How well do you know your summarization datasets?

by   Priyam Tejaswin, et al.

State-of-the-art summarization systems are trained and evaluated on massive datasets scraped from the web. Despite their prevalence, we know very little about the underlying characteristics (data noise, summarization complexity, etc.) of these datasets, and how these affect system performance and the reliability of automatic metrics like ROUGE. In this study, we manually analyze 600 samples from three popular summarization datasets. Our study is driven by a six-class typology which captures different noise types (missing facts, entities) and degrees of summarization difficulty (extractive, abstractive). We follow with a thorough analysis of 27 state-of-the-art summarization models and 5 popular metrics, and report our key insights: (1) Datasets have distinct data quality and complexity distributions, which can be traced back to their collection process. (2) The performance of models and reliability of metrics is dependent on sample complexity. (3) Faithful summaries often receive low scores because of the poor diversity of references. We release the code, annotated data and model outputs.



There are no comments yet.


page 7

page 12


Understanding Factuality in Abstractive Summarization with FRANK: A Benchmark for Factuality Metrics

Modern summarization models generate highly fluent but often factually u...

Everything You Always Wanted to Know About TREC RTS* (*But Were Afraid to Ask)

The TREC Real-Time Summarization (RTS) track provides a framework for ev...

Efficiency Metrics for Data-Driven Models: A Text Summarization Case Study

Using data-driven models for solving text summarization or similar tasks...

Metrics also Disagree in the Low Scoring Range: Revisiting Summarization Evaluation Metrics

In text summarization, evaluating the efficacy of automatic metrics with...

Facet-Aware Evaluation for Extractive Text Summarization

Commonly adopted metrics for extractive text summarization like ROUGE fo...

A Closer Look at Data Bias in Neural Extractive Summarization Models

In this paper, we take stock of the current state of summarization datas...

Mitigating Data Scarceness through Data Synthesis, Augmentation and Curriculum for Abstractive Summarization

This paper explores three simple data manipulation techniques (synthesis...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.