Joint Implicit and Explicit Neural Networks for Question Recommendation in CQA Services

Tu, Hongkui; Wen, Jiahui; Sun, Aixin; Wang, Xiaodong

doi:10.1109/access.2018.2881119

Cited by 10 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the popular of the deep neural network, representation learning is widely used to extract the features of images or texts [13]. The word sequence information is also taken into account to learn the semantic representation of the questions in CQA [4,7,8]. Tu et al [8] employs CNN model to obtain explicit the question textual representation while Zhao et al [7] and Li et al [4] utilize LSTM model to get the question features.…”

Section: Question Recommendation In Cqa Systemsmentioning

confidence: 99%

“…The word sequence information is also taken into account to learn the semantic representation of the questions in CQA [4,7,8]. Tu et al [8] employs CNN model to obtain explicit the question textual representation while Zhao et al [7] and Li et al [4] utilize LSTM model to get the question features. These methods model the text of the answers or questions, which contains the content and description of the answers or questions.…”

Section: Question Recommendation In Cqa Systemsmentioning

confidence: 99%

“…Recently, some methods jointly model the auxiliary information associated with users or answers for recommendation to alleviate the data sparseness problem, which mainly apply heterogeneous network containing social relationship. For example, Tu et al [8] consider social connections to obtain user representation based on that there are strong social connections between users in CQA. Fang et al [2] and Li et al [3] propose the heterogeneous network embedding that can collaboratively utilize the rich interaction among the questions, answers and users.…”

Section: Introductionmentioning

confidence: 99%

“…Another challenge is how to model the communitylevel interaction, i.e., how to model the impact of behavioral associations of social users. Some studies have demonstrated that considering social relationships improves recommendation performance when the user's historical behavior data is scarce [8,12]. Generally, these relationships are represented by adjacent matrices, so that the relationship between two persons is either 0 or 1.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation

Guo

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

Questions in Community Question Answering (CQA) sites are recommended to users, mainly based on users' interest extracted from questions that users have answered or have asked. However, there is a general phenomenon that users answer fewer questions while pay more attention to follow questions and vote answers. This can impact the performance when recommending questions to users (for obtaining their answers) by using their historical answering behaviors on existing studies. To address the data sparsity issue, we propose AskMe, which aims to leverage the rich, hybrid behavior interactions in CQA to improve the question recommendation performance. On the one hand, we model the rich correlations between the user's diverse behaviors (e.g., answer, follow, vote) to obtain the individual-level behavior interaction. On the other hand, we model the sophisticated behavioral associations between similar users to obtain the community-level behavior interaction.

show abstract

Section: Question Recommendation In Cqa Systemsmentioning

confidence: 99%

Section: Question Recommendation In Cqa Systemsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation

Guo

Liu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, deep learning brings remarkable improvements in many researches such as community question answering [14] and visual tracking [15]. New development in speech recognition has also been promoted.…”

Section: History Of Asrmentioning

confidence: 99%

An Overview of End-to-End Automatic Speech Recognition

Wang

2019

Symmetry

Self Cite

173

View full text Add to dashboard Cite

Automatic speech recognition, especially large vocabulary continuous speech recognition, is an important issue in the field of machine learning. For a long time, the hidden Markov model (HMM)-Gaussian mixed model (GMM) has been the mainstream speech recognition framework. But recently, HMM-deep neural network (DNN) model and the end-to-end model using deep learning has achieved performance beyond HMM-GMM. Both using deep learning techniques,

show abstract

Collaborative Community Knowledge Building with Personalized Question Recommendations

Neumann

Breuer

Klamma

2022

Collaboration Technologies and Social Computing

View full text Add to dashboard Cite

Joint Implicit and Explicit Neural Networks for Question Recommendation in CQA Services

Cited by 10 publications

References 41 publications

AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation

AskMe: Joint Individual-level and Community-level Behavior Interaction for Question Recommendation

An Overview of End-to-End Automatic Speech Recognition

Collaborative Community Knowledge Building with Personalized Question Recommendations

Contact Info

Product

Resources

About