Controlling hallucinations at word level in data-to-text generation
Open accessThe DOI matches its Crossref record; 78 of the 78 references it cites were found in a registry or an index.
Abstract
Data-to-Text Generation (DTG) is a subfield of Natural Language Generation aiming at transcribing structured data in natural language descriptions. The field has been recently boosted by the use of neural-based generators which exhibit on one side great syntactic skills without the need of hand-crafted pipelines; on the other side, the quality of the generated text reflects the quality of the training data, which in realistic settings only offer imperfectly aligned structure-text pairs. Consequently, state-of-art neural models include misleading statements –usually called hallucinations—in their outputs. The control of this phenomenon is today a major challenge for DTG, and is the problem addressed in the paper. Previous work deal with this issue at the instance level: using an alignment score for each table-reference pair. In contrast, we propose a finer-grained approach, arguing that hallucinations should rather be treated at the word level. Specifically, we propose a Multi-Branch Decoder which is able to leverage word-level labels to learn the relevant parts of each training instance. These labels are obtained following a simple and efficient scoring procedure based on co-occurrence analysis and dependency parsing. Extensive evaluations, via automated metrics and human judgment on the standard WikiBio benchmark, show the accuracy of our alignment labels and the effectiveness of the proposed Multi-Branch Decoder. Our model is able to reduce and control hallucinations, while keeping fluency and coherence in generated texts. Further experiments on a degraded version of ToTTo show that our model could be successfully used on very noisy settings.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Instance-level scores can lead to a signal loss because divergences occur at the word level; i.e., parts of the target sentence are loyal to the source input, while others diverge [216].”
From Survey of Hallucination in Natural Language Generation (2023) · cites this paper as [216]
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
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404 · cited 1×
“Therefore, all types of decoder can be used, such as Recurrent Neural Networks (RNNs) [57], Transformers [67], and Convolu-tional Neural Networks [16].”
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“Training is performed using the Adam algorithm (Kingma and Ba 2015) with learning rate η = 10−3, β1 = 0.”
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 1×
“2019) to fine-tune a BERT model (Devlin et al. 2019) on the UD English ParTUT dataset (Sanguinetti and Bosco 2015); Stanza (Qi et al.”
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 · cited 1×
“2019) to fine-tune a BERT model (Devlin et al. 2019) on the UD English ParTUT dataset (Sanguinetti and Bosco 2015); Stanza (Qi et al.”
Learning representations by back-propagating errors
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986) · Nature · doi:10.1038/323533a0 · Cited by 31,892
Distributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Effective Approaches to Attention-based Neural Machine Translation
Luong, T., Pham, H., & Manning, C. D. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1166 · Cited by 8,382 · cited 1×
“We use the general attention mechanism with input feeding (Luong et al. 2015) and the same copy mechanism as See et al.”
Get To The Point: Summarization with Pointer-Generator Networks
See, A., Liu, P. J., & Manning, C. D. (2017) · Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p17-1099 · Cited by 3,775
Convolutional Sequence to Sequence Learning
Gehring, J., Auli, M., Grangier, D., Yarats, D., & Dauphin, Y. N. (2017) · arXiv · doi:10.48550/arxiv.1705.03122 · Cited by 2,850 · cited 1×
“Therefore, all types of decoder can be used, such as Recurrent Neural Networks (RNNs) [57], Transformers [67], and Convolu-tional Neural Networks [16].”
OpenNMT: Open-Source Toolkit for Neural Machine Translation
Klein, G., Kim, Y., Deng, Y., Senellart, J., & Rush, A. (2017) · Proceedings of ACL 2017, System Demonstrations · doi:10.18653/v1/p17-4012 · Cited by 1,749
Stanza: A Python Natural Language Processing Toolkit for Many Human Languages
Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations · doi:10.18653/v1/2020.acl-demos.14 · Cited by 1,431
A Persona-Based Neural Conversation Model
Li, J., Galley, M., Brockett, C., Spithourakis, G., Gao, J., & Dolan, B. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1094 · Cited by 898 · cited 2×
“(2) Unlike previous CTG approaches [32, 60, 11, 12] which propose instance-level control factors, the control of the hallucination factor is performed at the word-level to enable finer-grained signal to be sent to the model.”
Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems
Wen, T.-H., Gasic, M., Mrkšić, N., Su, P.-H., Vandyke, D., & Young, S. (2015) · Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d15-1199 · Cited by 874
Gatt, A., & Krahmer, E. (2018) · Journal of Artificial Intelligence Research · doi:10.1613/jair.5477 · Cited by 776
Evaluating the Factual Consistency of Abstractive Text Summarization
Kryscinski, W., McCann, B., Xiong, C., & Socher, R. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.750 · Cited by 669
Building applied natural language generation systems
REITER, E., & DALE, R. (1997) · Natural Language Engineering · doi:10.1017/s1351324997001502 · Cited by 631
Flesch, R. (1950) · Stanford Law Review · doi:10.2307/1225957 · Cited by 529
Challenges in Data-to-Document Generation
Wiseman, S., Shieber, S., & Rush, A. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1239 · Cited by 524 · cited 9×
“Based on the now-standard encoder-decoder architecture, with attention and copy mechanisms [1, 59], neural methods for DTG are able to produce fluent text conditioned on structured data in a number of domains [29, 70, 50], without relying on heavy manual work from field experts.”
InfluentialStanza: A Python Natural Language Processing Toolkit for Many Human Languages
Qi, P., Zhang, Y., Zhang, Y., Bolton, J., & Manning, C. D. (2020) · arXiv · doi:10.48550/arxiv.2003.07082 · Cited by 476
Neural Text Generation from Structured Data with Application to the Biography Domain
Lebret, R., Grangier, D., & Auli, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1128 · Cited by 444
(2017) · doi:10.18653/v1/p17-1017 · Cited by 436 · cited 2×
“In particular, surface-realization abilities have been well studied on hand-crafted datasets such as E2E [43] and WebNLG [14], while content-selection has been addressed by automatically constructed dataset such as WikiBio [29] or RotoWire [70].”
Why We Need New Evaluation Metrics for NLG
Novikova, J., Dušek, O., Cercas Curry, A., & Rieser, V. (2017) · Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d17-1238 · Cited by 422
Why We Need New Evaluation Metrics for NLG
Novikova, J., Dušek, O., Curry, A. C., & Rieser, V. (2017) · arXiv · doi:10.48550/arxiv.1707.06875 · Cited by 406
A Structured Review of the Validity of BLEU
Reiter, E. (2018) · Computational Linguistics · doi:10.1162/coli_a_00322 · Cited by 386
Bootstrapping parsers via syntactic projection across parallel texts
HWA, R., RESNIK, P., WEINBERG, A., CABEZAS, C., & KOLAK, O. (2005) · Natural Language Engineering · doi:10.1017/s1351324905003840 · Cited by 340
Automatic generation of textual summaries from neonatal intensive care data
Portet, F., Reiter, E., Gatt, A., Hunter, J., Sripada, S., Freer, Y., & Sykes, C. (2009) · Artificial Intelligence · doi:10.1016/j.artint.2008.12.002 · Cited by 315
Controlling Politeness in Neural Machine Translation via Side Constraints
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1005 · Cited by 273
Controlling Linguistic Style Aspects in Neural Language Generation
Ficler, J., & Goldberg, Y. (2017) · Proceedings of the Workshop on Stylistic Variation · doi:10.18653/v1/w17-4912 · Cited by 265 · cited 3×
“Interestingly, one can view DTG models as Controlled Text Generation (CTG) ones focused on controlling content, as most CTG techniques condition the generation on several key-value pairs of control factors (e.g. tone, tense, length) [8, 19, 11].”
ToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.89 · Cited by 252
ToTTo: A Controlled Table-To-Text Generation Dataset
Parikh, A. P., Wang, X., Gehrmann, S., Faruqui, M., Dhingra, B., Yang, D., & Das, D. (2020) · arXiv · doi:10.48550/arxiv.2004.14373 · Cited by 252 · cited 3×
“We also test our framework on ToTTo [45], in which models are trained with noisy reference texts, and evaluated on references reviewed and cleaned by human annotators to ensure accuracy.”
BackgroundMethodInfluentialTable-to-Text Generation by Structure-Aware Seq2seq Learning
Liu, T., Wang, K., Sha, L., Chang, B., & Sui, Z. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11925 · Cited by 242
What to talk about and how? Selective Generation using LSTMs with Coarse-to-Fine Alignment
Mei, H., Bansal, M., & Walter, M. R. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1086 · Cited by 237 · cited 1×
“In recent years, neural models have blurred this distinction: various approaches showed that both content selection and surface realization can be learned in an end-to-end, data-driven fashion (Mei et al. 2016; Liu et al. 2019a; Roberti et al. 2019; Puduppully et al. 2019a).”
