pith. sign in

arxiv: 2606.01964 · v1 · pith:L2ABM2KMnew · submitted 2026-06-01 · 💻 cs.CL

Eyettention II: A Dual-Sequence Architecture for Modeling Fixation Location, Within-Word Landing Position, and Fixation Duration in Reading

Shuwen Deng , Cui Ding , David R. Reich , Paul Prasse , Lena A. J\"ager This is my paper

Pith reviewed 2026-06-28 15:10 UTC · model grok-4.3

classification 💻 cs.CL
keywords eye trackingscanpath predictionreadingfixation durationdeep learningpsycholinguisticsgaze modelingneural sequence model
0
0 comments X

The pith

Eyettention II generates complete reading scanpaths with fixation locations, landing positions, and durations using a dual-sequence architecture.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper presents Eyettention II as an end-to-end deep learning model that produces chronological sequences of eye fixations during reading. It addresses the difficulty of collecting large eye-tracking datasets by generating synthetic data that can support natural language processing tasks and psycholinguistic studies. The model is shown to exceed previous systems on standard prediction metrics while reproducing established patterns of human gaze behavior tied to text properties.

Core claim

Eyettention II is an end-to-end trained deep-learning model capable of generating realistic scanpaths consisting of a complete set of fixation attributes in chronological order, including fixation location, within-word landing position, and fixation duration. The model is lightweight and closely aligned with cognitive theories of reading.

What carries the argument

Dual-sequence architecture that processes the text sequence alongside the accumulating eye-movement sequence to predict each next fixation's attributes.

If this is right

  • Generated scanpaths can augment scarce eye-tracking datasets for training other language models.
  • The model can support piloting of experimental materials in psycholinguistics without recruiting participants.
  • Applications that rely on gaze data, such as reader-characteristic inference, become feasible at larger scale.
  • The approach may allow systematic exploration of reading behavior under controlled text variations.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the scanpaths prove realistic, the model could be used to simulate reading in populations or conditions where direct data collection is impractical.
  • The dual-sequence design might extend naturally to modeling eye movements in other sequential tasks such as visual search or scene viewing.
  • Combining the generator with existing language models could produce gaze-augmented training data for multimodal systems.

Load-bearing premise

Quantitative gains on scanpath metrics plus reproduction of a small set of known psycholinguistic effects are enough to establish that the generated sequences are realistic models of human reading.

What would settle it

New eye-tracking recordings on held-out texts that test whether the model reproduces additional, previously unexamined psycholinguistic effects or matches human distributions on metrics not used during training.

read the original abstract

The way our eyes move while reading provides valuable insights into both the reader's cognitive processes and the properties of the text. In particular, eye-tracking-while-reading data has shown to be highly beneficial in various technological applications, such as enhancing and interpreting language models and inferring a reader's characteristics. However, these applications often rely on large-scale, data-driven models, which demand extensive eye-tracking datasets that are challenging to obtain due to the resource-intensive nature of data collection. To address the challenge of data scarcity, we develop Eyettention II, an end-to-end trained deep-learning model capable of generating realistic scanpaths consisting of a complete set of fixation attributes in chronological order, including fixation location, within-word landing position, and fixation duration. Our model is lightweight, efficiently trainable on limited GPU resources, and closely aligned with cognitive theories. We demonstrate that Eyettention II surpasses state-of-the-art models in scanpath prediction and mirrors human-like gaze behavior by capturing key psycholinguistic phenomena. With its robust performance, Eyettention II holds the potential to drive advancements in natural language processing, facilitate piloting the materials of psycholinguistic experiments, and uncover new insights beyond what is explicitly encoded in theoretical cognitive models.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 0 minor

Summary. The manuscript introduces Eyettention II, a dual-sequence deep neural network for generating complete reading scanpaths that jointly model fixation location, within-word landing position, and fixation duration in chronological order. The authors claim the model is lightweight and end-to-end trainable on limited resources, surpasses prior state-of-the-art scanpath models on standard metrics, reproduces several known psycholinguistic effects, and is closely aligned with cognitive theories of reading.

Significance. If the superiority claims and the asserted cognitive alignment hold after proper controls, the work could help mitigate data scarcity in eye-tracking research and support downstream applications in NLP and experimental psycholinguistics. The dual-sequence design that outputs multiple fixation attributes simultaneously is a potentially useful architectural contribution.

major comments (2)
  1. [Abstract] Abstract: the claim that the model is 'closely aligned with cognitive theories' is load-bearing for the paper's positioning yet rests only on reproduction of known psycholinguistic phenomena and higher scanpath metrics; no control comparison against a non-cognitive baseline that matches the same marginal statistics is described, leaving open the possibility that any sufficiently expressive model trained on the same corpora would exhibit the same behavior by construction.
  2. [Abstract] Abstract: the central performance claims are evaluated on the same eye-tracking corpora used for training without mention of held-out test sets, data splits, or statistical tests for superiority; this makes it impossible to rule out data leakage or post-hoc metric selection as explanations for the reported gains.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on the abstract's positioning and evaluation details. We address each comment below and revise the manuscript to improve clarity and transparency.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim that the model is 'closely aligned with cognitive theories' is load-bearing for the paper's positioning yet rests only on reproduction of known psycholinguistic phenomena and higher scanpath metrics; no control comparison against a non-cognitive baseline that matches the same marginal statistics is described, leaving open the possibility that any sufficiently expressive model trained on the same corpora would exhibit the same behavior by construction.

    Authors: We agree that stronger evidence would require a control comparison to a non-cognitive baseline. The current support for the claim derives from the model's reproduction of specific, theoretically predicted psycholinguistic effects (e.g., word-length effects on landing positions) rather than generic marginal statistics. The dual-sequence architecture itself draws from cognitive distinctions between spatial and temporal processing in reading models. To address the concern directly, we will revise the abstract to qualify the claim as 'captures key psycholinguistic phenomena consistent with cognitive theories of reading' and add a limitations paragraph noting the absence of such a baseline comparison. revision: yes

  2. Referee: [Abstract] Abstract: the central performance claims are evaluated on the same eye-tracking corpora used for training without mention of held-out test sets, data splits, or statistical tests for superiority; this makes it impossible to rule out data leakage or post-hoc metric selection as explanations for the reported gains.

    Authors: We apologize for the lack of explicit mention in the abstract. The full manuscript reports evaluations on held-out test portions of the corpora using standard splits, with statistical tests for performance differences. We will revise the abstract to state that results are reported on held-out test sets with statistical significance testing, thereby clarifying the evaluation protocol and ruling out the concerns raised. revision: yes

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper presents a standard end-to-end trained neural architecture for scanpath generation whose central claims rest on empirical performance comparisons against prior models on eye-tracking corpora. No equations, parameter fittings, or self-citations are shown that reduce any claimed prediction or theoretical alignment to an input by construction; evaluation on held-out data (standard in the domain) constitutes genuine out-of-sample prediction rather than tautological reproduction. The reproduction of known psycholinguistic effects is an empirical outcome of training, not a definitional or self-citation loop that forces the result.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The model is a standard deep neural network whose parameters are learned from eye-tracking corpora; no new physical or cognitive entities are postulated, but the claim of cognitive alignment rests on the untested assumption that matching a handful of aggregate statistics implies mechanistic fidelity.

free parameters (1)
  • neural network weights and hyperparameters
    All model parameters are fitted to eye-tracking data; their number and specific values are not reported in the abstract.
axioms (1)
  • domain assumption Eye-movement sequences during reading can be usefully modeled as the output of a dual-sequence recurrent or transformer architecture trained on existing corpora.
    This modeling choice is the foundation of the architecture and is not derived from first principles.

pith-pipeline@v0.9.1-grok · 5770 in / 1402 out tokens · 20825 ms · 2026-06-28T15:10:55.243621+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

100 extracted references · 4 canonical work pages · 3 internal anchors

  1. [1]

    Psychological Bulletin124(3), 372–422 (1998)

    Rayner, K.: Eye movements in reading and information processing: 20 years of research. Psychological Bulletin124(3), 372–422 (1998)

    1998

  2. [2]

    Quarterly Journal of Experimental Psychology62(8), 1457–1506 (2009)

    Rayner, K.: The 35th Sir Frederick Bartlett Lecture: Eye movements and attention in reading, scene perception, and visual search. Quarterly Journal of Experimental Psychology62(8), 1457–1506 (2009)

    2009

  3. [3]

    The Behavioral and Brain Sciences26, 445–526 (2003)

    Reichle, E., Rayner, K., A, P.: The E-Z reader model of eye-movement control in reading: comparisons to other models. The Behavioral and Brain Sciences26, 445–526 (2003)

    2003

  4. [4]

    Vision Research42(5), 621–636 (2002)

    Engbert, R., Longtin, A., Kliegl, R.: A dynamical model of saccade generation in reading based on spatially distributed lexical processing. Vision Research42(5), 621–636 (2002)

    2002

  5. [5]

    Topics in Cognitive Science5(3), 452–474 (2013)

    Engelmann, F., Vasishth, S., Engbert, R., Kliegl, R.: A framework for modeling the interaction of syntactic processing and eye movement control. Topics in Cognitive Science5(3), 452–474 (2013)

    2013

  6. [6]

    In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Berlin, Germany, pp

    Barrett, M., Bingel, J., Keller, F., Søgaard, A.: Weakly supervised part-of-speech tagging using eye-tracking data. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL), Berlin, Germany, pp. 579–584 (2016)

    2016

  7. [7]

    In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, Berlin, Germany, pp

    Mishra, A., Kanojia, D., Nagar, S., Dey, K., Bhattacharyya, P.: Leveraging 33 cognitive features for sentiment analysis. In: Proceedings of the 20th SIGNLL Conference on Computational Natural Language Learning, Berlin, Germany, pp. 156–166 (2016)

    2016

  8. [8]

    In: Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, Minnesota, pp

    Hollenstein, N., Zhang, C.: Entity recognition at first sight: Improving NER with eye movement information. In: Proceedings of North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), Minneapolis, Minnesota, pp. 1–10 (2019)

    2019

  9. [9]

    In: Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL), Brussels, Belgium, pp

    Barrett, M., Bingel, J., Hollenstein, N., Rei, M., Søgaard, A.: Sequence clas- sification with human attention. In: Proceedings of the 22nd Conference on Computational Natural Language Learning (CoNLL), Brussels, Belgium, pp. 302–312 (2018)

    2018

  10. [10]

    In: Proceedings of the Conference on Neural Information Processing Systems, vol

    Sood, E., Tannert, S., M¨ uller, P., Bulling, A.: Improving natural language pro- cessing tasks with human gaze-guided neural attention. In: Proceedings of the Conference on Neural Information Processing Systems, vol. 33. Online, pp. 6327–6341 (2020)

    2020

  11. [11]

    In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, pp

    Sood, E., K¨ ogel, F., M¨ uller, P., Thomas, D., Bˆ ace, M., Bulling, A.: Multimodal integration of human-like attention in visual question answering. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada, pp. 2648–2658 (2023)

    2023

  12. [12]

    Springer, Cham (2023)

    Beinborn, L., Hollenstein, N.: Cognitive Plausibility in Natural Language Processing. Springer, Cham (2023)

    2023

  13. [13]

    In: Proceedings of the 24th Conference on Computational Natural Language Learning, Online, pp

    Sood, E., Tannert, S., Frassinelli, D., Bulling, A., Vu, N.T.: Interpreting atten- tion models with human visual attention in machine reading comprehension. In: Proceedings of the 24th Conference on Computational Natural Language Learning, Online, pp. 12–25 (2020)

    2020

  14. [14]

    In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, pp

    Hollenstein, N., Pirovano, F., Zhang, C., J¨ ager, L., Beinborn, L.: Multilingual language models predict human reading behavior. In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, pp. 106–123 (2021)

    2021

  15. [15]

    In: Proceedings of the Workshop on the Cognitive Aspects of the Lexicon, AACL, Online (2022)

    Hollenstein, N., Gonzalez-Dios, I., Beinborn, L., J¨ ager, L.A.: Patterns of text readability in human and predicted eye movements. In: Proceedings of the Workshop on the Cognitive Aspects of the Lexicon, AACL, Online (2022)

    2022

  16. [16]

    12–22 (2021)

    Merkx, D., Frank, S.L.: Human sentence processing: recurrence or attention? In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, Online, pp. 12–22 (2021)

    2021

  17. [17]

    In: Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, pp

    Deng, S., Prasse, P., Reich, D.R., Dziemian, S., Stegenwallner-Sch¨ utz, M., Krakowczyk, D., Makowski, S., Langer, N., Scheffer, T., J¨ ager, L.A.: Detection 34 of ADHD based on eye movements during natural viewing. In: Proceedings of the European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 403–418. Springer, Grenoble, France (2022)

    2022

  18. [18]

    Array12, 100087 (2021)

    Raatikainen, P., Hautala, J., Loberg, O., K¨ arkk¨ ainen, T., Lepp¨ anen, P., Niem- inen, P.: Detection of developmental dyslexia with machine learning using eye movement data. Array12, 100087 (2021)

    2021

  19. [19]

    In: Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), Abu Dhabi, United Arab Emirates (Virtual), pp

    Haller, P., S¨ auberli, A., Kiener, S., Pan, J., Yan, M., J¨ ager, L.: Eye-tracking based classification of Mandarin Chinese readers with and without dyslexia using neural sequence models. In: Proceedings of the Workshop on Text Simplification, Accessibility, and Readability (TSAR-2022), Abu Dhabi, United Arab Emirates (Virtual), pp. 111–118 (2022)

    2022

  20. [20]

    In: Proceedings of the 2022 Symposium on Eye Tracking Research and Applications

    Reich, D.R., Prasse, P., Tschirner, C., Haller, P., Goldhammer, F., J¨ ager, L.A.: Inferring native and non-native human reading comprehension and subjective text difficulty from scanpaths in reading. In: Proceedings of the 2022 Symposium on Eye Tracking Research and Applications. ETRA ’22, vol. 23. Seattle, WA, USA (2022)

    2022

  21. [21]

    In: Proceedings of the 2020 Symposium on Eye Tracking Research and Applications, Stuttgart, Germany, pp

    Ahn, S., Kelton, C., Balasubramanian, A., Zelinsky, G.: Towards predicting read- ing comprehension from gaze behavior. In: Proceedings of the 2020 Symposium on Eye Tracking Research and Applications, Stuttgart, Germany, pp. 1–5 (2020)

    2020

  22. [22]

    Berzak, Y., Katz, B., Levy, R.: Assessing language proficiency from eye move- ments in reading. In: Proceedings of the 17th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, New Orleans, Louisiana, pp. 1986–1996 (2018)

    1986

  23. [23]

    In: Proceedings of the 39th Conference on Neural Information Processing Systems (2025)

    Shubi, O., Reich, D.R., Gruteke Klein, K., Angel, Y., Prasse, P., J¨ ager, L.A., Berzak, Y.: EyeBench: Predictive modeling from eye movements in reading. In: Proceedings of the 39th Conference on Neural Information Processing Systems (2025)

    2025

  24. [24]

    In: Proceed- ings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, pp

    Khurana, V., Kumar, Y., Hollenstein, N., Kumar, R., Krishnamurthy, B.: Synthesizing human gaze feedback for improved NLP performance. In: Proceed- ings of the 17th Conference of the European Chapter of the Association for Computational Linguistics, Dubrovnik, Croatia, pp. 1895–1908 (2023)

    1908

  25. [25]

    In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, pp

    Deng, S., Prasse, P., Reich, D., Scheffer, T., J¨ ager, L.: Pre-trained language mod- els augmented with synthetic scanpaths for natural language understanding. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, pp. 6500–6507 (2023)

    2023

  26. [26]

    In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 35 Papers), Bangkok, Thailand, pp

    Deng, S., Prasse, P., Reich, D., Scheffer, T., J¨ ager, L.: Fine-tuning pre-trained language models with gaze supervision. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short 35 Papers), Bangkok, Thailand, pp. 217–224 (2024)

    2024

  27. [27]

    In: Proceedings of the 2024 Joint International Conference on Com- putational Linguistics, Language Resources and Evaluation (LREC-COLING), Torino, Italia, pp

    Reich, D.R., Deng, S., Bj¨ ornsd´ ottir, M., J¨ ager, L., Hollenstein, N.: Reading does not equal reading: Comparing, simulating and exploiting reading behavior across populations. In: Proceedings of the 2024 Joint International Conference on Com- putational Linguistics, Language Resources and Evaluation (LREC-COLING), Torino, Italia, pp. 13586–13594 (2024)

    2024

  28. [28]

    PeerJ5, 3544 (2017)

    Amrhein, V., Korner-Nievergelt, F., Roth, T.: The earth is flat (p¿ 0.05): significance thresholds and the crisis of unreplicable research. PeerJ5, 3544 (2017)

    2017

  29. [29]

    Science349(6251), 4716 (2015)

    Collaboration, O.S.: Estimating the reproducibility of psychological science. Science349(6251), 4716 (2015)

    2015

  30. [30]

    Journal of Memory and Language111, 104063 (2020)

    J¨ ager, L.A., Mertzen, D., Van Dyke, J.A., Vasishth, S.: Interference patterns in subject-verb agreement and reflexives revisited: A large-sample study. Journal of Memory and Language111, 104063 (2020)

    2020

  31. [31]

    Journal of Memory and Language103, 151–175 (2018)

    Vasishth, S., Mertzen, D., J¨ ager, L.A., Gelman, A.: The statistical significance filter leads to overoptimistic expectations of replicability. Journal of Memory and Language103, 151–175 (2018)

    2018

  32. [32]

    Computers & Graphics119, 103901 (2024)

    Prasse, P., Reich, D.R., Makowski, S., Scheffer, T., J¨ ager, L.A.: Improv- ing cognitive-state analysis from eye gaze with synthetic eye-movement data. Computers & Graphics119, 103901 (2024)

    2024

  33. [33]

    Proceedings of the ACM on Human-Computer Interaction 7(ETRA), 1–24 (2023)

    Deng, S., Reich, D.R., Prasse, P., Haller, P., Scheffer, T., J¨ ager, L.A.: Eyetten- tion: An attention-based dual-sequence model for predicting human scanpaths during reading. Proceedings of the ACM on Human-Computer Interaction 7(ETRA), 1–24 (2023)

    2023

  34. [34]

    In: Bouamor, H., Pino, J., Bali, K

    Bolliger, L., Reich, D., Haller, P., Jakobi, D., Prasse, P., J¨ ager, L.: ScanDL: A diffusion model for generating synthetic scanpaths on texts. In: Bouamor, H., Pino, J., Bali, K. (eds.) Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, Singapore, pp. 15513–15538 (2023)

    2023

  35. [35]

    In: Pro- ceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp

    Hahn, M., Keller, F.: Modeling human reading with neural attention. In: Pro- ceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, Austin, Texas, pp. 85–95 (2016)

    2016

  36. [36]

    Complexity2019(2019)

    Wang, X., Zhao, X., Ren, J.: A new type of eye movement model based on recurrent neural networks for simulating the gaze behavior of human reading. Complexity2019(2019)

    2019

  37. [37]

    In: Proceedings of the 2021 36 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, pp

    Hollenstein, N., Pirovano, F., Zhang, C., J¨ ager, L., Beinborn, L.: Multilingual language models predict human reading behavior. In: Proceedings of the 2021 36 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Online, pp. 106–123 (2021)

    2021

  38. [38]

    In: Proceedings of the Work- shop on Cognitive Modeling and Computational Linguistics, Online, pp

    Hollenstein, N., Chersoni, E., Jacobs, C.L., Oseki, Y., Pr´ evot, L., Santus, E.: CMCL 2021 shared task on eye-tracking prediction. In: Proceedings of the Work- shop on Cognitive Modeling and Computational Linguistics, Online, pp. 72–78 (2021)

    2021

  39. [39]

    In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, Dublin, Ireland, pp

    Hollenstein, N., Chersoni, E., Jacobs, C., Oseki, Y., Pr´ evot, L., Santus, E.: CMCL 2022 shared task on multilingual and crosslingual prediction of human reading behavior. In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, Dublin, Ireland, pp. 121–129 (2022)

    2022

  40. [40]

    Psychological review105(1), 125 (1998)

    Reichle, E.D., Pollatsek, A., Fisher, D.L., Rayner, K.: Toward a model of eye movement control in reading. Psychological review105(1), 125 (1998)

    1998

  41. [41]

    Vision Research39(26), 4403–4411 (1999)

    Reichle, E.D., Rayner, K., Pollatsek, A.: Eye movement control in reading: Accounting for initial fixation locations and refixations within the E-Z Reader model. Vision Research39(26), 4403–4411 (1999)

    1999

  42. [42]

    Psychological Review112(4), 777 (2005)

    Engbert, R., Nuthmann, A., Richter, E.M., Kliegl, R.: SWIFT: a dynamical model of saccade generation during reading. Psychological Review112(4), 777 (2005)

    2005

  43. [43]

    Rayner, K., McConkie, G.W.: What guides a reader’s eye movements? Vision Research16(8), 829–837 (1976)

    1976

  44. [44]

    Journal of Experimental Psychology: General109(2), 160–174 (1980)

    Posner, M.I., Snyder, C.R., Davidson, B.J.: Attention and the detection of signals. Journal of Experimental Psychology: General109(2), 160–174 (1980)

    1980

  45. [45]

    Vision Research14(4), 273–284 (1974)

    Bouma, H., De Voogd, A.: On the control of eye saccades in reading. Vision Research14(4), 273–284 (1974)

    1974

  46. [46]

    Journal of Experimental Psychology: Human Perception and Performance10(5), 667–682 (1984)

    Morrison, R.E.: Manipulation of stimulus onset delay in reading: evidence for parallel programming of saccades. Journal of Experimental Psychology: Human Perception and Performance10(5), 667–682 (1984)

    1984

  47. [47]

    Biological Cybernetics85(2), 77–87 (2001)

    Engbert, R., Kliegl, R.: Mathematical models of eye movements in reading: A possible role for autonomous saccades. Biological Cybernetics85(2), 77–87 (2001)

    2001

  48. [48]

    Cognitive Systems Research1(4), 201–220 (2001)

    Salvucci, D.D.: An integrated model of eye movements and visual encoding. Cognitive Systems Research1(4), 201–220 (2001)

    2001

  49. [49]

    Psychological Review111(4), 1036 (2004)

    Anderson, J.R., Bothell, D., Byrne, M.D., Douglass, S., Lebiere, C., Qin, Y.: An integrated theory of the mind. Psychological Review111(4), 1036 (2004)

    2004

  50. [50]

    In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol

    Veldre, A., Yu, L., Andrews, S., Reichle, E.D.: Towards a complete model of 37 reading: Simulating lexical decision, word naming, and sentence reading with ¨Uber-reader. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 42 (2020)

    2020

  51. [51]

    Journal of Memory and Language135, 104496 (2024)

    Rabe, M.M., Paape, D., Mertzen, D., Vasishth, S., Engbert, R.: Seam: An inte- grated activation-coupled model of sentence processing and eye movements in reading. Journal of Memory and Language135, 104496 (2024)

    2024

  52. [52]

    Cognitive Science29(3), 375–419 (2005)

    Lewis, R.L., Vasishth, S.: An activation-based model of sentence processing as skilled memory retrieval. Cognitive Science29(3), 375–419 (2005)

    2005

  53. [53]

    Journal of Cognitive Psychology27(5), 657–676 (2015)

    Mancheva, L., Reichle, E., Lemaire, B., Valdois, S., Ecalle, J., Gu´ erin-Dugu´ e, A.: An analysis of reading skill development using E-Z reader. Journal of Cognitive Psychology27(5), 657–676 (2015)

    2015

  54. [54]

    Developmental Review33(2), 110–149 (2013)

    Reichle, E.D., Liversedge, S.P., Drieghe, D., Blythe, H.I., Joseph, H.S., White, S.J., Rayner, K.: Using E-Z reader to examine the concurrent development of eye-movement control and reading skill. Developmental Review33(2), 110–149 (2013)

    2013

  55. [55]

    In: Proceedings of the Thirteenth Conference on Computational Natural Language Learning, Boulder, Colorado, pp

    Nilsson, M., Nivre, J.: Learning where to look: Modeling eye movements in reading. In: Proceedings of the Thirteenth Conference on Computational Natural Language Learning, Boulder, Colorado, pp. 93–101 (2009)

    2009

  56. [56]

    In: Proceedings of the 2010 Workshop on Cognitive Modeling and Computational Linguistics, ACL, