English
Related papers

Related papers: Unifying Human and Statistical Evaluation for Natu…

200 papers

Language Models (LMs) have shown promising performance in natural language generation. However, as LMs often generate incorrect or hallucinated responses, it is crucial to correctly quantify their uncertainty in responding to given inputs.…

Computation and Language · Computer Science 2024-09-17 Xinmeng Huang , Shuo Li , Mengxin Yu , Matteo Sesia , Hamed Hassani , Insup Lee , Osbert Bastani , Edgar Dobriban

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 reference-free evaluation…

Computation and Language · Computer Science 2022-04-22 Esin Durmus , Faisal Ladhak , Tatsunori Hashimoto

Natural language generation (NLG) has received increasing attention, which has highlighted evaluation as a central methodological concern. Since human evaluations for these systems are costly, automatic metrics have broad appeal in NLG.…

Computation and Language · Computer Science 2019-08-01 Johnny Tian-Zheng Wei

Language models (LMs) are statistical models trained to assign probability to human-generated text. As such, it is reasonable to question whether they approximate linguistic variability exhibited by humans well. This form of statistical…

Computation and Language · Computer Science 2024-03-19 Evgenia Ilia , Wilker Aziz

Evaluating the quality of automatically generated image descriptions is challenging, requiring metrics that capture various aspects such as grammaticality, coverage, correctness, and truthfulness. While human evaluation offers valuable…

Computer Vision and Pattern Recognition · Computer Science 2024-08-06 Jia-Hong Huang , Hongyi Zhu , Yixian Shen , Stevan Rudinac , Alessio M. Pacces , Evangelos Kanoulas

Evaluation in natural language processing guides and promotes research on models and methods. In recent years, new evalua-tion data sets and evaluation tasks have been continuously proposed. At the same time, a series of problems exposed by…

Computation and Language · Computer Science 2021-04-21 Qingxiu Dong , Zhifang Sui , Weidong Zhan , Baobao Chang

Automatic text generation based on neural language models has achieved performance levels that make the generated text almost indistinguishable from those written by humans. Despite the value that text generation can have in various…

Computation and Language · Computer Science 2022-05-02 Vijini Liyanage , Davide Buscaldi , Adeline Nazarenko

Natural language generation (NLG) is increasingly deployed in high-stakes domains, yet common intrinsic evaluation methods, such as n-gram overlap or sentence plausibility, weakly correlate with actual decision-making efficacy. We propose a…

Computation and Language · Computer Science 2025-07-04 Yu-Shiang Huang , Chuan-Ju Wang , Chung-Chi Chen

We argue that there are currently two major bottlenecks to the commercial use of statistical machine learning approaches for natural language generation (NLG): (a) The lack of reliable automatic evaluation metrics for NLG, and (b) The…

Computation and Language · Computer Science 2017-06-30 Jekaterina Novikova , Ondřej Dušek , Verena Rieser

This paper proposes an enhanced natural language generation system combining the merits of both rule-based approaches and modern deep learning algorithms, boosting its performance to the extent where the generated textual content is capable…

Computation and Language · Computer Science 2020-06-18 Wei Wei , Bei Zhou , Georgios Leontidis

Natural language processing (NLP) systems are increasingly trained to generate open-ended text rather than classifying between responses. This makes research on evaluation metrics for generated language -- functions that score system output…

Computation and Language · Computer Science 2021-10-19 Thomas Scialom , Felix Hill

Obtaining meaningful quality scores for machine translation systems through human evaluation remains a challenge given the high variability between human evaluators, partly due to subjective expectations for translation quality for…

Computation and Language · Computer Science 2022-05-18 Daniel Licht , Cynthia Gao , Janice Lam , Francisco Guzman , Mona Diab , Philipp Koehn

As large language models (LLMs) continue to advance, accurately and comprehensively evaluating their performance becomes increasingly challenging. Ranking the relative performance of LLMs based on Elo ratings, according to human judgment,…

Computation and Language · Computer Science 2023-11-14 Minghao Wu , Alham Fikri Aji

When the training dataset comprises a 1:1 proportion of dogs to cats, a generative model that produces 1:1 dogs and cats better resembles the training species distribution than another model with 3:1 dogs and cats. Can we capture this…

Computer Vision and Pattern Recognition · Computer Science 2024-07-18 Dongkyun Kim , Mingi Kwon , Youngjung Uh

Natural language generation lies at the core of generative dialogue systems and conversational agents. We describe an ensemble neural language generator, and present several novel methods for data representation and augmentation that yield…

Computation and Language · Computer Science 2018-05-18 Juraj Juraska , Panagiotis Karagiannis , Kevin K. Bowden , Marilyn A. Walker

Personality have been found to predict many life outcomes, and there have been huge interests on automatic personality recognition from a speaker's utterance. Previously, we achieved accuracies between 37%-44% for three-way classification…

Sound · Computer Science 2018-02-06 Guozhen An , Rivka Levitan

Neural approaches to Natural Language Generation (NLG) have been promising for goal-oriented dialogue. One of the challenges of productionizing these approaches, however, is the ability to control response quality, and ensure that generated…

Computation and Language · Computer Science 2022-08-24 Ashwini Challa , Kartikeya Upasani , Anusha Balakrishnan , Rajen Subba

Key doctrines, including novelty (patent), originality (copyright), and distinctiveness (trademark), turn on a shared empirical question: whether a body of work is meaningfully distinct from a relevant reference class. Yet analyses…

Computers and Society · Computer Science 2026-01-27 Anirban Mukherjee , Hannah Hanwen Chang

This thesis argues that the currently widely used Natural Language Processing algorithms possibly have various limitations related to the properties of the texts they handle and produce. With the wide adoption of these tools in rapid…

Computation and Language · Computer Science 2024-09-17 Josef Jon

By harnessing pre-trained language models, summarization models had rapid progress recently. However, the models are mainly assessed by automatic evaluation metrics such as ROUGE. Although ROUGE is known for having a positive correlation…

Computation and Language · Computer Science 2021-06-03 Wonjin Yoon , Yoon Sun Yeo , Minbyul Jeong , Bong-Jun Yi , Jaewoo Kang