Controlling Output Length in Neural Encoder-Decoders
Kikuchi, Y., Neubig, G., Sasano, R., Takamura, H., & Okumura, M. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1140 · Cited by 222 · cited 1×
“…a language model’s output during inference on a number of desired attributes, or control factors , such as the identity of the speaker in a dialog setting [32], the politeness of the generated text or the text length in machine-translation [60, 24], or the tense in generated movie reviews [19].”
The E2E Dataset: New Challenges For End-to-End Generation
Novikova, J., Dušek, O., & Rieser, V. (2017) · Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue · doi:10.18653/v1/w17-5525 · Cited by 220
Best practices for the human evaluation of automatically generated text
van der Lee, C., Gatt, A., van Miltenburg, E., Wubben, S., & Krahmer, E. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8643 · Cited by 205 · cited 1×
“Finally, we perform qualitative evaluations of the results obtained on WikiBIO and ToTTo, following the best practices outlined by van der Lee et al. [30].”
Reiter, E., & Belz, A. (2009) · Computational Linguistics · doi:10.1162/coli.2009.35.4.35405 · Cited by 196
A Systematic Comparison of Smoothing Techniques for Sentence-Level BLEU
Chen, B., & Cherry, C. (2014) · Proceedings of the Ninth Workshop on Statistical Machine Translation · doi:10.3115/v1/w14-3346 · Cited by 191 · cited 1×
“For the automatic analysis, we use five metrics: – BLEU [44] is a length-penalized precision score over n -grams, n ∈ 1 , 4 , optionally improved with a smoothing technique [4].”
Learning to Generate Product Reviews from Attributes
Dong, L., Huang, S., Wei, F., Lapata, M., Zhou, M., & Xu, K. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers · doi:10.18653/v1/e17-1059 · Cited by 190 · cited 1×
“Interestingly, one can view DTG models as Controlled Text Generation (CTG) ones focused on controlling content, as most CTG techniques condition the generation on several key-value pairs of control factors (e.g. tone, tense, length) [8, 19, 11].”
Learning Neural Templates for Text Generation
Wiseman, S., Shieber, S., & Rush, A. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1356 · Cited by 184 · cited 2×
“– hsmm [61], an encoder-decoder model with a multi-branch decoder.”
Borensztajn, G., Zuidema, W., & Bod, R. (2009) · Topics in Cognitive Science · doi:10.1111/j.1756-8765.2008.01009.x · Cited by 163 · cited 1×
“According to the already stated assumption (2) – words inside the same statement should have the same score – , we first split the sentence y into statements y t i : t i +1 − 1 , via dependency parsing and its rule-based conversion to constituency trees [18, 73, 20, 3].”
Handling Divergent Reference Texts when Evaluating Table-to-Text Generation
Dhingra, B., Faruqui, M., Parikh, A., Chang, M.-W., Das, D., & Cohen, W. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1483 · Cited by 150 · cited 10×
“This dataset has been automatically built from the Internet; concerning divergences, 62% of the references mention extra information not grounded by the table [7].”
InfluentialText-to-Text Pre-Training for Data-to-Text Tasks
Kale, M., & Rastogi, A. (2020) · Proceedings of the 13th International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.14 · Cited by 138
Smeuninx, N., Clerck, B. D., & Aerts, W. (2016) · International Journal of Business Communication · doi:10.1177/2329488416675456 · Cited by 134
Toward Controlled Generation of Text
Hu, Z., Yang, Z., Liang, X., Salakhutdinov, R., & Xing, E. P. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.00955 · Cited by 119 · cited 2×
“Interestingly, one can view DTG models as Controlled Text Generation (CTG) ones focused on controlling content, as most CTG techniques condition the generation on several key-value pairs of control factors (e.g. tone, tense, length) [8, 19, 11].”
Few-Shot NLG with Pre-Trained Language Model
Chen, Z., Eavani, H., Chen, W., Liu, Y., & Wang, W. Y. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.18 · Cited by 116
Data-to-text Generation with Entity Modeling
Puduppully, R., Dong, L., & Lapata, M. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1195 · Cited by 113 · cited 1×
“Based on the now-standard encoder-decoder architecture, with attention and copy mechanisms [1, 59], neural methods for DTG are able to produce fluent text conditioned on structured data in a number of domains [29, 70, 50], without relying on heavy manual work from field experts.”
