We present a neural framework for opinion summarization from online product reviews which is knowledge-lean and only requires light supervision (e.g., in the form of product domain labels and user-provided ratings). Our method combines two weakly supervised components to identify salient opinions and form extractive summaries from multiple reviews: an aspect extractor trained under a multi-task objective, and a sentiment predictor based on multiple instance learning. We introduce an opinion summarization dataset that includes a training set of product reviews from six diverse domains and human-annotated development and test sets with gold standard aspect annotations, salience labels, and opinion summaries. Automatic evaluation shows significant improvements over baselines, and a largescale study indicates that our opinion summaries are preferred by human judges according to multiple criteria. 1

We consider the task of fine-grained sentiment analysis from the perspective of multiple instance learning (MIL). Our neural model is trained on document sentiment labels, and learns to predict the sentiment of text segments, i.e. sentences or elementary discourse units (EDUs), without segment-level supervision. We introduce an attention-based polarity scoring method for identifying positive and negative text snippets and a new dataset which we call SPOT (as shorthand for Segment-level POlariTy annotations) for evaluating MILstyle sentiment models like ours. Experimental results demonstrate superior performance against multiple baselines, whereas a judgement elicitation study shows that EDU-level opinion extraction produces more informative summaries than sentence-based alternatives.

We present OPINIONDIGEST, an abstractive opinion summarization framework, which does not rely on gold-standard summaries for training. 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. At summarization time, we merge extractions from multiple reviews and select the most popular ones. 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. Automatic evaluation on YELP data shows that our framework outperforms competitive baselines. Human studies on two corpora verify that OPINIONDIGEST produces informative summaries and shows promising customization capabilities 1 .

We present the Quantized Transformer (QT), an unsupervised system for extractive opinion summarization. QT is inspired by Vector- Quantized Variational Autoencoders, which we repurpose for popularity-driven summarization. It uses a clustering interpretation of the quantized space and a novel extraction algorithm to discover popular opinions among hundreds of reviews, a significant step towards opinion summarization of practical scope. In addition, QT enables controllable summarization without further training, by utilizing properties of the quantized space to extract aspect-specific summaries. We also make publicly available Space, a large-scale evaluation benchmark for opinion summarizers, comprising general and aspect-specific summaries for 50 hotels. Experiments demonstrate the promise of our approach, which is validated by human studies where judges showed clear preference for our method over competitive baselines.

Recent advances in text autoencoders have significantly improved the quality of the latent space, which enables models to generate grammatical and consistent text from aggregated latent vectors. As a successful application of this property, unsupervised opinion summarization models generate a summary by decoding the aggregated latent vectors of inputs. More specifically, they perform the aggregation via simple average. However, little is known about how the vector aggregation step affects the generation quality. In this study, we revisit the commonly used simple average approach by examining the latent space and generated summaries. We found that text autoencoders tend to generate overly generic summaries from simply averaged latent vectors due to an unexpected L 2 -norm shrinkage in the aggregated latent vectors, which we refer to as summary vector degeneration. To overcome this issue, we develop a framework COOP, which searches input combinations for the latent vector aggregation using input-output word overlap. Experimental results show that COOP successfully alleviates the summary vector degeneration issue and establishes new state-of-theart performance on two opinion summarization benchmarks. Code is available at https: //github.com/megagonlabs/coop. * Work done while at Megagon Labs. This is a great place to eat. The food is always fresh and the staff is very friendly. It's a great place to go if you are in the area. The food is always good and the prices are very reasonable.