Convex Aggregation for Opinion Summarization

• URL: http://arxiv.org/abs/2104.01371v1
• Date: Sat, 3 Apr 2021 10:52:14 GMT
• Title: Convex Aggregation for Opinion Summarization
• Authors: Hayate Iso, Xiaolan Wang, Yoshihiko Suhara, Stefanos Angelidis, Wang-Chiew Tan
• Abstract summary: An encoder-decoder model is trained to reconstruct single reviews and learns a latent review encoding space. At summarization time, the unweighted average of latent review vectors is decoded into a summary. We propose Coop, a convex vector aggregation framework for opinion summarization, that searches for better combinations of input reviews.
• Score: 18.753472191533515
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent approaches for unsupervised opinion summarization have predominantly used the review reconstruction training paradigm. An encoder-decoder model is trained to reconstruct single reviews and learns a latent review encoding space. At summarization time, the unweighted average of latent review vectors is decoded into a summary. In this paper, we challenge the convention of simply averaging the latent vector set, and claim that this simplistic approach fails to consider variations in the quality of input reviews or the idiosyncrasies of the decoder. We propose Coop, a convex vector aggregation framework for opinion summarization, that searches for better combinations of input reviews. Coop requires no further supervision and uses a simple word overlap objective to help the model generate summaries that are more consistent with input reviews. Experimental results show that extending opinion summarizers with Coop results in state-of-the-art performance, with ROUGE-1 improvements of 3.7% and 2.9% on the Yelp and Amazon benchmark datasets, respectively.

Related papers

• Self-Consistent Decoding for More Factual Open Responses [28.184313177333642]
  "Sample & Select" improves factuality by a 30% relative margin against decoders of DoLA, P-CRR, and S-CRR. We collect human verifications of the generated summaries, confirming the factual superiority of our method.
  arXiv  Detail & Related papers  (2024-03-01T17:31:09Z)
• Large Language Models are not Fair Evaluators [60.27164804083752]
  We find that the quality ranking of candidate responses can be easily hacked by altering their order of appearance in the context. This manipulation allows us to skew the evaluation result, making one model appear considerably superior to the other. We propose a framework with three simple yet effective strategies to mitigate this issue.
  arXiv  Detail & Related papers  (2023-05-29T07:41:03Z)
• Gradient-Boosted Decision Tree for Listwise Context Model in Multimodal Review Helpfulness Prediction [40.09991896766369]
  Multimodal Review Helpfulness Prediction aims to rank product reviews based on predicted helpfulness scores. We propose a listwise attention network that clearly captures the MRHP ranking context. We also propose gradient-boosted decision tree as the score predictor to efficaciously partition product reviews' representations.
  arXiv  Detail & Related papers  (2023-05-22T03:31:00Z)
• 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)
• Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarization [20.87460375478907]
  Text summarization aims to generate a short summary for an input text. In this work, we propose a Non-Autoregressive Unsupervised Summarization approach. Experiments show that NAUS achieves state-of-the-art performance for unsupervised summarization.
  arXiv  Detail & Related papers  (2022-05-28T21:09:23Z)
• Learning Opinion Summarizers by Selecting Informative Reviews [81.47506952645564]
  We collect a large dataset of summaries paired with user reviews for over 31,000 products, enabling supervised training. The content of many reviews is not reflected in the human-written summaries, and, thus, the summarizer trained on random review subsets hallucinates. We formulate the task as jointly learning to select informative subsets of reviews and summarizing the opinions expressed in these subsets.
  arXiv  Detail & Related papers  (2021-09-09T15:01:43Z)
• Hierarchical Bi-Directional Self-Attention Networks for Paper Review Rating Recommendation [81.55533657694016]
  We propose a Hierarchical bi-directional self-attention Network framework (HabNet) for paper review rating prediction and recommendation. Specifically, we leverage the hierarchical structure of the paper reviews with three levels of encoders: sentence encoder (level one), intra-review encoder (level two) and inter-review encoder (level three) We are able to identify useful predictors to make the final acceptance decision, as well as to help discover the inconsistency between numerical review ratings and text sentiment conveyed by reviewers.
  arXiv  Detail & Related papers  (2020-11-02T08:07:50Z)
• A Unified Dual-view Model for Review Summarization and Sentiment Classification with Inconsistency Loss [51.448615489097236]
  Acquiring accurate summarization and sentiment from user reviews is an essential component of modern e-commerce platforms. We propose a novel dual-view model that jointly improves the performance of these two tasks. Experiment results on four real-world datasets from different domains demonstrate the effectiveness of our model.
  arXiv  Detail & Related papers  (2020-06-02T13:34:11Z)
• OpinionDigest: A Simple Framework for Opinion Summarization [22.596995566588422]
  The framework uses an Aspect-based Sentiment Analysis model to extract opinion phrases from reviews, and trains a Transformer model to reconstruct the original reviews from these extractions. The selected opinions are used as input to the trained Transformer model, which verbalizes them into an opinion summary. OpinionDigest can also generate customized summaries, tailored to specific user needs, by filtering the selected opinions according to their aspect and/or sentiment.
  arXiv  Detail & Related papers  (2020-05-05T01:22:29Z)
• Unsupervised Opinion Summarization with Noising and Denoising [85.49169453434554]
  We create a synthetic dataset from a corpus of user reviews by sampling a review, pretending it is a summary, and generating noisy versions thereof. At test time, the model accepts genuine reviews and generates a summary containing salient opinions, treating those that do not reach consensus as noise.
  arXiv  Detail & Related papers  (2020-04-21T16:54:57Z)

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.