Converting dependency structures to phrase structures
Xia, F., & Palmer, M. S. (2001) · International Conference on Human Language Technology Research · doi:10.3115/1072133.1072147 · Cited by 113 · cited 1×
“According to the assumption that words inside the same statement should have the same score, we first split the sentence y into statements yti:ti+1−1, via dependency parsing and its rule-based conversion to constituency trees [16, 63, 18, 2].”
BackgroundData-Driven News Generation for Automated Journalism
Leppänen, L., Munezero, M., Granroth-Wilding, M., & Toivonen, H. (2017) · Proceedings of the 10th International Conference on Natural Language Generation · doi:10.18653/v1/w17-3528 · Cited by 97
Semantic Noise Matters for Neural Natural Language Generation
Dušek, O., Howcroft, D. M., & Rieser, V. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8652 · Cited by 85 · cited 3×
“Indeed, rule-based [9] or neural-based methods [41] have been proposed, specifically with table regularization techniques, where attributes are added or removed to re-align table and target descrip-Controlling tion.”
Controlled Hallucinations: Learning to Generate Faithfully from Noisy Data
Filippova, K. (2020) · Findings of the Association for Computational Linguistics: EMNLP 2020 · doi:10.18653/v1/2020.findings-emnlp.76 · Cited by 79
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation
Juraska, J., Karagiannis, P., Bowden, K., & Walker, M. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1014 · Cited by 75 · cited 2×
“2019) or hand crafted rules (Juraska et al. 2018) can help to reduce hallucinations.”
End-to-End Content and Plan Selection for Data-to-Text Generation
Gehrmann, S., Dai, F., Elder, H., & Rush, A. (2018) · Proceedings of the 11th International Conference on Natural Language Generation · doi:10.18653/v1/w18-6505 · Cited by 70 · cited 2×
“…Juraska et al. [21] leverage templating and hand-crafted rules to re-rank the top outputs of a model decoding via beam search; Gehrmann et al. [17] also leverage the possible templating formats of E2E’s reference texts, and train an ensemble of decoders where each decoder is associated to one…”
A Simple Recipe towards Reducing Hallucination in Neural Surface Realisation
Nie, F., Yao, J.-G., Wang, J., Pan, R., & Lin, C.-Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1256 · Cited by 68 · cited 2×
“Indeed, rule-based [9] or neural-based methods [41] have been proposed, specifically with table regularization techniques, where attributes are added or removed to re-align table and target descrip-Controlling tion.”
Sticking to the Facts: Confident Decoding for Faithful Data-to-Text Generation
Tian, R., Narayan, S., Sellam, T., & Parikh, A. P. (2019) · arXiv · doi:10.48550/arxiv.1910.08684 · Cited by 60 · cited 1×
“[58]), we asked 16 annotators to annotate a bigger sample of 300 instances (where each instance consists of one table and four associated outputs), as Liu et al.”
Liu, T., Luo, F., Xia, Q., Ma, S., Chang, B., & Sui, Z. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016786 · Cited by 53 · cited 3×
“Based on the literature review, the lack of model control can be evidenced when loss modification methods are used [68, 34, 52], although these approaches can be efficient and transposed from one domain to another.”
BackgroundMethodNeural Data-to-Text Generation via Jointly Learning the Segmentation and Correspondence
Shen, X., Chang, E., Su, H., Niu, C., & Klakow, D. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.641 · Cited by 44
Han, C., Lavoie, B., Palmer, M. S., Rambow, O., Kittredge, R. I., Korelsky, T., Kim, N., & Kim, M. (2000) · Lecture notes in computer science · doi:10.1007/3-540-39965-8_5 · Cited by 38
Revisiting Challenges in Data-to-Text Generation with Fact Grounding
Wang, H. (2019) · Proceedings of the 12th International Conference on Natural Language Generation · doi:10.18653/v1/w19-8639 · Cited by 34 · cited 5×
“Similarly to the coverage constraints, a reconstruction loss has proven only marginally efficient in these settings, as it contradicts the content selection task [68], and needs to be well calibrated using expert insight in order to bring improvements.”
