Cyclegen: Cyclic consistency based product review generator from attributes

Abstract

In this paper we present an automatic review generator system which can generate personalized reviews based on the user identity, product identity and designated rating the user wishes to allot to the review. We combine this with a sentiment analysis system which performs the complimentary task of assigning ratings to reviews based purely on the textual content of the review. We introduce an additional loss term to ensure cyclic consistency of the sentiment rating of the generated review with the conditioning rating used to generate the review. The introduction of this new loss term constraints the generation space while forcing it to generate reviews adhering better to the requested rating. The use of 'soft' generation and cyclic consistency allows us to train our model in an end to end fashion. We demonstrate the working of our model on product reviews from Amazon dataset.

Retrieval-Augmented Controllable Review Generation

“…Models As baselines, we report performance of Attr2Seq (Dong et al, 2017) and Cyclegen (Sharma et al, 2018) which use embedding vectors to encode given attributes. For our models, we report performance of GEN using retrieved references by Coarse-and Fine-Grained REFLECT trained using SL and RL, denoted by GEN-C-F (SL) and GEN-C-F (RL) respectively 2 .…”

“…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.…”

“…Most of the previous approaches (Dong et al, 2017;Sharma et al, 2018) have framed review generation as A2T (Attribute-to-Text problem), where the given input is a non-linguistic data (i.e., attribute identifiers for user, product, and rating) and the output is the review text. In this problem setup, the key challenge is to learn rich representations of the attributes, which are then used to produce the text using either template-based surface realization methods (Kukich, 1983;McKeown, 1992) or neural-based decoders (Mei et al, 2016;Wiseman et al, 2017), as shown in the red box in Figure 1.…”

AI-Powered Text Generation for Harmonious Human-Machine Interaction: Current State and Future Directions

“…They also introduced an attention mechanism to syndicate comments and align words with input attributes. Sharma et al [51] used the model similar to [10] and added loss terms to generate more compliant comments. Ni et al [41] designed a review generation model that could make use of user and project information as well as auxiliary text input and aspect perception knowledge.…”

Towards trustworthy recommenders: building explainable and unbiased recommendation systems

“…The output of the encoder is decoded by stacked multi-layer RNNs to generate reviews. Cyclegen [200] improves Att2Seq using an additional loss to force Att2Seq to generate reviews that better adhere to the sentiment rating by constraining the generation space.…”