Combining Deep Neural Reranking and Unsupervised Extraction for Multi-Query Focused Summarization

02/02/2023
by   Philipp Seeberger, et al.
0

The CrisisFACTS Track aims to tackle challenges such as multi-stream fact-finding in the domain of event tracking; participants' systems extract important facts from several disaster-related events while incorporating the temporal order. We propose a combination of retrieval, reranking, and the well-known Integer Linear Programming (ILP) and Maximal Marginal Relevance (MMR) frameworks. In the former two modules, we explore various methods including an entity-based baseline, pre-trained and fine-tuned Question Answering systems, and ColBERT. We then use the latter module as an extractive summarization component by taking diversity and novelty criteria into account. The automatic scoring runs show strong results across the evaluation setups but also reveal shortcomings and challenges.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/05/2023

Unsupervised Broadcast News Summarization; a comparative study on Maximal Marginal Relevance (MMR) and Latent Semantic Analysis (LSA)

The methods of automatic speech summarization are classified into two gr...
research
05/27/2021

Improve Query Focused Abstractive Summarization by Incorporating Answer Relevance

Query focused summarization (QFS) models aim to generate summaries from ...
research
11/29/2022

Few-shot Query-Focused Summarization with Prefix-Merging

Query-focused summarization has been considered as an important extensio...
research
04/06/2020

Query Focused Multi-Document Summarization with Distant Supervision

We consider the problem of better modeling query-cluster interactions to...
research
08/01/2020

Experiments in Extractive Summarization: Integer Linear Programming, Term/Sentence Scoring, and Title-driven Models

In this paper, we revisit the challenging problem of unsupervised single...
research
08/24/2020

A Baseline Analysis for Podcast Abstractive Summarization

Podcast summary, an important factor affecting end-users' listening deci...

Please sign up or login with your details

Forgot password? Click here to reset