InfluentialPartTUT: The Turin University Parallel Treebank
Sanguinetti, M., & Bosco, C. (2015) · Studies in computational intelligence · doi:10.1007/978-3-319-14206-7_3 · Cited by 32 · cited 1×
“2019) on the UD English ParTUT dataset (Sanguinetti and Bosco 2015); Stanza (Qi et al.”
Data-to-Text Generation with Style Imitation
Lin, S., Wang, W., Yang, Z., Liang, X., Xu, F. F., Xing, E. P., & Hu, Z. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.144 · Cited by 31
Twitter User Profiling: Bot and Gender Identification
Kosmajac, D., & Kešelj, V. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58219-7_13 · Cited by 30 · cited 1×
“– The classic readability Flesch index (Flesch 1962), which is based on words per sentence and syllables per word, and is still used as a standard benchmark (Kosmajac and Keselj 2019; Smeuninx et al. 2020; Stajner and Hulpus 2020; Stajner et al. 2020).”
MethodText-to-Text Pre-Training for Data-to-Text Tasks
Kale, M., & Rastogi, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.10433 · Cited by 29 · cited 1×
“In this direction, adapting the work of [5, 22] to our model could bring improvements to the results presented in this paper.”
Analysing Data-To-Text Generation Benchmarks
Perez-Beltrachini, L., & Gardent, C. (2017) · Proceedings of the 10th International Conference on Natural Language Generation · doi:10.18653/v1/w17-3537 · Cited by 27 · cited 2×
“They were not constructed by human annotators, but rather created from Internet sources, and consist of loosely aligned table-reference pairs: in Wik-iBio, almost two thirds of the training instances contain divergences [7], and no instance has a 1-to-1 source-target alignment [46].”
(2019) · doi:10.1609/aaai.v33i01.33016908 · Cited by 26
Towards NLG for Physiological Data Monitoring with Body Area Networks
Banaee, H., Ahmed, M. U., & Loutfi, A. (2013) · DiVA (Digitala Vetenskapliga Arkivet) · Cited by 25
Data-to-Text Generation with Iterative Text Editing
Kasner, Z., & Dušek, O. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.9 · Cited by 25
Deep Learning Approaches to Text Production
Narayan, S., & Gardent, C. (2020) · Synthesis lectures on human language technologies · doi:10.2200/s00979ed1v01y201912hlt044 · Cited by 22
Towards Comprehensive Description Generation from Factual Attribute-value Tables
Liu, T., Luo, F., Yang, P., Wu, W., Chang, B., & Sui, Z. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1600 · Cited by 20 · cited 3×
“Regarding RL, Perez-Beltrachini and Lapata [47] build an instance-level reward which sums up word-level scores; Liu et al. [35] pro-pose a reward based on document frequency to favor words from the source table more than rare words; and Rebuffel et al. [52] train a network with a variant of PARENT…”
Copy Mechanism and Tailored Training for Character-Based Data-to-Text Generation
Roberti, M., Bonetta, G., Cancelliere, R., & Gallinari, P. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-46147-8_39 · Cited by 16 · cited 1×
“In recent years, neural models have blurred this distinction: various approaches showed that both content selection and surface realization can be learned in an end-to-end, data-driven fashion [38, 34, 56, 49].”
BackgroundSelf-citationRebuffel, C., Soulier, L., Scoutheeten, G., & Gallinari, P. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.18 · Cited by 10
Self-citationCoCo: A Tool for Automatically Assessing Conceptual Complexity of Texts.
Štajner, S., Nisioi, S., & Hulpuş, I. (2020) · MADOC (University of Mannheim) · Cited by 8
Copy Mechanism and Tailored Training for character-based data-to-text generation
Roberti, M., Bonetta, G., Cancelliere, R., & Gallinari, P. (2019) · Institutional Research Information System University of Turin (University of Turin) · Cited by 7
Self-citationDeep Learning Approaches to Text Production
Gardent, C., & Narayan, S. (2018) · doi:10.18653/v1/n18-6002 · Cited by 6
Štajner, S., & Hulpuş, I. (2020) · MADOC (University of Mannheim) · Cited by 6
Studying the Impact of Filling Information Gaps on the Output Quality of Neural Data-to-Text
Thomson, C., Zhao, Z., & Sripada, S. G. (2020) · International Conference on Natural Language Generation · doi:10.18653/v1/2020.inlg-1.6 · Cited by 5
Data-to-Text Generation with Iterative Text EditingPreprint
Kasner, Z., & Dušek, O. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2011.01694 · Cited by 2 · cited 1×
“…search; Gehrmann et al. [17] also leverage the possible templating formats of E2E’s reference texts, and train an ensemble of decoders where each decoder is associated to one template; and Kasner and Dusek [23] produce template-based lexicalizations and improve them via a sentence fusion model.”
