalized item recommendations in an e-commerce marketplace by learning to embed items and users in the same vector space. In order to alleviate the considerable cold-start problem present in large marketplaces, item and user embeddings are computed using content features and multi-modal onsite user activity respectively. Data ablation is incorporated into the offline model training process to improve the robustness of the production system. In offline evaluation using a dataset collected from eBay traffic, our approach was able to improve the Recall@k metric over the Recently-Viewed-Item (RVI) method. This approach to generating personalized recommendations has been launched to serve production traffic, and the corresponding scalable engineering architecture is also presented. Initial A/B test results show that compared to the current personalized recommendation module in production, the proposed method increases the surface rate by ∼6% to generate recommendations for 90% of listing page impressions.

show abstract

Section: Offline Evaluationmentioning

confidence: 99%

Personalized Embedding-based e-Commerce Recommendations at eBay

Brovman¹,

Madhvanath²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Other ways to achieve the permutation invariant loss for neural networks include sequential decision making (Welleck et al 2018), mixture of experts (Yang et al 2018b;Wang, Cho, and Wen 2019), beam search (Qin et al 2019), predicting the permutation using a CNN (Rezatofighi et al 2018), Transformers (Stern et al 2019;Gu, Liu, and Cho 2019;Carion et al 2020) or reinforcement learning (Welleck et al 2019). In contrast, our goal is to efficiently predict a set of cluster centers that can well reconstruct the set of observed instances rather than directly predicting the observed instances.…”

Section: Related Workmentioning

confidence: 99%

Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

Chang

Agrawal

McCallum

2021

Preprint

View full text Add to dashboard Cite

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel embedding method for a text sequence (a phrase or a sentence) where each sequence is represented by a distinct set of multi-mode codebook embeddings to capture different semantic facets of its meaning. The codebook embeddings can be viewed as the cluster centers which summarize the distribution of possibly co-occurring words in a pre-trained word embedding space. We introduce an end-to-end trainable neural model that directly predicts the set of cluster centers from the input text sequence during test time. Our experiments show that the per-sentence codebook embeddings significantly improve the performances in unsupervised sentence similarity and extractive summarization benchmarks. In phrase similarity experiments, we discover that the multifacet embeddings provide an interpretable semantic representation but do not outperform the single-facet baseline.

show abstract

Section: Related Workmentioning

confidence: 99%

Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

Chang

Agrawal

McCallum

2021

AAAI

View full text Add to dashboard Cite

Most unsupervised NLP models represent each word with a single point or single region in semantic space, while the existing multi-sense word embeddings cannot represent longer word sequences like phrases or sentences. We propose a novel embedding method for a text sequence (a phrase or a sentence) where each sequence is represented by a distinct set of multi-mode codebook embeddings to capture different semantic facets of its meaning. The codebook embeddings can be viewed as the cluster centers which summarize the distribution of possibly co-occurring words in a pre-trained word embedding space. We introduce an end-to-end trainable neural model that directly predicts the set of cluster centers from the input text sequence during test time. Our experiments show that the per-sentence codebook embeddings significantly improve the performances in unsupervised sentence similarity and extractive summarization benchmarks. In phrase similarity experiments, we discover that the multi-facet embeddings provide an interpretable semantic representation but do not outperform the single-facet baseline.

show abstract

Attention-based mixture density recurrent networks for history-based recommendation

Cited by 7 publications

References 27 publications

Personalized Embedding-based e-Commerce Recommendations at eBay

Personalized Embedding-based e-Commerce Recommendations at eBay

Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

Extending Multi-Sense Word Embedding to Phrases and Sentences for Unsupervised Semantic Applications

Contact Info

Product

Resources

About