Opinosis: A Graph Based Approach to Abstractive Summarization of Highly Redundant Opinions
We present a novel graph-based summarization framework (Opinosis) that generates concise abstractive summaries of highly redundant opinions. Evaluation results on summarizing user reviews show that Opinosis summaries have better agreement with human summaries compared to the baseline extractive method. The summaries are readable, reasonably well-formed and are informative enough to convey the major opinions.
- Download Paper
- Download Slides [new link is now fixed]
- See Sample Results
- Software: Opinosis Runnable Jar File
- Software: Opinosis Web API
External Discussion Related to Opinosis
- Cosmina Croitoru
- * DZONE
- * Example visual of Opinosis Graph
- * Blog Post by Micahel Hunger
- * Patrick Durusau's Website
* Please note that the starred external discussions mainly talk about the graph construction for opinosis (Opinosis-Graph) and not the entire summarization framework. Please see Section 3 onwards in the paper on how to use Opinosis-Graph for summarization. The article by Cosmina Croitoru is a good one to look at.
The Big Idea
The Opinosis Summarization framework focuses on generating very short abstractive summaries from large amounts of text. These summaries can resemble micropinions or "micro-reviews" that you see on sites like twitter and four squares. The idea of the algorithm is to use a word graph data structure referred to as the Opinosis-Graph to represent the text to be summarized. Then, the resulting graph is repeatedly explored to find meaningful paths which in turn becomes candidate summary phrases. The Opinosis summarizer is considered a "shallow" abstractive summarizer as it uses the original text itself to generate summaries (this makes it shallow) but it can generate phrases that were previously not seen in the original text because of the way paths are explored (and this makes it abstractive rather than purely extractive). The summarization framework was evaluated on an opinion (user review) dataset. The approach itself is actually very general in that, it can be applied to any corpus containing high amounts of redundancies, for example, Twitter comments or user comments on blog/news articles. Here is an example Opinosis summary for hotels from a live system:
Here is an example Opinosis summary of Twitter comments related to the disappearence of MH 370 sometime around mid April 2014:
Here is another example of an Opinosis summary for a Car (Acura 2007) generated using the OpinRank Edmunds data set. :
While most research projects in data mining and NLP focus on technical complexity, the focus of Opinosis was its practicality, in that it uses very shallow representation of text, relying mostly on redundancy to help generate summaries. This is not too much to ask given that we live in an era of big data, and we have ample user reviews on the Web to work with. Even though the Opinosis paper uses part-of-speech tags in its graph representation, you don't have to use this at all and the algorithm will still work fine as long as you have sufficient volume of reviews and you make a few tweaks in finding sentence breaks.
My Related Opinion Summarization Works
Other Related Works
Katja Fillipova - News Summarization
A very similar work to ours (published at the same time and at the same conference) is the following:
Multi-sentence compression: Finding shortest paths in word graphs
Proceedings of the 23rd International Conference on Computaional Linguistics (COLING 10). Beijing, China, August 23-27, 2010. Katja Filippova
Katja's work was evaluated on a news dataset (google news) for both English and Spanish while Opinosis was evaluated on user reviews from various sources (English only). She studies the informativeness and grammaticality of sentences and in a similar way we evaluate these aspects by studying how close the Opinosis summaries are compared to the human composed summaries in terms of information overlap and readability (using a human assessor).
Peilin Yang and Hui Fang - Contextual Suggestion
Another related work uses the Opinosis Algorithm to extract terms from reviews for the purpose of Contextual Suggestion. This was done as part of the Contextual Suggestion TREC Task. It turns out that Yang and Fang had the highest rank and MRR scores in this track. Their paper can be found here: An Opinion-aware Approach to Contextual Suggestion. The details of the TREC run can be found here: Overview of the TREC 2013 Contextual Suggestion Track.
Opinosis Presentation Slides