• Corpus ID: 35338382

Towards Summarization of Written Text Conversations

  title={Towards Summarization of Written Text Conversations},
  author={Arpit Sood and Vasudeva Varma and Kushal Dave and Aditya Mogadala and Niraj Kumar and Piyush Arora and Hemant Baid and Nachiket Bhagwat and Sarvesh Ranade and Aman Mahajan and Sumati Prabhakar},
The immense growth of social media and web technologies have enabled users to create, share and exchange information in virtual communities and networks. The ease of usability has attracted considerable amount of users who collaborate on such social platforms. Content generated from such interactions and conversations contains a lot of information that could be of very good commercial and educational value. This necessitates the need to extract information from such conversations. Therefore… 
Automatic Text Document Summarization using Semantic-based Analysis
This work is based on Extractive approaches and is using some statistical features and semantic-based features for sentiment as a feature in text document summarization, which aims to reduce query access time and optimize the document results according to specific users requirements.
Interactive Minutes Generation System Based on Hierarchical Discussion Structure
This research leads to the development of a system that generates minutes by using repeated questions and answers between a user and the system to provide the user with an interactive analysis of meeting records, with a specific purpose or viewpoint.
Pasokh: A standard corpus for the evaluation of Persian text summarizers
Pasokh was constructed as a standard large enough reference corpus for Persian due to the lack of such a standard corpus for Iranian, which made the systems non-comparable.
Discussion Summarization Based on Hierarchical Structure Using Verbal and Non-Verbal Information
The aim of the study is to analyze the semantic relationships among utterances in a meeting at a deep level. To achieve the aim, we propose a novel tree structure, called discussion time-span tree,
Similarity versus relatedness: A novel approach in extractive Persian document summarisation
This article presents a single/multi-document summariser using a novel clustering method for creating summaries using FarsNet, the Persian WordNet, to extract the semantic information of words.
Fear the REAPER: A System for Automatic Multi-Document Summarization with Reinforcement Learning
It is shown that ROUGE results can be improved using a unigram and bigram similarity metric when training a learner to select sentences for summarization, and query focused extensions of this approach show an improvement.


Extracting sentence segments for text summarization: a machine learning approach
An approach to the design of an automatic text summarizer that generates a summary by extracting sentence segments that compares very favorably with other approaches in terms of precision, recall, and classification accuracy.
Summarizing Emails with Conversational Cohesion and Subjectivity
A sentence quotation graph is built that captures the conversation structure among emails and three cohesion measures are adopted: clue words, semantic similarity and cosine similarity as the weight of the edges.
Query-Focused Summarization by Combining Topic Model and Affinity Propagation
This paper proposes a novel approach by combining statistical topic model and affinity propagation, called qLDA, that can simultaneously model documents and the query and can automatically discover key sentences from the document collection without predefining the length of the summary.
Domain adaptation for summarizing conversations
This work uses a labeled corpus of meeting transcripts as the source, and attempts to summarize a different target domain, threaded emails, showing that in the supervised case, given the amount of email data available and the set of features specific to conversations, training directly indomain and ignoring the out-of-domain data is best.
Structural analysis of chat messages for topic detection
An indicative term‐based categorization approach for chat topic detection is proposed and is superior to the traditional documen...
Multi-topic Based Query-Oriented Summarization
Experimental results on two different genres of data show that the proposed approach can effectively extract a multi-topic summary from a document collection and the summarization performance is better than baseline methods.
Using latent semantic analysis to improve access to textual information
Initial tests find this completely automatic method widely applicable and a promising way to improve users' access to many kinds of textual materials, or to objects and services for which textual descriptions are available.
Latent Dirichlet learning for document summarization
A new hierarchical representation of words, sentences and documents in a corpus is presented, and the proposed sentence-based latent Dirichlet allocation (SLDA) outperforms other methods for document summarization in terms of precision, recall and F-measure.
A Relevance-Based Language Modeling approach to DUC 2005
A sentence extraction based summarization system which scores the sentences using Relevance Based Language Modeling, Latent Semantic Indexing and number of special words to generate a summary of required granularity.
The rhetorical parsing, summarization, and generation of natural language texts
This thesis is an inquiry into the nature of the high-level, rhetorical structure of unrestricted natural language texts, computational means to enable its derivation, and two applications (in