Амазон
Related Papers
Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation
AbstractWith the rise of e-commerce, people are accustomed to writing their reviews after receiving the goods. These comments are so important that a bad review can have a direct impact …...
Delete, Retrieve, Generate: a Simple Approach to Sentiment and Style Transfer
AbstractWe consider the task of text attribute transfer: transforming a sentence to alter a specific attribute (e.g., sentiment) while preserving its attribute-independent content (e.g., “screen is just the right size” …...
Domain Adaptation for Sentiment Analysis using Keywords in the Target Domain as the Learning Weight
This paper proposes a new method of instance-based domain adaptation for senti- ment analysis. First, our method defines the likelihood of keywords, through the value of inverse document frequency (IDF), …...
Few-Shot Learning for Opinion Summarization
AbstractOpinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents, such as user reviews of a product. The task is practically important and has attracted …...
SAFER: A Structure-free Approach for Certified Robustness to Adversarial Word Substitutions
AbstractState-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that …...
Unsupervised Opinion Summarization as Copycat-Review Generation
AbstractOpinion summarization is the task of automatically creating summaries that reflect subjective information expressed in multiple documents, such as product reviews. While the majority of previous work has focused on …...
Opinion Summarization by Weak-Supervision from Mix-structured Data
AbstractOpinion summarization of multiple reviews suffers from the lack of reference summaries for training. Most previous approaches construct multiple reviews and their summary based on textual similarities between reviews,resulting in …...
Rethinking Style Transformer with Energy-based Interpretation: Adversarial Unsupervised Style Transfer using a Pretrained Model
AbstractStyle control, content preservation, and fluency determine the quality of text style transfer models. To train on a nonparallel corpus, several existing approaches aim to deceive the style discriminator with …...
Unsupervised Extractive Opinion Summarization Using Sparse Coding
AbstractOpinion summarization is the task of automatically generating summaries that encapsulate information expressed in multiple user reviews. We present Semantic Autoencoder (SemAE) to perform extractive opinion summarization in an unsupervised …...
Mixture-of-Domain-Adapters: Decoupling and Injecting Domain Knowledge to Pre-trained Language Models’ Memories
AbstractPre-trained language models (PLMs) demonstrate excellent abilities to understand texts in the generic domain while struggling in a specific domain. Although continued pre-training on a large domain-specific corpus is effective, …...