Quality Matters: Assessing cQA Pair Quality via Transductive Multi-View Learning

Community-based question answering (cQA) sites have become important knowledge sharing platforms, as massive cQA pairs are archived, but the uneven quality of cQA pairs leaves information seekers unsatisfied. Various efforts have been dedicated to predicting the quality of cQA contents. Most of them concatenate different features into single vectors and then feed them into regression models. In fact, the quality of cQA pairs is influenced by different views, and the agreement among them is essential for quality assessment. Besides, the lacking of labeled data significantly hinders the quality prediction performance. Toward this end, we present a transductive multi-view learning model. It is designed to find a latent common space by unifying and preserving information from various views, including question, answer, QA relevance, asker, and answerer. Additionally, rich information in the unlabeled test cQA pairs are utilized via transductive learning to enhance the representation ability of the common space. Extensive experiments on real-world datasets have well-validated the proposed model.

Download Full-text

The oncologist as genetic consultant: Two-year results in a large community-based practice

Journal of Clinical Oncology ◽

10.1200/jco.2009.27.15_suppl.e22140 ◽

2009 ◽

Vol 27 (15_suppl) ◽

pp. e22140-e22140

Author(s):

L. J. Geier ◽

M. Sheehan ◽

M. Elia ◽

S. Ethirajan ◽

E. Kent

Keyword(s):

Cancer Survivors ◽

Cancer Risk Assessment ◽

Cancer Center ◽

Deleterious Mutations ◽

Community Based ◽

Gene Testing ◽

Community Oncology ◽

The Common ◽

One Year

e22140 Background: Oncologists are in a unique position to provide effective genetic cancer risk assessment (GCRA). However, in most communities they defer this to genetic counselors (GC). At KC Cancer Center, a 35-MD community oncology group, the difficulty obtaining timely and effective GCRA became a quality of care issue. Methods: In December 2006 a new program was launched with 4 designated oncologists providing GCRA at 4 separate cancer centers. Each oncologist was responsible for gaining expertise in the common hereditary syndromes and appropriate interpretation of gene testing results prior to starting GCRA. Two-year results were analyzed. For those pts found to have deleterious mutations, charts were reviewed to confirm the gene affected, and the length of time between cancer dx and GCRA. Pts more than one year out from dx were designated as cancer survivors. Results: After 2 years, 490 pts had gone through gene testing after GCRA, and 85 were found to carry deleterious mutations. These data were compared to the previous three years when pts had been referred to GC ( Table ). Both the number of pts tested and the number with mutations in yrs 2007–8 were approximately 400% of the numbers for yrs 2005–06. Of the 85 pts with mutations, 51 (60%) were cancer survivors. Their median time from diagnosis was 5.5 yrs (range 1–25). 75/85 (88%) mutations were in a BRCA gene. Conclusions: This oncologist-centered model proved to be very effective in identifying mutation carriers, particularly among cancer survivors in whom the hereditary syndrome had been previously overlooked. Acceptance of this approach by pts, physicians, and payers has been extremely high. This model should be considered by oncology practices wanting to add GCRA to their service lines. [Table: see text] [Table: see text]

Download Full-text

Predicting the quality of user-generated answers using co-training in community-based question answering portals

Pattern Recognition Letters ◽

10.1016/j.patrec.2015.02.015 ◽

2015 ◽

Vol 58 ◽

pp. 29-34 ◽

Cited By ~ 21

Author(s):

Bingquan Liu ◽

Jian Feng ◽

Ming Liu ◽

Haifeng Hu ◽

Xiaolong Wang

Keyword(s):

Question Answering ◽

Community Based

Download Full-text

HINRL4Rec: A Novel Integrated Heterogeneous Network Embedding with Reinforcement Learning for Recommendation

10.21203/rs.3.rs-610194/v1 ◽

2021 ◽

Author(s):

Tham Vo

Keyword(s):

Reinforcement Learning ◽

Recommendation System ◽

Direct Interaction ◽

Heterogeneous Information ◽

Heterogeneous Information Networks ◽

Proposed Model ◽

Meta Path ◽

Rich Information ◽

The Rich ◽

Real World Datasets

Abstract Recent KG-oriented recommendation techniques mainly focus on the direct interaction between entities in the given KGs as the rich information sources for leveraging the quality of recommendation outputs. However, they are still hindered by the heterogeneity, type-varied entities and their relationships in knowledge graphs (KG) as the heterogeneous information networks (HIN). This limitation seems challenging to build up an effective approach for the KG-based recommendation system in both semantic path-based exploitation and heterogeneous information extraction. To meet these challenges, we proposed a novel integrated HIN embedding with reinforcement learning (RL)-based feature engineering for recommendation, called as: HINRL4Rec. First of all, we apply the combined textual meta-path-based embedding approach for learning multiple-rich-schematic representations of user/item and their associated entities. Then, these extracted multi-typed embeddings of user and item entities are fused into the unified embedding spaces during the KG embedding process. Finally, the unified representations of users and items are then used to facilitate the RL-based policy-driven searching process in the next steps for performing the recommendation task. Extensive experiments in real-world datasets demonstrate the effectiveness of our proposed model in comparing with recent state-of-the-art recommendation baselines.

