Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
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.Previous work has typically focused on a single task and developed individual evaluation metrics based on specific intuitions.In this paper, we propose a unifying perspective based on the nature of information change in NLG tasks, including compression (e.g., summarization), transduction (e.g., text rewriting), and creation (e.g., dialog).Information alignment between input, context, and output text plays a common central role in characterizing the generation.With automatic alignment prediction models, we develop a family of interpretable metrics that are suitable for evaluating key aspects of different NLG tasks, often without need of gold reference data.Experiments show the uniformly designed metrics achieve stronger or comparable correlations with human judgement compared to state-of-the-art metrics in each of diverse tasks, including text summarization, style transfer, and knowledgegrounded dialog. 1
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2019) · Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers) · doi:10.18653/v1/n19-1423 · Cited by 54,325
Lewis, M., Liu, Y., Goyal, N., Ghazvininejad, M., Mohamed, A., Levy, O., Stoyanov, V., & Zettlemoyer, L. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.703 · Cited by 8,821
BERTScore: Evaluating Text Generation with BERT
Zhang, T., Kishore, V., Wu, F., Weinberger, K. Q., & Artzi, Y. (2019) · arXiv · doi:10.48550/arxiv.1904.09675 · Cited by 2,865
Abstractive Text Summarization using Sequence-to-sequence RNNs and Beyond
Nallapati, R., Zhou, B., dos Santos, C., Gulcehre, C., & Xiang, B. (2016) · Proceedings of The 20th SIGNLL Conference on Computational Natural Language Learning · doi:10.18653/v1/k16-1028 · Cited by 2,361
chrF: character n-gram F-score for automatic MT evaluation
Popović, M. (2015) · Proceedings of the Tenth Workshop on Statistical Machine Translation · doi:10.18653/v1/w15-3049 · Cited by 1,220 · cited 1×
“It has typically been approximated by n-gram overlap (Papineni et al., 2002; Popovi´c, 2015), synonym matching (Banerjee and Lavie, 2005) and embedding similarities (Kusner et al., 2015).”
MethodNarayan, S., Cohen, S. B., & Lapata, M. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1206 · Cited by 1,207
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.173 · Cited by 1,185
On Faithfulness and Factuality in Abstractive Summarization
Maynez, J., Narayan, S., Bohnet, B., & McDonald, R. (2020) · arXiv · doi:10.48550/arxiv.2005.00661 · Cited by 1,185 · cited 4×
“Factual Correctness, Faithfulness, (No) Hallucination (Wang et al., 2020), (Maynez et al., 2020), (Durmus et al., 2020), (Kry´sci´nski et al., 2019), (Fabbri et al., 2021), etc.”
MethodInfluentialPersonalizing Dialogue Agents: I have a dog, do you have pets too?
Zhang, S., Dinan, E., Urbanek, J., Szlam, A., Kiela, D., & Weston, J. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1205 · Cited by 1,177
DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation
Zhang, Y., Sun, S., Galley, M., Chen, Y.-C., Brockett, C., Gao, X., Gao, J., Liu, J., & Dolan, B. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2020.acl-demos.30 · Cited by 1,076
Cited by
Repairing the Cracked Foundation: A Survey of Obstacles in Evaluation Practices for Generated Text
Gehrmann, S., Clark, E., & Sellam, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13715 · Cited by 123
Towards a Unified Multi-Dimensional Evaluator for Text Generation
Zhong, M., Liu, Y., Yin, D., Mao, Y., Jiao, Y., Liu, P., Zhu, C., Ji, H., & Han, J. (2022) · Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2022.emnlp-main.131 · Cited by 117
“For the score calculation, we follow previous work to compute sentence-level average scores for fluency and consistency (Laban et al., 2021) in summarization, and sentence-level cumulative scores for engagingness (Deng et al., 2021), while the rest is calculated as Equation 1.”
BackgroundMethodInfluentialAlignScore: Evaluating factual consistency with a unified alignment function
Zha, Y., Yang, Y., Li, R., & Hu, Z. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.634 · Cited by 81
Self-citationMulti-Dimensional Evaluation of Text Summarization with In-Context Learning
Jain, S., Keshava, V., Mysore Sathyendra, S., Fernandes, P., Liu, P., Neubig, G., & Zhou, C. (2023) · Findings of the Association for Computational Linguistics: ACL 2023 · doi:10.18653/v1/2023.findings-acl.537 · Cited by 15
“We compare I CE to the following state-of-the-art multi-dimensional evaluators: (1) CTC (Deng et al., 2021) uses information alignment between generated outputs and references or inputs; (2) BARTScore (Yuan et al., 2021) uses the conditional probability of a sequence given inputs or references; and (3) UniEval (Zhong…”
BackgroundMethodInfluential
Metadata
- Authors
- Deng, M., Tan, B., Liu, Z., Xing, E., & Hu, Z.
- Venue
- Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
- Published
- 2021
- Pages
- 7580-7605
- OpenAlex
- W3201085013
- Cited by
- 47
- References
- 32
- FWCI
- 5.18
- Type
- conference paper
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation. https://app.cochat.ai/papers/10.18653/v1/2021.emnlp-main.599
- The paper
- Deng, M., Tan, B., Liu, Z., Xing, E., & Hu, Z. (2021). Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation. Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. https://doi.org/10.18653/v1/2021.emnlp-main.599
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.