Research works printed but not linked: 4
- Bahdanau D, Cho K, Bengio Y (2015) Neural machine translation by jointly learning to align and translate. In: ICLR
- Ferreira TC, van der Lee C, van Miltenburg E, Krahmer E (2019) Neural data-to-text generation: A comparison between pipeline and end-to-end architectures. In: EMNLP-IJCNLP
- Perez-Beltrachini L, Lapata M (2018) Bootstrapping generators from noisy data. In: NAACL-HLT · DOI
- Puduppully R, Dong L, Lapata M (2019b) Data-to-text generation with entity modeling. In: ACL · DOI · Paper page
Cited by
Survey of Hallucination in Natural Language Generation
Ji, Z., Lee, N., Frieske, R., Yu, T., Su, D., Xu, Y., Ishii, E., Bang, Y. J., Madotto, A., & Fung, P. (2023) · ACM Computing Surveys · doi:10.1145/3571730 · Cited by 5,025
“, parts of the target sentence are loyal to the source input, while others diverge [110].”
BackgroundInfluentialSiren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Xu, C., et al. (2023) · arXiv · doi:10.48550/arxiv.2309.01219 · Cited by 544
“Examples include the multi-branch decoder (Rebuffel et al., 2022) and the uncertainty-aware decoder (Xiao and Wang, 2021).”
Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models
Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., Chen, Y., et al. (2025) · Computational Linguistics · doi:10.1162/coli.a.16 · Cited by 534
“Examples include the multi-branch decoder (Rebuffel et al., 2022) and the uncertainty-aware decoder (Xiao and Wang, 2021).”
Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code
Liu, F., Liu, Y., Shi, L., Yang, Z., Zhang, L., Lian, X., Li, Z., & Ma, Y. (2024) · arXiv · doi:10.48550/arxiv.2404.00971 · Cited by 188
“…advanced training techniques ( e.g. reinforcement learning [56]), improved decoding strategies [10], [38], model architecture optimization [42], [60], and multi-agent interaction [14], as well as leveraging external tools for knowledge retrieval and fact-checking [75], [78], are also worthwhile…”
Wang, Y., Pan, Y., Su, Z., Deng, Y., Zhao, Q., Du, L., Luan, T. H., Kang, J., & Niyato, D. (2026) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2025.3576176 · Cited by 68
“Multi-branch decoder [208] and uncertainty-aware decoder [209] are two examples of modified decoder structures to mitigate hallucinations.”
Metadata
- Authors
- Rebuffel, C., Roberti, M., Soulier, L., Scoutheeten, G., Cancelliere, R., & Gallinari, P.
- Affiliations
- University of Turin (IT)
- Centre National de la Recherche Scientifique (FR)
- BNP Paribas (France) (FR)
- Corresponding author
- Roberti, Marco
- Venue
- Data Mining and Knowledge Discovery
- Published
- 2021-10-22
- Volume
- 36
- Issue
- 1
- Pages
- 318-354
- ISSN
- 1384-5810 (ISSN-L)
- 1573-756X
- OpenAlex
- W3127986942
- Semantic Scholar
- 0368a16887369a56d9abb41ae8d697d4691a2021
- Cited by
- 50
- References
- 77
- Citations by year
- 2026: 5 · 2025: 14 · 2024: 4 · 2023: 15 · 2022: 9 · 2021: 3
- FWCI
- 2.71
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Data Mining and Knowledge Discovery (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- Institutional Research Information System University of Turin (University of Turin) (submittedVersion, cc-by)
- HAL (submittedVersion)
- arXiv (Cornell University)
- Funders
- Horizon2020 AI4EU (825619)
- ANR JCJC SESAMS (ANR-18-CE23-0001)
- Istituto Nazionale di Alta Matematica “Francesco Severi”
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
- Keywords
- data-to-text generation, hallucination mitigation, co-occurrence analysis, dependency parsing, noisy training data
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
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.