English
Related papers

Related papers: Not All Errors are Equal: Learning Text Generation…

200 papers

The majority of NLG evaluation relies on automatic metrics, such as BLEU . In this paper, we motivate the need for novel, system- and data-independent automatic evaluation methods: We investigate a wide range of metrics, including…

Computation and Language · Computer Science 2017-09-18 Jekaterina Novikova , Ondřej Dušek , Amanda Cercas Curry , Verena Rieser

Word-level quality estimation (WQE) aims to automatically identify fine-grained error spans in machine-translated outputs and has found many uses, including assisting translators during post-editing. Modern WQE techniques are often…

Computation and Language · Computer Science 2025-11-18 Gabriele Sarti , Vilém Zouhar , Malvina Nissim , Arianna Bisazza

Personalized tutoring, teacher training, and education research need access to \emph{targeted} synthetic misconceptions, but privacy and IRB constraints make labelled corpora of real student errors scarce. LLMs could in principle generate…

Computation and Language · Computer Science 2026-05-29 Xinming Yang , Jun Li

As research on machine translation moves to translating text beyond the sentence level, it remains unclear how effective automatic evaluation metrics are at scoring longer translations. In this work, we first propose a method for creating…

Computation and Language · Computer Science 2023-08-29 Daniel Deutsch , Juraj Juraska , Mara Finkelstein , Markus Freitag

Automatic evaluation comparing candidate translations to human-generated paraphrases of reference translations has recently been proposed by Freitag et al. When used in place of original references, the paraphrased versions produce metric…

Computation and Language · Computer Science 2020-10-21 Markus Freitag , George Foster , David Grangier , Colin Cherry

We introduce unsupervised techniques based on phrase-based statistical machine translation for grammatical error correction (GEC) trained on a pseudo learner corpus created by Google Translation. We verified our GEC system through…

Computation and Language · Computer Science 2019-07-24 Satoru Katsumata , Mamoru Komachi

The growing interest in automatic survey generation (ASG), a task that traditionally required considerable time and effort, has been spurred by recent advances in large language models (LLMs). With advancements in retrieval-augmented…

Computation and Language · Computer Science 2025-08-18 Beichen Guo , Zhiyuan Wen , Yu Yang , Peng Gao , Ruosong Yang , Jiaxing Shen

Large language models (LLMs) have demonstrated great potential for automating the evaluation of natural language generation. Previous frameworks of LLM-as-a-judge fall short in two ways: they either use zero-shot setting without consulting…

Computation and Language · Computer Science 2025-04-11 Mingxuan Li , Hanchen Li , Chenhao Tan

Recent advancements in large language models (LLMs) on language modeling and emergent capabilities make them a promising reference-free evaluator of natural language generation quality, and a competent alternative to human evaluation.…

Computation and Language · Computer Science 2023-09-26 Yuxuan Liu , Tianchi Yang , Shaohan Huang , Zihan Zhang , Haizhen Huang , Furu Wei , Weiwei Deng , Feng Sun , Qi Zhang

Language generation based on maximum likelihood estimation (MLE) has become the fundamental approach for text generation. Maximum likelihood estimation is typically performed by minimizing the log-likelihood loss, also known as the…

Computation and Language · Computer Science 2024-05-30 Chenze Shao , Fandong Meng , Yijin Liu , Jie Zhou

The quality of texts generated by natural language generation (NLG) systems is hard to measure automatically. Conventional reference-based metrics, such as BLEU and ROUGE, have been shown to have relatively low correlation with human…

Computation and Language · Computer Science 2023-05-25 Yang Liu , Dan Iter , Yichong Xu , Shuohang Wang , Ruochen Xu , Chenguang Zhu

We survey human evaluation in papers presenting work on creative natural language generation that have been published in INLG 2020 and ICCC 2020. The most typical human evaluation method is a scaled survey, typically on a 5 point scale,…

Computation and Language · Computer Science 2021-08-03 Mika Hämäläinen , Khalid Alnajjar

Automatic evaluations for natural language generation (NLG) conventionally rely on token-level or embedding-level comparisons with text references. This differs from human language processing, for which visual imagination often improves…

Computation and Language · Computer Science 2023-02-16 Wanrong Zhu , Xin Eric Wang , An Yan , Miguel Eckstein , William Yang Wang

Natural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of NLG particularly challenging.…

Computation and Language · Computer Science 2022-01-25 Mingkai Deng , Bowen Tan , Zhengzhong Liu , Eric P. Xing , Zhiting Hu

Neural natural language generation (NLG) and understanding (NLU) models are data-hungry and require massive amounts of annotated data to be competitive. Recent frameworks address this bottleneck with generative models that synthesize weak…

Computation and Language · Computer Science 2021-02-09 Ernie Chang , Vera Demberg , Alex Marin

Estimating the expected output quality of generation systems is central to NLG. This paper qualifies the notion that automatic metrics are not as good as humans in estimating system-level quality. Statistically, humans are unbiased, high…

Computation and Language · Computer Science 2024-12-17 Johnny Tian-Zheng Wei , Robin Jia

Large language models can now directly generate answers to many factual questions without referencing external sources. Unfortunately, relatively little attention has been paid to methods for evaluating the quality and correctness of these…

Information Retrieval · Computer Science 2024-01-11 Negar Arabzadeh , Amin Bigdeli , Charles L. A. Clarke

Response diversity has become an important criterion for evaluating the quality of open-domain dialogue generation models. However, current evaluation metrics for response diversity often fail to capture the semantic diversity of generated…

Computation and Language · Computer Science 2022-10-25 Seungju Han , Beomsu Kim , Buru Chang

While often assumed a gold standard, effective human evaluation of text generation remains an important, open area for research. We revisit this problem with a focus on producing consistent evaluations that are reproducible -- over time and…

Computation and Language · Computer Science 2022-11-02 Daniel Khashabi , Gabriel Stanovsky , Jonathan Bragg , Nicholas Lourie , Jungo Kasai , Yejin Choi , Noah A. Smith , Daniel S. Weld

Pretraining-based (PT-based) automatic evaluation metrics (e.g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e.g., machine translation and text summarization) due to their better correlation with…

Computation and Language · Computer Science 2022-11-04 Peiyuan Gong , Xuebo Liu , Heyan Huang , Min Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›