English
Related papers

Related papers: On the Relation between Quality-Diversity Evaluati…

200 papers

Text generation is an important Natural Language Processing task with various applications. Although several metrics have already been introduced to evaluate the text generation methods, each of them has its own shortcomings. The most…

Machine Learning · Computer Science 2019-05-22 Ehsan Montahaei , Danial Alihosseini , Mahdieh Soleymani Baghshah

The purpose of unconditional text generation is to train a model with real sentences, then generate novel sentences of the same quality and diversity as the training data. However, when different metrics are used for comparing the methods…

Computation and Language · Computer Science 2020-07-03 Ping Cai , Xingyuan Chen , Peng Jin , Hongjun Wang , Tianrui Li

The text generated by neural language models is not as good as the real text. This means that their distributions are different. Generative Adversarial Nets (GAN) are used to alleviate it. However, some researchers argue that GAN variants…

Computer Vision and Pattern Recognition · Computer Science 2019-11-26 Xingyuan Chen , Ping Cai , Peng Jin , Haokun Du , Hongjun Wang , Xingyu Dai , Jiajun Chen

A good automatic evaluation metric for language generation ideally correlates highly with human judgements of text quality. Yet, there is a dearth of such metrics, which inhibits the rapid and efficient progress of language generators. One…

Computation and Language · Computer Science 2023-06-30 Tiago Pimentel , Clara Meister , Ryan Cotterell

Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this work, we propose a framework for evaluating…

Computation and Language · Computer Science 2021-01-26 Guy Tevet , Jonathan Berant

Large data-driven image models are extensively used to support creative and artistic work. Under the currently predominant distribution-fitting paradigm, a dataset is treated as ground truth to be approximated as closely as possible. Yet,…

Machine Learning · Computer Science 2023-06-16 Sebastian Berns , Simon Colton , Christian Guckelsberger

Generative models are increasingly able to produce remarkably high quality images and text. The community has developed numerous evaluation metrics for comparing generative models. However, these metrics do not effectively quantify data…

Machine Learning · Computer Science 2020-10-15 Liam Fowl , Micah Goldblum , Arjun Gupta , Amr Sharaf , Tom Goldstein

We propose a function-valued evaluation metric for generative models based on the relative density ratio (RDR) designed to characterize distributional differences between real and generated samples. As an evaluation metric, the RDR function…

Methodology · Statistics 2025-12-29 Yuliang Xu , Yun Wei , Li Ma

The diversity across outputs generated by LLMs shapes perception of their quality and utility. High lexical diversity is often desirable, but there is no standard method to measure this property. Templated answer structures and ``canned''…

Computation and Language · Computer Science 2026-02-19 Chantal Shaib , Venkata S. Govindarajan , Joe Barrow , Jiuding Sun , Alexa F. Siu , Byron C. Wallace , Ani Nenkova

Summarizing data samples by quantitative measures has a long history, with descriptive statistics being a case in point. However, as natural language processing methods flourish, there are still insufficient characteristic metrics to…

Computation and Language · Computer Science 2020-03-20 Yi-An Lai , Xuan Zhu , Yi Zhang , Mona Diab

In natural language generation for advertising, creating diverse and engaging ad texts is crucial for capturing a broad audience and avoiding advertising fatigue. Regardless of the importance of diversity, the impact of the…

Computation and Language · Computer Science 2025-05-23 Yoichi Aoki , Soichiro Murakami , Ukyo Honda , Akihiko Kato

Generating diverse and relevant questions over text is a task with widespread applications. We argue that commonly-used evaluation metrics such as BLEU and METEOR are not suitable for this task due to the inherent diversity of reference…

Computation and Language · Computer Science 2020-08-18 Michael Sejr Schlichtkrull , Weiwei Cheng

Well-calibrated model confidence scores can improve the usefulness of text generation models. For example, users can be prompted to review predictions with low confidence scores, to prevent models from returning bad or potentially dangerous…

Computation and Language · Computer Science 2025-06-16 Lorenzo Jaime Yu Flores , Ori Ernst , Jackie Chi Kit Cheung

Open-ended text generation has become a prominent task in natural language processing due to the rise of powerful (large) language models. However, evaluating the quality of these models and the employed decoding strategies remains…

Computation and Language · Computer Science 2025-06-18 Esteban Garces Arias , Hannah Blocher , Julian Rodemann , Meimingwei Li , Christian Heumann , Matthias Aßenmacher

Text generation has made significant advances in the last few years. Yet, evaluation metrics have lagged behind, as the most popular choices (e.g., BLEU and ROUGE) may correlate poorly with human judgments. We propose BLEURT, a learned…

Computation and Language · Computer Science 2020-05-22 Thibault Sellam , Dipanjan Das , Ankur P. Parikh

As major progress is made in open-ended text generation, measuring how close machine-generated text is to human language remains a critical open problem. We introduce MAUVE, a comparison measure for open-ended text generation, which…

Computation and Language · Computer Science 2021-11-24 Krishna Pillutla , Swabha Swayamdipta , Rowan Zellers , John Thickstun , Sean Welleck , Yejin Choi , Zaid Harchaoui

Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers…

Computation and Language · Computer Science 2020-11-30 Nicholas Roberts , Davis Liang , Graham Neubig , Zachary C. Lipton

How can we measure whether a natural language generation system produces both high quality and diverse outputs? Human evaluation captures quality but not diversity, as it does not catch models that simply plagiarize from the training set.…

Computation and Language · Computer Science 2019-04-08 Tatsunori B. Hashimoto , Hugh Zhang , Percy Liang

Traditional automated metrics for evaluating conditional natural language generation use pairwise comparisons between a single generated text and the best-matching gold-standard ground truth text. When multiple ground truths are available,…

Computation and Language · Computer Science 2022-09-30 David M Chan , Yiming Ni , David A Ross , Sudheendra Vijayanarasimhan , Austin Myers , John Canny

Controlled generation refers to the problem of creating text that contains stylistic or semantic attributes of interest. Many approaches reduce this problem to training a predictor of the desired attribute. For example, researchers hoping…

Computation and Language · Computer Science 2023-06-02 Carolina Zheng , Claudia Shi , Keyon Vafa , Amir Feder , David M. Blei
‹ Prev 1 2 3 10 Next ›