Unsupervised Opinion Summarization with Noising and Denoising
- URL: http://arxiv.org/abs/2004.10150v1
- Date: Tue, 21 Apr 2020 16:54:57 GMT
- Title: Unsupervised Opinion Summarization with Noising and Denoising
- Authors: Reinald Kim Amplayo and Mirella Lapata
- Abstract summary: 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.
- Score: 85.49169453434554
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: The supervised training of high-capacity models on large datasets containing
hundreds of thousands of document-summary pairs is critical to the recent
success of deep learning techniques for abstractive summarization.
Unfortunately, in most domains (other than news) such training data is not
available and cannot be easily sourced. In this paper we enable the use of
supervised learning for the setting where there are only documents available
(e.g.,~product or business reviews) without ground truth summaries. 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 which we
treat as pseudo-review input. We introduce several linguistically motivated
noise generation functions and a summarization model which learns to denoise
the input and generate the original review. At test time, the model accepts
genuine reviews and generates a summary containing salient opinions, treating
those that do not reach consensus as noise. Extensive automatic and human
evaluation shows that our model brings substantial improvements over both
abstractive and extractive baselines.
Related papers
- Assessment of Transformer-Based Encoder-Decoder Model for Human-Like Summarization [0.05852077003870416]
This work leverages transformer-based BART model for human-like summarization.
On training and fine-tuning the encoder-decoder model, it is tested with diverse sample articles.
The finetuned model performance is compared with the baseline pretrained model.
Empirical results on BBC News articles highlight that the gold standard summaries written by humans are more factually consistent by 17%.
arXiv Detail & Related papers (2024-10-22T09:25:04Z) - Learning with Rejection for Abstractive Text Summarization [42.15551472507393]
We propose a training objective for abstractive summarization based on rejection learning.
We show that our method considerably improves the factuality of generated summaries in automatic and human evaluations.
arXiv Detail & Related papers (2023-02-16T19:07:08Z) - Efficient Few-Shot Fine-Tuning for Opinion Summarization [83.76460801568092]
Abstractive summarization models are typically pre-trained on large amounts of generic texts, then fine-tuned on tens or hundreds of thousands of annotated samples.
We show that a few-shot method based on adapters can easily store in-domain knowledge.
We show that this self-supervised adapter pre-training improves summary quality over standard fine-tuning by 2.0 and 1.3 ROUGE-L points on the Amazon and Yelp datasets.
arXiv Detail & Related papers (2022-05-04T16:38:37Z) - Learning to Revise References for Faithful Summarization [10.795263196202159]
We propose a new approach to improve reference quality while retaining all data.
We construct synthetic unsupported alternatives to supported sentences and use contrastive learning to discourage/encourage (un)faithful revisions.
We extract a small corpus from a noisy source--the Electronic Health Record (EHR)--for the task of summarizing a hospital admission from multiple notes.
arXiv Detail & Related papers (2022-04-13T18:54:19Z) - 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) - Aspect-Controllable Opinion Summarization [58.5308638148329]
We propose an approach that allows the generation of customized summaries based on aspect queries.
Using a review corpus, we create a synthetic training dataset of (review, summary) pairs enriched with aspect controllers.
We fine-tune a pretrained model using our synthetic dataset and generate aspect-specific summaries by modifying the aspect controllers.
arXiv Detail & Related papers (2021-09-07T16:09:17Z) - Unsupervised Opinion Summarization with Content Planning [58.5308638148329]
We show that explicitly incorporating content planning in a summarization model yields output of higher quality.
We also create synthetic datasets which are more natural, resembling real world document-summary pairs.
Our approach outperforms competitive models in generating informative, coherent, and fluent summaries.
arXiv Detail & Related papers (2020-12-14T18:41:58Z) - On Faithfulness and Factuality in Abstractive Summarization [17.261247316769484]
We analyzed limitations of neural text generation models for abstractive document summarization.
We found that these models are highly prone to hallucinate content that is unfaithful to the input document.
We show that textual entailment measures better correlate with faithfulness than standard metrics.
arXiv Detail & Related papers (2020-05-02T00:09:16Z) - Few-Shot Learning for Opinion Summarization [117.70510762845338]
Opinion summarization is the automatic creation of text reflecting subjective information expressed in multiple documents.
In this work, we show that even a handful of summaries is sufficient to bootstrap generation of the summary text.
Our approach substantially outperforms previous extractive and abstractive methods in automatic and human evaluation.
arXiv Detail & Related papers (2020-04-30T15:37:38Z)
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.