TL;DR
This paper introduces a new task called Comparative Snippet Generation, which creates single-sentence comparative responses from contrasting product opinions, supported by a new dataset and analysis of BERT-based models.
Contribution
It presents the first dataset for comparative snippet generation and evaluates a pre-trained BERT model for this task.
Findings
BERT can generate meaningful comparative snippets
The dataset enables future research in opinion comparison
Preliminary results show promising performance
Abstract
We model product reviews to generate comparative responses consisting of positive and negative experiences regarding the product. Specifically, we generate a single-sentence, comparative response from a given positive and a negative opinion. We contribute the first dataset for this task of Comparative Snippet Generation from contrasting opinions regarding a product, and a performance analysis of a pre-trained BERT model to generate such snippets.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsMulti-Head Attention · Attention Is All You Need · Linear Layer · Dense Connections · Weight Decay · Linear Warmup With Linear Decay · Layer Normalization · WordPiece · Refunds@Expedia|||How do I get a full refund from Expedia? · Softmax
