paper-with-me

홈 › Papers

Reference-free Evaluation Metrics for Text Generation: A Survey

2025-01-21 · Takumi Ito, Kees Van Deemter, Jun Suzuki

A number of automatic evaluation metrics have been proposed for natural language generation systems. The most common approach to automatic evaluation is the use of a reference-based metric that compares the model's output with gold-standard references written by humans. However, it is expensive to create such references, and for some tasks, such as response generation in dialogue, creating references is not a simple matter. Therefore, various reference-free metrics have been developed in recent years. In this survey, which intends to cover the full breadth of all NLG tasks, we investigate the most commonly used approaches, their application, and their other uses beyond evaluating models. The survey concludes by highlighting some promising directions for future research.

📄 PDF Abstract BibTeX arXiv:2501.12011

Code (0)

등록된 구현이 없습니다.

Tasks

Response GenerationSurveyText Generation

Similar Papers 제목 키워드 기반

Spurious Correlations in Reference-Free Evaluation of Text Generation

2022-04-21 · ACL 2022 5 · Esin Durmus, Faisal Ladhak, Tatsunori Hashimoto

Model-based, reference-free evaluation metrics have been proposed as a fast and cost-effective approach to evaluate Natural Language Generation (NLG) systems. Despite promising recent results, we find evidence that refer…

Abstractive Text SummarizationText GenerationText Summarization

On the Limitations of Reference-Free Evaluations of Generated Text

2022-10-22 · Daniel Deutsch, Rotem Dror, Dan Roth

There is significant interest in developing evaluation metrics which accurately estimate the quality of generated text without the aid of a human-written reference text, which can be time consuming and expensive to colle…

DiagnosticMachine Translation

On the Evaluation Metrics for Paraphrase Generation

2022-02-17 · Lingfeng Shen, Lemao Liu, Haiyun Jiang, Shuming Shi

In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance than their reference-based counterparts…

Machine TranslationParaphrase Generation

CTRLEval: An Unsupervised Reference-Free Metric for Evaluating Controlled Text Generation

2022-04-02 · ACL 2022 5 · Pei Ke, Hao Zhou, Yankai Lin, Peng Li 외

Existing reference-free metrics have obvious limitations for evaluating controlled text generation models. Unsupervised metrics can only provide a task-agnostic evaluation result which correlates weakly with human judgme…

Language ModelingLanguage ModellingText GenerationText Infilling

Learning to Rank Visual Stories From Human Ranking Data

2022-05-01 · ACL 2022 5 · Chi-Yang Hsu, Yun-Wei Chu, Vincent Chen, Kuan-Chieh Lo 외

Visual storytelling (VIST) is a typical vision and language task that has seen extensive development in the natural language generation research domain. However, it remains unclear whether conventional automatic evaluati…

Learning-To-RankText GenerationVisual Storytelling