Challenge: Existing evaluation metrics for stories are limited in assessing intricate aspects of storytelling, such as fluency and interestingness.
Approach: They propose a novel method that uses perturbation techniques to evaluate story aspects . they compare fluency, coherence, relatedness, logicality, interestingness and interestingness to existing metrics .
Outcome: The proposed method shows that one specific perturbation is highly effective in capturing multiple aspects.

Similar Papers

DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence (2023.eacl-main)

Copied to clipboard

Challenge: DiscoScore is a parametrized discourse metric that uses BERT to model discourse coherence . it is weak when operated at system level, and is therefore not reliable in a way to spot improvements .
Approach: They propose a parametrized discourse metric which uses BERT to model discourse coherence from different perspectives.
Outcome: The proposed model outperforms existing models on document-level machine translation and summarization.
DATScore: Evaluating Translation with Data Augmented Translations (2023.findings-eacl)

Copied to clipboard

Challenge: Experimental results show that DATScore correlates better with human meta-evaluations than the other recent state-of-the-art metrics.
Approach: They propose to use data augmented translations to improve the evaluation of machine translations by using two new scoring strategies.
Outcome: The proposed metric improves on 3 NLG tasks other than translation.
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020.emnlp-main)

Copied to clipboard

Challenge: Existing datasets lack rich enough contexts to guide models and evaluations are unreliable for long-form creative text.
Approach: They propose a dataset and evaluation platform built from STORIUM . their dataset contains 6K lengthy stories with fine-grained natural language annotations .
Outcome: The proposed model can be used to generate 6K long stories with fine-grained natural language annotations and a user-generated dataset.
NovAScore: A New Automated Metric for Evaluating Document Level Novelty (2025.coling-main)

Copied to clipboard

Challenge: Recent research has focused on identifying text that introduces new, previously unknown information, but has seen a decline in novelty detection due to the rise of large language models.
Approach: They propose a novel automated metric for evaluating document-level novelty that aggregates the novelty and salience scores of atomic information and provides high interpretability and a detailed analysis of a document's novelty.
Outcome: The proposed metric scores high on the TAP-DLND 1.0 dataset and a human-annotated dataset.
Perturbation CheckLists for Evaluating NLG Evaluation Metrics (2021.emnlp-main)

Copied to clipboard

Challenge: Existing evaluation metrics for natural language generation are inadequate . existing metrics are not robust against simple perturbations and disagree with scores assigned by humans to perturbed output.
Approach: They propose to propose checks which perturb the output and target a specific criteria and then use them to refine their evaluation.
Outcome: The proposed templates show that existing evaluation metrics are not robust against simple perturbations and disagree with human scores on the perturbed output.
Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization (2025.acl-long)

Copied to clipboard

Challenge: n-gram-based metrics are considered indicative (even if imperfect) of human evaluation for English, but their suitability for other languages remains unclear.
Approach: They systematically assess evaluation metrics for generation for languages and tasks using n-gram-based and neural-based metrics.
Outcome: The proposed evaluation suite is based on eight languages from four typological families and shows that it is sensitivity to the language type at hand.
Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation (2021.naacl-main)

Copied to clipboard

Challenge: Existing methods to generate implausible stories using plots are unnatural and oversimplify the characteristics of implusible machine-generated stories.
Approach: They propose to generate a more comprehensive set of implausible stories using plots . plots are structured representations of controllable factors used to generate stories .
Outcome: The proposed model improves the quality of generated implausible stories using plots . it shows that the evaluation metrics trained on the generated data correlate better with human judgments compared to baselines.
DEMETR: Diagnosing Evaluation Metrics for Translation (2022.emnlp-main)

Copied to clipboard

Challenge: BLEU scores are based on string overlap, but they are opaque in comparison to newer learned metrics.
Approach: They propose a dataset to evaluate MT evaluation metrics based on linguistic perturbations in English . they find learned metrics perform substantially better than string-based metrics .
Outcome: The proposed dataset shows that learned metrics perform better than string-based metrics . the dataset contains 31K English examples that cover 35 different linguistic phenomena .
SESCORE2: Learning Text Generation Evaluation via Synthesizing Realistic Mistakes (2023.acl-long)

Copied to clipboard

Challenge: Existing learned metrics perform unsatisfactory across text generation tasks or require human annotations for training on specific tasks.
Approach: They propose a self-supervised approach to train a model-based metric for text generation evaluation using sentences retrieved from a corpus.
Outcome: The proposed model outperforms all prior unsupervised metrics on four text generation evaluation benchmarks, with an average Kendall improvement of 0.158.
Double Perturbation: On the Robustness of Robustness and Counterfactual Bias Evaluation (2021.naacl-main)

Copied to clipboard

Challenge: Recent studies show that NLP models are vulnerable to adversarial perturbations such as synonym substitutions or syntax-guided paraphrasing.
Approach: They propose a “double perturbation” framework to uncover model weaknesses beyond the test dataset.
Outcome: The proposed attack achieves high success rates on both original and robustly trained CNNs and Transformers.

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