Towards Controllable and Personalized Review Generation

Li, Pan; Tuzhilin, Alexander

doi:10.18653/v1/d19-1319

Cited by 22 publications

(21 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the most popular models is seqGAN [37], which leverages a discriminator and a generator to play a minimax game to generate text. Extensions were developed, such as DP-GAN [36],RevGAN [20], RankGAN [21] and LeakGAN [12]. However, these algorithms do not offer means to control the trade-off between diversity and accuracy.…”

Section: Related Workmentioning

confidence: 99%

Controllable and Diverse Text Generation in E-commerce

Shao

Wang

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

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 Apex, that uses an algorithm borrowed from automatic control (namely, a variant of the 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 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 1 show that the proposed method outperforms existing generative models in terms of diversity and relevance. Moreover, it achieves about 97% accuracy in the control of the order of keywords.Apex is currently deployed to generate production descriptions and item recommendation reasons in Taobao 2 , 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 * Part of work was completed at Alibaba Group.

show abstract

Section: Related Workmentioning

confidence: 99%

Controllable and Diverse Text Generation in E-commerce

Shao

Wang

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

show abstract

“…While review generation is essentially a subtask of D2T, it is relatively understudied than other D2T tasks. Previous models include an encoder-decoder model with attention (Dong et al, 2017), improved by including an objective function for rating accuracy (Sharma et al, 2018;Li and Tuzhilin, 2019), by introducing a hierarchical decoder (Zang and Wan, 2017), by decomposing the decoding stage as coarse-to-fine manner , and by using additional inputs such as user-given summary (Ni and McAuley, 2018) or product description (Li and Tuzhilin, 2019). In this paper, we make performance improvements by proposing a concept of leveraging references, and extensions proposed in the aforementioned literature are orthogonal and thus applicable to improve our models further.…”

Section: Related Workmentioning

confidence: 99%

Retrieval-Augmented Controllable Review Generation

Kim

Choi

Amplayo

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

In this paper, we study review generation given a set of attribute identifiers which are user ID, product ID and rating. This is a difficult subtask of natural language generation since models are limited to the given identifiers, without any specific descriptive information regarding the inputs, when generating the text. The capacity of these models is thus confined and dependent to how well the models can capture vector representations of attributes. We thus propose to additionally leverage references, which are selected from a large pool of texts labeled with one of the attributes, as textual information that enriches inductive biases of given attributes. With these references, we can now pose the problem as an instance of text-to-text generation, which makes the task easier since texts that are syntactically, semantically similar to the output text are provided as inputs. Using this framework, we address issues such as selecting references from a large candidate set without textual context and improving the model complexity for generation. Our experiments show that our models improve over previous approaches on both automatic and human evaluation metrics.

show abstract

“…Rational Response Generation: Existing rational response generation models usually rely on knowledge bases, such as open-domain response generation (Han et al 2015;Young et al 2018;Ghazvininejad et al 2018;Liu et al 2018;Tuan, Chen, and Lee 2019;Moon et al 2019), task-oriented response generation (Madotto, Wu, and Fung 2018;Wu, Socher, and Xiong 2019) and question answering (Sun et al 2018;Banerjee et al 2019). Zhou et al (2018b) (Hu et al 2017;Li and Tuzhilin 2019), language models (Ghosh et al 2017) and Seq2Seq models (Xing et al 2017;Xu et al 2019). Keskar et al (2019) trained a Transformer-based conditional language model on a large collection of corpora with control codes that govern style, content, and task-specific behavior.…”

Section: Related Workmentioning

confidence: 99%

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

Zhong¹,

Wang²,

Li³

et al. 2020

Preprint

View full text Add to dashboard Cite

Rationality and emotion are two fundamental elements of humans. Endowing agents with rationality and emotion has been one of the major milestones in AI. However, in the field of conversational AI, most existing models only specialize in one aspect and neglect the other, which often leads to dull or unrelated responses. In this paper, we hypothesize that combining rationality and emotion into conversational agents can improve response quality. To test the hypothesis, we focus on one fundamental aspect of rationality, i.e., commonsense, and propose CARE, a novel model for commonsense-aware emotional response generation. Specifically, we first propose a framework to learn and construct commonsense-aware emotional latent concepts of the response given an input message and a desired emotion. We then propose three methods to collaboratively incorporate the latent concepts into response generation. Experimental results on two large-scale datasets support our hypothesis and show that our model can produce more accurate and commonsense-aware emotional responses and achieve better human ratings than state-of-the-art models that only specialize in one aspect.

show abstract

Towards Controllable and Personalized Review Generation

Cited by 22 publications

References 32 publications

Controllable and Diverse Text Generation in E-commerce

Controllable and Diverse Text Generation in E-commerce

Retrieval-Augmented Controllable Review Generation

CARE: Commonsense-Aware Emotional Response Generation with Latent Concepts

Contact Info

Product

Resources

About