Challenge: Existing evaluation metrics for text summarization systems are expensive and time-consuming.
Approach: They propose a training-free and reference-free summarization evaluation metric that incorporates a centrality-weighted relevance score and a self-referenced redundancy score.
Outcome: The proposed evaluation metric outperforms existing methods on multi-document and single-document summarization evaluation.

Similar Papers

Mitigating the Impact of Reference Quality on Evaluation of Summarization Systems with Reference-Free Metrics (2024.emnlp-main)

Copied to clipboard

Challenge: Existing metrics for summarization are reference-based and correlate poorly with relevance . fluency, faithfulness, coherence and relevance are all measures of human evaluation .
Approach: They propose a reference-free metric that correlates well with human evaluated relevance . n-gram importance weighting is used to weight a summary's importance .
Outcome: The proposed metric can be used along reference-based metrics to improve their robustness in low quality reference settings.
Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio (2022.naacl-main)

Copied to clipboard

Challenge: Existing evaluation metrics for summarization use human annotations as reference.
Approach: They propose a new automatic reference-free evaluation metric that compares semantic distribution between source document and summary by pretrained language models and considers summary compression ratio.
Outcome: The proposed metric is more consistent with human evaluation in terms of coherence, consistency, relevance and fluency.
Unsupervised Reference-Free Summary Quality Evaluation via Contrastive Learning (2020.emnlp-main)

Copied to clipboard

Challenge: Existing methods for document summarization consider the informativeness of the assessed summary and require human-generated references for each test summary.
Approach: They propose to evaluate summary qualities without reference summaries by unsupervised contrastive learning.
Outcome: The proposed method outperforms other evaluation metrics even without reference summaries.
SUPERT: Towards New Frontiers in Unsupervised Evaluation Metrics for Multi-Document Summarization (2020.acl-main)

Copied to clipboard

Challenge: Existing evaluation methods for document summarization require human annotations and annotations.
Approach: They propose a method which measures the quality of a summary by measuring its semantic similarity with a pseudo reference summary, using contextualized embeddings and soft token alignment techniques.
Outcome: The proposed method correlates better with human ratings by 18- 39% compared to the state-of-the-art evaluation metrics.
DocAsRef: An Empirical Study on Repurposing Reference-based Summary Quality Metrics as Reference-free Metrics (2023.findings-emnlp)

Copied to clipboard

Challenge: Existing reference-based metrics are limited by their reliance on human input.
Approach: They propose to adapt some reference-based metrics to assess system summary against human-written references.
Outcome: The proposed model outperforms reference-based metrics on two datasets and is comparable to reference-free metrics.
SummEval: Re-evaluating Summarization Evaluation (2021.tacl-1)

Copied to clipboard

Challenge: a lack of comprehensive studies on evaluation metrics for text summarization hinders progress . a new study aims to improve evaluation metrics that correlate with human judgments .
Approach: They propose to re-evaluate automatic evaluation metrics and share a toolkit for evaluation . they hope to promote a more complete evaluation protocol for text summarization .
Outcome: The proposed evaluation metrics are inconsistent with existing evaluation protocols.
HighRES: Highlight-based Reference-less Evaluation of Summarization (P19-1)

Copied to clipboard

Challenge: Existing methods for summarizing documents are inconsistent due to the difficulty of manual evaluation.
Approach: They propose a method where summaries are evaluated by multiple annotators against the source document via manually highlighted salient content.
Outcome: The proposed method improves inter-annotator agreement while highlighting differences among systems.
PrefScore: Pairwise Preference Learning for Reference-free Summarization Quality Assessment (2022.coling-1)

Copied to clipboard

Challenge: Existing studies on summarization evaluation without a human-written reference summary have shown high correlations with human ratings.
Approach: They propose to judge summary quality by learning preference rank from corrupted summaries . they use Bradley-Terry power ranking model to learn preference rank .
Outcome: Experiments on several datasets show that the proposed model can produce scores highly correlated with human ratings.
Summarization Evaluation in the Absence of Human Model Summaries Using the Compositionality of Word Embeddings (C18-1)

Copied to clipboard

Challenge: Existing summary evaluation methods rely on multiple model summaries to evaluate quality of summary outputs.
Approach: They propose a new summary evaluation approach that does not require human model summaries . they exploit compositional capabilities of word embeddings to develop features .
Outcome: The proposed metric replicates human-generated summarization scores on data from TAC 2008 and 2009 . the features are then used to train a learning model for predicting the summary content quality in the absence of gold models.
On the Limitations of Reference-Free Evaluations of Generated Text (2022.emnlp-main)

Copied to clipboard

Challenge: a recent study has shown that evaluation metrics which accurately estimate the quality of generated text are limited in their ability to evaluate generated text.
Approach: They argue that reference-free metrics are limited in their ability to evaluate generated text . they recommend that they be used as diagnostic tools for analyzing and understanding model behavior .
Outcome: The proposed evaluation metrics are limited in their ability to evaluate generated text . they can be optimized at test time, can be biased against models with similar outputs .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations