FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3130694907> ?p ?o ?g. }

• W3130694907 abstract "In E-commerce, a key challenge in text generation is to find a good trade-off between word diversity and accuracy (relevance) in order to make generated text appear more natural and human-like. In order to improve the relevance of generated results, conditional text generators were developed that use input keywords or attributes to produce the corresponding text. Prior work, however, do not finely control the diversity of automatically generated sentences. For example, it does not control the order of keywords to put more relevant ones first. Moreover, it does not explicitly control the balance between diversity and accuracy. To remedy these problems, we propose a fine-grained controllable generative model, called~textit{Apex}, that uses an algorithm borrowed from automatic control (namely, a variant of the textit{proportional, integral, and derivative (PID) controller}) to precisely manipulate the diversity/accuracy trade-off of generated text. The algorithm is injected into a Conditional Variational Autoencoder (CVAE), allowing textit{Apex} to control both (i) the order of keywords in the generated sentences (conditioned on the input keywords and their order), and (ii) the trade-off between diversity and accuracy. Evaluation results on real-world datasets show that the proposed method outperforms existing generative models in terms of diversity and relevance. Apex is currently deployed to generate production descriptions and item recommendation reasons in Taobao owned by Alibaba, the largest E-commerce platform in China. The A/B production test results show that our method improves click-through rate (CTR) by 13.17% compared to the existing method for production descriptions. For item recommendation reason, it is able to increase CTR by 6.89% and 1.42% compared to user reviews and top-K item recommendation without reviews, respectively." @default.
• W3130694907 created "2021-03-01" @default.
• W3130694907 creator A5010101040 @default.
• W3130694907 creator A5022094334 @default.
• W3130694907 creator A5025823765 @default.
• W3130694907 creator A5037027582 @default.
• W3130694907 creator A5041685416 @default.
• W3130694907 creator A5049841140 @default.
• W3130694907 creator A5075033889 @default.
• W3130694907 date "2021-02-23" @default.
• W3130694907 modified "2023-09-24" @default.
• W3130694907 title "Controllable and Diverse Text Generation in E-commerce" @default.
• W3130694907 cites W1530435204 @default.
• W3130694907 cites W1990378975 @default.
• W3130694907 cites W2015244008 @default.
• W3130694907 cites W2075577126 @default.
• W3130694907 cites W2099471712 @default.
• W3130694907 cites W2105501265 @default.
• W3130694907 cites W2123301721 @default.
• W3130694907 cites W2130942839 @default.
• W3130694907 cites W2134282505 @default.
• W3130694907 cites W2148404145 @default.
• W3130694907 cites W2210838531 @default.
• W3130694907 cites W2214168287 @default.
• W3130694907 cites W2337374637 @default.
• W3130694907 cites W2605246398 @default.
• W3130694907 cites W2616969219 @default.
• W3130694907 cites W2757836268 @default.
• W3130694907 cites W2775022418 @default.
• W3130694907 cites W2785896739 @default.
• W3130694907 cites W2786744843 @default.
• W3130694907 cites W2798277467 @default.
• W3130694907 cites W2805486818 @default.
• W3130694907 cites W2889862754 @default.
• W3130694907 cites W2890969459 @default.
• W3130694907 cites W2892153332 @default.
• W3130694907 cites W2896457183 @default.
• W3130694907 cites W2908804015 @default.
• W3130694907 cites W2922338294 @default.
• W3130694907 cites W2951004968 @default.
• W3130694907 cites W2951520714 @default.
• W3130694907 cites W2951575317 @default.
• W3130694907 cites W2951670304 @default.
• W3130694907 cites W2963403868 @default.
• W3130694907 cites W2964042872 @default.
• W3130694907 cites W2964222296 @default.
• W3130694907 cites W2964265128 @default.
• W3130694907 cites W2964268978 @default.
• W3130694907 cites W2970909388 @default.
• W3130694907 cites W2971060546 @default.
• W3130694907 cites W3105157853 @default.
• W3130694907 cites W3105830849 @default.
• W3130694907 cites W3092847270 @default.
• W3130694907 doi "https://doi.org/10.48550/arxiv.2102.11497" @default.
• W3130694907 hasPublicationYear "2021" @default.
• W3130694907 type Work @default.
• W3130694907 sameAs 3130694907 @default.
• W3130694907 citedByCount "1" @default.
• W3130694907 countsByYear W31306949072021 @default.
• W3130694907 crossrefType "posted-content" @default.
• W3130694907 hasAuthorship W3130694907A5010101040 @default.
• W3130694907 hasAuthorship W3130694907A5022094334 @default.
• W3130694907 hasAuthorship W3130694907A5025823765 @default.
• W3130694907 hasAuthorship W3130694907A5037027582 @default.
• W3130694907 hasAuthorship W3130694907A5041685416 @default.
• W3130694907 hasAuthorship W3130694907A5049841140 @default.
• W3130694907 hasAuthorship W3130694907A5075033889 @default.
• W3130694907 hasBestOaLocation W31306949071 @default.
• W3130694907 hasConcept C10138342 @default.
• W3130694907 hasConcept C101738243 @default.
• W3130694907 hasConcept C108583219 @default.
• W3130694907 hasConcept C11413529 @default.
• W3130694907 hasConcept C119857082 @default.
• W3130694907 hasConcept C127413603 @default.
• W3130694907 hasConcept C133731056 @default.
• W3130694907 hasConcept C139719470 @default.
• W3130694907 hasConcept C144024400 @default.
• W3130694907 hasConcept C154945302 @default.
• W3130694907 hasConcept C158154518 @default.
• W3130694907 hasConcept C162324750 @default.
• W3130694907 hasConcept C167966045 @default.
• W3130694907 hasConcept C17744445 @default.
• W3130694907 hasConcept C182306322 @default.
• W3130694907 hasConcept C19165224 @default.
• W3130694907 hasConcept C199539241 @default.
• W3130694907 hasConcept C203479927 @default.
• W3130694907 hasConcept C2524010 @default.
• W3130694907 hasConcept C2775924081 @default.
• W3130694907 hasConcept C2778348673 @default.
• W3130694907 hasConcept C2781316041 @default.
• W3130694907 hasConcept C33923547 @default.
• W3130694907 hasConcept C39890363 @default.
• W3130694907 hasConcept C41008148 @default.
• W3130694907 hasConcept C47116090 @default.
• W3130694907 hasConcept C536315585 @default.
• W3130694907 hasConcept C6557445 @default.
• W3130694907 hasConcept C86803240 @default.
• W3130694907 hasConcept C90805587 @default.
• W3130694907 hasConceptScore W3130694907C10138342 @default.
• W3130694907 hasConceptScore W3130694907C101738243 @default.

• next