Comparing Apples to Apples: Generating Aspect-Aware Comparative Sentences from User Reviews

• URL: http://arxiv.org/abs/2307.03691v2
• Date: Sun, 23 Jul 2023 17:05:06 GMT
• Title: Comparing Apples to Apples: Generating Aspect-Aware Comparative Sentences from User Reviews
• Authors: Jessica Echterhoff, An Yan, Julian McAuley
• Abstract summary: We show that our pipeline generates fluent and diverse comparative sentences. We run experiments on the relevance and fidelity of our generated sentences in a human evaluation study.
• Score: 6.428416845132992
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is time-consuming to find the best product among many similar alternatives. Comparative sentences can help to contrast one item from others in a way that highlights important features of an item that stand out. Given reviews of one or multiple items and relevant item features, we generate comparative review sentences to aid users to find the best fit. Specifically, our model consists of three successive components in a transformer: (i) an item encoding module to encode an item for comparison, (ii) a comparison generation module that generates comparative sentences in an autoregressive manner, (iii) a novel decoding method for user personalization. We show that our pipeline generates fluent and diverse comparative sentences. We run experiments on the relevance and fidelity of our generated sentences in a human evaluation study and find that our algorithm creates comparative review sentences that are relevant and truthful.

Related papers

• Active Preference Learning for Ordering Items In- and Out-of-sample [7.0774164818430565]
  actively sampling item pairs can reduce the number of annotations necessary for learning an accurate ordering. Many algorithms ignore shared structure between items. It is also common to disregard how noise in comparisons varies between item pairs.
  arXiv  Detail & Related papers  (2024-05-05T21:44:03Z)
• Unveiling Comparative Sentiments in Vietnamese Product Reviews: A Sequential Classification Framework [2.235716381266672]
  We propose an approach that consists of solving three sequential sub-tasks: identifying comparative sentence, extracting comparative elements, and classifying comparison types. Our method is ranked fifth at the Vietnamese Language and Speech Processing (VLSP) 2023 challenge on Comparative Opinion Mining (ComOM) from Vietnamese Product Reviews.
  arXiv  Detail & Related papers  (2024-01-02T08:58:01Z)
• Predicting Text Preference Via Structured Comparative Reasoning [110.49560164568791]
  We introduce SC, a prompting approach that predicts text preferences by generating structured intermediate comparisons. We select consistent comparisons with a pairwise consistency comparator that ensures each aspect's comparisons clearly distinguish differences between texts. Our comprehensive evaluations across various NLP tasks, including summarization, retrieval, and automatic rating, demonstrate that SC equips LLMs to achieve state-of-the-art performance in text preference prediction.
  arXiv  Detail & Related papers  (2023-11-14T18:51:38Z)
• Attributable and Scalable Opinion Summarization [79.87892048285819]
  We generate abstractive summaries by decoding frequent encodings, and extractive summaries by selecting the sentences assigned to the same frequent encodings. Our method is attributable, because the model identifies sentences used to generate the summary as part of the summarization process. It scales easily to many hundreds of input reviews, because aggregation is performed in the latent space rather than over long sequences of tokens.
  arXiv  Detail & Related papers  (2023-05-19T11:30:37Z)
• Beyond Contrastive Learning: A Variational Generative Model for Multilingual Retrieval [109.62363167257664]
  We propose a generative model for learning multilingual text embeddings. Our model operates on parallel data in $N$ languages. We evaluate this method on a suite of tasks including semantic similarity, bitext mining, and cross-lingual question retrieval.
  arXiv  Detail & Related papers  (2022-12-21T02:41:40Z)
• Visual Comparison of Language Model Adaptation [55.92129223662381]
  adapters are lightweight alternatives for model adaptation. In this paper, we discuss several design and alternatives for interactive, comparative visual explanation methods. We show that, for instance, an adapter trained on the language debiasing task according to context-0 embeddings introduces a new type of bias.
  arXiv  Detail & Related papers  (2022-08-17T09:25:28Z)
• Comparative Snippet Generation [18.920306511866553]
  We generate a single-sentence, comparative response from a given positive and a negative opinion. We contribute the first dataset for this task, and a performance analysis of a pre-trained BERT model to generate such snippets.
  arXiv  Detail & Related papers  (2022-06-11T09:02:27Z)
• Training Language Models with Natural Language Feedback [51.36137482891037]
  We learn from language feedback on model outputs using a three-step learning algorithm. In synthetic experiments, we first evaluate whether language models accurately incorporate feedback to produce refinements. Using only 100 samples of human-written feedback, our learning algorithm finetunes a GPT-3 model to roughly human-level summarization.
  arXiv  Detail & Related papers  (2022-04-29T15:06:58Z)
• Comparative Explanations of Recommendations [33.89230323979306]
  We develop an extract-and-refine architecture to explain the relative comparisons among a set of ranked items from a recommender system. We design a new explanation quality metric based on BLEU to guide the end-to-end training of the extraction and refinement components.
  arXiv  Detail & Related papers  (2021-11-01T02:55:56Z)
• Adaptive Sampling for Heterogeneous Rank Aggregation from Noisy Pairwise Comparisons [85.5955376526419]
  In rank aggregation problems, users exhibit various accuracy levels when comparing pairs of items. We propose an elimination-based active sampling strategy, which estimates the ranking of items via noisy pairwise comparisons. We prove that our algorithm can return the true ranking of items with high probability.
  arXiv  Detail & Related papers  (2021-10-08T13:51:55Z)
• Sentiment Analysis Using Averaged Weighted Word Vector Features [1.2691047660244332]
  We develop two methods that combine different types of word vectors to learn and estimate polarity of reviews. We apply the methods to several datasets from different domains that are used as standard benchmarks for sentiment analysis.
  arXiv  Detail & Related papers  (2020-02-13T16:30:34Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.