Towards Controllable Explanation Generation for Recommender Systems via Neural Template

Li, Lei; Chen, Li; Zhang, Yongfeng

doi:10.1145/3366424.3383540

Cited by 12 publications

(8 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, show the explanations by assembling the model predicted attributes and the pre-defined templates. [Li, 2020b;Li, 2021a] present the explanations which are completely generated from the models.…”

Section: Evaluation With Case Studiesmentioning

confidence: 99%

“…In [Li, 2021b], the annotators are asked to upvote or down-vote the explanations generated from the designed model and the baseline, respectively. In [Xian, 2021;Li, 2020b], the annotators have to evaluate whether the proposed model can help users make better purchase decision. In [Chen, 2021b], the authors ask the annotators to label whether the explanations produced from the designed model are fluent and useful.…”

Section: Evaluation With Crowdsourcingmentioning

confidence: 99%

“…The third category are "pair-model" questions, where the problems focus on the comparison between a pair of explainable models. In [Li, 2020b], the annotators need to answer which explanations produced from the designed model and baseline are more closer to the ground truth. In [Tao et al, 2019], the annotation questions are: between A and B, whose explanations do you think can better help you understand the recommendations?…”

Section: Evaluation With Crowdsourcingmentioning

confidence: 99%

See 2 more Smart Citations

Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation

Chen¹,

Zhang²,

Wen³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Explainable recommendation has shown its great advantages for improving recommendation persuasiveness, user satisfaction, system transparency and among others. A fundamental problem of explainable recommendation is how to evaluate the explanations. In the past few years, various evaluation strategies have been proposed. However, they are scattered in different papers, and there lacks a systematic and detailed comparison between them. To bridge this gap, in this paper, we comprehensively review the previous work, and provide different taxonomies according to the evaluation perspectives and evaluation methods. Beyond summarization, we also analyze the (dis)advantages of existing evaluation methods, and provide a series of guidelines on how to select them. The contents of this survey are concluded from more than 100 papers from top-tier conferences like IJCAI, AAAI, TheWebConf, Recsys, UMAP and IUI, and the complete comparisons are presented at https://shimo.im/sheets/VKrpYTcwVH6KXgdy/MO DOC/. With this survey, we finally aim to provide a clear and comprehensive review on the evaluation of explainable recommendation.

show abstract

Section: Evaluation With Case Studiesmentioning

confidence: 99%

Section: Evaluation With Crowdsourcingmentioning

confidence: 99%

Section: Evaluation With Crowdsourcingmentioning

confidence: 99%

See 1 more Smart Citation

Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation

Chen¹,

Zhang²,

Wen³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This shows the effectiveness of our model in generating high-quality sentences. Notice that Li et al (2020b) conducted a user survey and reported that NETE's explanations were perceived useful by most participants. It suggests that our model's explanations with better quality could also be very useful to real users.…”

Section: Quantitative Analysis On Explanationsmentioning

confidence: 99%

Personalized Transformer for Explainable Recommendation

Li¹,

Zhang²,

Chen³

2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Personalization of natural language generation plays a vital role in a large spectrum of tasks, such as explainable recommendation, review summarization and dialog systems. In these tasks, user and item IDs are important identifiers for personalization. Transformer, which is demonstrated with strong language modeling capability, however, is not personalized and fails to make use of the user and item IDs since the ID tokens are not even in the same semantic space as the words. To address this problem, we present a PErsonalized Transformer for Explainable Recommendation (PE-TER 1 ), on which we design a simple and effective learning objective that utilizes the IDs to predict the words in the target explanation, so as to endow the IDs with linguistic meanings and to achieve personalized Transformer. Besides generating explanations, PETER can also make recommendations, which makes it a unified model for the whole recommendationexplanation pipeline. Extensive experiments show that our small unpretrained model outperforms fine-tuned BERT on the generation task, in terms of both effectiveness and efficiency, which highlights the importance and the nice utility of our design.

show abstract

“…Besides automatic evaluation, we also conduct a small-scale user survey [24], where explanations produced by our method are perceived useful by participants to explaining the recommendations. Table 4: Example explanations generated by our NETE model on the TA-HK dataset.…”

Section: Quantitative Analysis On Explanationsmentioning

confidence: 99%

Generate Neural Template Explanations for Recommendation

Zhang

Chen

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

Self Cite

107

View full text Add to dashboard Cite

Personalized recommender systems are important to assist user decision-making in the era of information overload. Meanwhile, explanations of the recommendations further help users to better understand the recommended items so as to make informed choices, which gives rise to the importance of explainable recommendation research. Textual sentence-based explanation has been an important form of explanations for recommender systems due to its advantage in communicating rich information to users. However, current approaches to generating sentence explanations are either limited to predefined sentence templates, which restricts the sentence expressiveness, or opt for free-style sentence generation, which makes it difficult for sentence quality control. In an attempt to benefit both sentence expressiveness and quality, we propose a Neural Template (NETE) explanation generation framework, which brings the best of both worlds by learning sentence templates from data and generating template-controlled sentences that comment about specific features. Experimental results on real-world datasets show that NETE consistently outperforms state-of-the-art explanation generation approaches in terms of sentence quality and expressiveness. Further analysis on case study also shows the advantages of NETE on generating diverse and controllable explanations. CCS CONCEPTS • Information systems → Recommender systems; • Computing methodologies → Natural language generation.

show abstract

Towards Controllable Explanation Generation for Recommender Systems via Neural Template

Cited by 12 publications

References 8 publications

Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation

Measuring "Why" in Recommender Systems: a Comprehensive Survey on the Evaluation of Explainable Recommendation

Personalized Transformer for Explainable Recommendation

Generate Neural Template Explanations for Recommendation

Contact Info

Product

Resources

About