Improving the similarity measure of determinantal point processes for extractive multi-document summarization
The most important obstacles facing multi-document summarization include excessive
redundancy in source descriptions and the looming shortage of training data. These …
redundancy in source descriptions and the looming shortage of training data. These …
[PDF][PDF] Toward extractive summarization of online forum discussions via hierarchical attention networks
Forum threads are lengthy and rich in content. Concise thread summaries will benefit both
newcomers seeking information and those who participate in the discussion. Few studies …
newcomers seeking information and those who participate in the discussion. Few studies …
Weakly-supervised opinion summarization by leveraging external information
C Zhao, S Chaturvedi - Proceedings of the AAAI Conference on …, 2020 - ojs.aaai.org
Opinion summarization from online product reviews is a challenging task, which involves
identifying opinions related to various aspects of the product being reviewed. While previous …
identifying opinions related to various aspects of the product being reviewed. While previous …
Neural abstractive unsupervised summarization of online news discussions
Summarization has usually relied on gold standard summaries to train extractive or
abstractive models. Social media brings a hurdle to summarization techniques since it …
abstractive models. Social media brings a hurdle to summarization techniques since it …
Updated headline generation: Creating updated summaries for evolving news stories
S Panthaplackel, A Benton… - Proceedings of the 60th …, 2022 - aclanthology.org
We propose the task of updated headline generation, in which a system generates a
headline for an updated article, considering both the previous article and headline. The …
headline for an updated article, considering both the previous article and headline. The …
Classifying Conspiratorial Narratives at Scale: False Alarms and Erroneous Connections
Online discussions frequently involve conspiracy theories, which can contribute to the
proliferation of belief in them. However, not all discussions surrounding conspiracy theories …
proliferation of belief in them. However, not all discussions surrounding conspiracy theories …
[HTML][HTML] Generating aspect-based extractive opinion summary: Drawing inferences from social media texts
This paper presents an integrated framework to generate extractive aspect-based opinion
summary from a large volume of free-form text reviews. The framework has three major …
summary from a large volume of free-form text reviews. The framework has three major …
Automatic debate text summarization in online debate forum
AD Chowanda, AR Sanyoto, D Suhartono… - Procedia computer …, 2017 - Elsevier
The goal of this research is to create a system that can generate summaries from online
debate forum by using abstractive technique. This research is based on the point-based …
debate forum by using abstractive technique. This research is based on the point-based …
Visualizing reviews summaries as a tool for restaurants recommendation
Online customers opinions about products and services, in the form of reviews, are a major
part of today's web culture. However, customers, when looking for a product or service, do …
part of today's web culture. However, customers, when looking for a product or service, do …
A study on deep learning frameworks for opinion summarization
S Ramakrishnan, LDD Babu - … of Emerging Trends and Technologies on …, 2022 - Springer
Opinion summarization has gained interest among researchers due to the usefulness and
challenges in extracting insights from the unprecedented amount of opinionated data …
challenges in extracting insights from the unprecedented amount of opinionated data …