Is Reference Necessary in the Evaluation of NLG Systems? When and Where?

• URL: http://arxiv.org/abs/2403.14275v1
• Date: Thu, 21 Mar 2024 10:31:11 GMT
• Title: Is Reference Necessary in the Evaluation of NLG Systems? When and Where?
• Authors: Shuqian Sheng, Yi Xu, Luoyi Fu, Jiaxin Ding, Lei Zhou, Xinbing Wang, Chenghu Zhou,
• Abstract summary: We show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.
• Score: 58.52957222172377
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: The majority of automatic metrics for evaluating NLG systems are reference-based. However, the challenge of collecting human annotation results in a lack of reliable references in numerous application scenarios. Despite recent advancements in reference-free metrics, it has not been well understood when and where they can be used as an alternative to reference-based metrics. In this study, by employing diverse analytical approaches, we comprehensively assess the performance of both metrics across a wide range of NLG tasks, encompassing eight datasets and eight evaluation models. Based on solid experiments, the results show that reference-free metrics exhibit a higher correlation with human judgment and greater sensitivity to deficiencies in language quality. However, their effectiveness varies across tasks and is influenced by the quality of candidate texts. Therefore, it's important to assess the performance of reference-free metrics before applying them to a new task, especially when inputs are in uncommon form or when the answer space is highly variable. Our study can provide insight into the appropriate application of automatic metrics and the impact of metric choice on evaluation performance.

Related papers

• What is the Best Automated Metric for Text to Motion Generation? [19.71712698183703]
  There is growing interest in generating skeleton-based human motions from natural language descriptions. Human evaluation is the ultimate accuracy measure for this task, and automated metrics should correlate well with human quality judgments. This paper systematically studies which metrics best align with human evaluations and proposes new metrics that align even better.
  arXiv  Detail & Related papers  (2023-09-19T01:59:54Z)
• Towards Multiple References Era -- Addressing Data Leakage and Limited Reference Diversity in NLG Evaluation [55.92852268168816]
  N-gram matching-based evaluation metrics, such as BLEU and chrF, are widely utilized across a range of natural language generation (NLG) tasks. Recent studies have revealed a weak correlation between these matching-based metrics and human evaluations. We propose to utilize textitmultiple references to enhance the consistency between these metrics and human evaluations.
  arXiv  Detail & Related papers  (2023-08-06T14:49:26Z)
• DecompEval: Evaluating Generated Texts as Unsupervised Decomposed Question Answering [95.89707479748161]
  Existing evaluation metrics for natural language generation (NLG) tasks face the challenges on generalization ability and interpretability. We propose a metric called DecompEval that formulates NLG evaluation as an instruction-style question answering task. We decompose our devised instruction-style question about the quality of generated texts into the subquestions that measure the quality of each sentence. The subquestions with their answers generated by PLMs are then recomposed as evidence to obtain the evaluation result.
  arXiv  Detail & Related papers  (2023-07-13T16:16:51Z)
• NLG Evaluation Metrics Beyond Correlation Analysis: An Empirical Metric Preference Checklist [20.448405494617397]
  Task-agnostic metrics, such as Perplexity, BLEU, BERTScore, are cost-effective and highly adaptable to diverse NLG tasks. Human-aligned metrics (CTC, CtrlEval, UniEval) improves correlation level by incorporating desirable human-like qualities as training objective. We show that automatic metrics provide a better guidance than human on discriminating system-level performance in Text Summarization and Controlled Generation tasks.
  arXiv  Detail & Related papers  (2023-05-15T11:51:55Z)
• BEAMetrics: A Benchmark for Language Generation Evaluation Evaluation [16.81712151903078]
  Natural language processing (NLP) systems are increasingly trained to generate open-ended text. Different metrics have different strengths and biases, and reflect human intuitions better on some tasks than others. Here, we describe the Benchmark to Evaluate Automatic Metrics (BEAMetrics) to make research into new metrics itself easier to evaluate.
  arXiv  Detail & Related papers  (2021-10-18T10:03:19Z)
• Perturbation CheckLists for Evaluating NLG Evaluation Metrics [16.20764980129339]
  Natural Language Generation (NLG) evaluation is a multifaceted task requiring assessment of multiple desirable criteria. Across existing datasets for 6 NLG tasks, we observe that the human evaluation scores on these multiple criteria are often not correlated. This suggests that the current recipe of proposing new automatic evaluation metrics for NLG is inadequate.
  arXiv  Detail & Related papers  (2021-09-13T08:26:26Z)
• OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics [53.779709191191685]
  We propose OpenMEVA, a benchmark for evaluating open-ended story generation metrics. OpenMEVA provides a comprehensive test suite to assess the capabilities of metrics. We observe that existing metrics have poor correlation with human judgments, fail to recognize discourse-level incoherence, and lack inferential knowledge.
  arXiv  Detail & Related papers  (2021-05-19T04:45:07Z)
• GO FIGURE: A Meta Evaluation of Factuality in Summarization [131.1087461486504]
  We introduce GO FIGURE, a meta-evaluation framework for evaluating factuality evaluation metrics. Our benchmark analysis on ten factuality metrics reveals that our framework provides a robust and efficient evaluation. It also reveals that while QA metrics generally improve over standard metrics that measure factuality across domains, performance is highly dependent on the way in which questions are generated.
  arXiv  Detail & Related papers  (2020-10-24T08:30:20Z)
• Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metrics [64.88815792555451]
  We show that current methods for judging metrics are highly sensitive to the translations used for assessment. We develop a method for thresholding performance improvement under an automatic metric against human judgements.
  arXiv  Detail & Related papers  (2020-06-11T09:12:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.