Award Abstract # 1566382
CRII: RI: Towards Abstractive Summarization of Meetings

NSF Org: IIS
Division of Information & Intelligent Systems
Recipient: NORTHEASTERN UNIVERSITY
Initial Amendment Date: March 2, 2016
Latest Amendment Date: March 2, 2016
Award Number: 1566382
Award Instrument: Standard Grant
Program Manager: Tatiana Korelsky
IIS
 Division of Information & Intelligent Systems
CSE
 Directorate for Computer and Information Science and Engineering
Start Date: September 1, 2016
End Date: August 31, 2019 (Estimated)
Total Intended Award Amount: $147,649.00
Total Awarded Amount to Date: $147,649.00
Funds Obligated to Date: FY 2016 = $147,649.00
History of Investigator:
  • Lu Wang (Principal Investigator)
    wangluxy@umich.edu
Recipient Sponsored Research Office: Northeastern University
360 HUNTINGTON AVE
BOSTON
MA  US  02115-5005
(617)373-5600
Sponsor Congressional District: 07
Primary Place of Performance: Northeastern University
360 Huntington Ave
Boston
MA  US  02115-5005
Primary Place of Performance
Congressional District:
07
Unique Entity Identifier (UEI): HLTMVS2JZBS6
Parent UEI:
NSF Program(s): CRII CISE Research Initiation
Primary Program Source: 01001617DB NSF RESEARCH & RELATED ACTIVIT
Program Reference Code(s): 7495, 8228
Program Element Code(s): 026Y00
Award Agency Code: 4900
Fund Agency Code: 4900
Assistance Listing Number(s): 47.070

ABSTRACT

Meeting is a common way to collaborate, share information and exchange opinions. Many available meeting transcripts, however, are lengthy, unstructured, and thus difficult to navigate. It would be time-consuming for users to access important meeting output by reading the full transcripts. Consequently, automatically generated meeting summaries is of great value to people and businesses alike by providing quick access to the essential content of past meetings. The core objective of this research project is to automatically generate abstract-style focused meeting summaries to help users digest the vast amount of meeting content in an easy manner. It helps the research community to better understand the characteristics of the meeting domain, define the summarization task in meetings in a more consistent way, improve speech summarization evaluation metrics, and allow the wide use of speech summarization techniques in many applications (such as generating meeting minutes or lecture outlines). The broader impacts of this project includes sharing insights on conversational text with social scientists, providing natural language processing research training to students, and contributing effective methods for meeting summarization to the general public.

This research project aims at constructing abstractive summaries of meetings by developing computational models for important outcome identification and natural language summary generation, as well as designing objective summary evaluation methods. Existing meeting summarization systems remain largely extractive: Their summaries are comprised exclusively of patchworks of utterances selected directly from the meetings to be summarized. Although relatively easy to construct, extractive approaches simply present a set of utterances as the final summary, and fall short of producing concise and readable summaries, largely due to the spontaneous nature of spoken dialogue. This project formulates a new framework that accounts for the special aspects of meetings and use them to identify the utterances that contain important outcomes. A discriminative learning-based latent variable model trained with rich features is utilized to jointly capture topic shifting and extract utterances with important outputs. To perform sentence planning and surface realization in one single process, a neural network-based natural language generation model is developed. Objective evaluation methods are designed to measure various aspects for the quality of generated summaries.

PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH

Note:  When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Kechen Qin, Lu Wang, Joseph Kim "Joint Modeling of Content and Discourse Relations in Dialogues" Annual Meeting of the Association for Computational Linguistics , 2017
Lu Wang, Nick Beauchamp, Sarah Shugars, Kechen Qin "Winning on the Merits: The Joint Effects of Content and Style on Debate Outcomes" Transactions of the Association for Computational Linguistics , 2017

PROJECT OUTCOMES REPORT

Disclaimer

This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.

This project targets at constructing abstractive summaries of meetings by developing computational models for important outcome identification and abstractivesummary generation. Below I summarize the project outcomes in two aspects of intellectual merits and broader impacts. 


Intellectual Merits. This project advances natural language processing research by making the following contributions: (1) Joint learning and inference models are developed to detect salient content in meetings as well as predict speakers' intentions. (2) Novel neural network-based summarization systems are built for generating not only informative but also also coherent summaries with high clarity. Multi-task learning and reinforcement learning models are studied. Especially, linguistic-aware rewards are designed to drive the model to produce summaries of higher quality. (3) Keyphrase extraction and generation algorithms are developed to identify important phrases from articles. New evaluation methods are also proposed to address the previous problem on exact-matching based measurement.  

Broader Impacts. The project delivers at least four contributions: (1) The developed summarization algorithms can facilitate information consumption for the general public for learning from lengthy transcripts and documents. (2) The tools that are built from this project are made publicly available on the project website, to facilitate the usage by broader community. (3) Newly collected summarization dataset is also released to promote future research on building more effective summarization systems. (4) Seven papers are published at top natural language processing venues and co-located workshops.


Last Modified: 12/17/2019
Modified by: Lu Wang

Please report errors in award information by writing to: awardsearch@nsf.gov.

Print this page

Back to Top of page