Download Full-text

An Intelligent Question Answering Platform for Graduate Enrollment

10.5121/csit.2021.111602 ◽

2021 ◽

Author(s):

Mengyuan Zhang ◽

Yuting Wang ◽

Jianxia Chen ◽

Yu Cheng

Keyword(s):

Question Answering ◽

Short Term Memory ◽

Retrieval Model ◽

Retrieval Performance ◽

Short Term ◽

Data Sparseness ◽

Proposed Model ◽

Graduate Enrollment ◽

Long Short Term Memory

To enhance the competitiveness of colleges and universities in the graduate enrollment and reduce the pressure on candidates for examination and consultation, it is necessary and practically significant to develop an intelligent Q&A platform, which can understand and analyze users' semantics and accurately return the information they need. However, there are problems such as the low volume and low quality of the corpus in the graduate enrollment, this paper develops a question answering platform based on a novel retrieval model including density-based logistic regression and the combination of convolutional neural networks and bidirectional long short-term memory. The experimental results show that the proposed model can effectively alleviate the problem of data sparseness and greatly improve the accuracy of the retrieval performance for the graduate enrollment.

Download Full-text

Norm-guided Adaptive Visual Embedding for Zero-Shot Sketch-Based Image Retrieval

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2021/153 ◽

2021 ◽

Author(s):

Wenjie Wang ◽

Yufeng Shi ◽

Shiming Chen ◽

Qinmu Peng ◽

Feng Zheng ◽

...

Keyword(s):

Image Retrieval ◽

State Of The Art ◽

Visual Similarity ◽

Language Models ◽

Visual Appearance ◽

Common Space ◽

Great Progress ◽

Real World Applications ◽

The Common

Zero-shot sketch-based image retrieval (ZS-SBIR), which aims to retrieve photos with sketches under the zero-shot scenario, has shown extraordinary talents in real-world applications. Most existing methods leverage language models to generate class-prototypes and use them to arrange the locations of all categories in the common space for photos and sketches. Although great progress has been made, few of them consider whether such pre-defined prototypes are necessary for ZS-SBIR, where locations of unseen class samples in the embedding space are actually determined by visual appearance and a visual embedding actually performs better. To this end, we propose a novel Norm-guided Adaptive Visual Embedding (NAVE) model, for adaptively building the common space based on visual similarity instead of language-based pre-defined prototypes. To further enhance the representation quality of unseen classes for both photo and sketch modality, modality norm discrepancy and noisy label regularizer are jointly employed to measure and repair the modality bias of the learned common embedding. Experiments on two challenging datasets demonstrate the superiority of our NAVE over state-of-the-art competitors.

Download Full-text

Adversarial auto-encoder for rating prediction with ratings and reviews

Web Intelligence ◽

10.3233/web-210449 ◽

2021 ◽

pp. 1-10

Author(s):

Jin Yi ◽

Jiajin Huang ◽

Jin Qin

Keyword(s):

Real World ◽

Empirical Studies ◽

Auxiliary Information ◽

Rating Data ◽

Adversarial Learning ◽

Rich Information ◽

Rating Prediction ◽

Sparsity Problem ◽

Real World Datasets

Recommender systems have been widely used in our life in recent years to facilitate our life. And it is very important and meaningful to improve recommendation performance. Generally, recommendation methods use users’ historical ratings on items to predict ratings on their unrated items to make recommendations. However, with the increase of the number of users and items, the degree of data sparsity increases, and the quality of recommendations decreases sharply. In order to solve the sparsity problem, other auxiliary information is combined to mine users’ preferences for higher recommendation quality. Similar to rating data, review data also contain rich information about users’ preferences on items. This paper proposes a novel recommendation model, which harnesses an adversarial learning among auto-encoders to improve recommendation quality by minimizing the gap of the rating and review relation between a user and an item. The empirical studies on real-world datasets show that the proposed method improves the recommendation performance.

Download Full-text

A Deep Content-Based Model for Persian Rumor Verification

ACM Transactions on Asian and Low-Resource Language Information Processing ◽

10.1145/3487289 ◽

2022 ◽

Vol 21 (1) ◽

pp. 1-29

Author(s):

Zoleikha Jahanbakhsh-Nagadeh ◽

Mohammad-Reza Feizi-Derakhshi ◽

Arash Sharifi

Keyword(s):

Early Stage ◽

Structural Features ◽

Proposed Model ◽

The Social ◽

Rich Information ◽

The Rich ◽

Real World Datasets ◽

Rumor Detection ◽

Content Information

During the development of social media, there has been a transformation in social communication. Despite their positive applications in social interactions and news spread, it also provides an ideal platform for spreading rumors. Rumors can endanger the security of society in normal or critical situations. Therefore, it is important to detect and verify the rumors in the early stage of their spreading. Many research works have focused on social attributes in the social network to solve the problem of rumor detection and verification, while less attention has been paid to content features. The social and structural features of rumors develop over time and are not available in the early stage of rumor. Therefore, this study presented a content-based model to verify the Persian rumors on Twitter and Telegram early. The proposed model demonstrates the important role of content in spreading rumors and generates a better-integrated representation for each source rumor document by fusing its semantic, pragmatic, and syntactic information. First, contextual word embeddings of the source rumor are generated by a hybrid model based on ParsBERT and parallel CapsNets. Then, pragmatic and syntactic features of the rumor are extracted and concatenated with embeddings to capture the rich information for rumor verification. Experimental results on real-world datasets demonstrated that the proposed model significantly outperforms the state-of-the-art models in the early rumor verification task. Also, it can enhance the performance of the classifier from 2% to 11% on Twitter and from 5% to 23% on Telegram. These results validate the model's effectiveness when limited content information is available.

Download Full-text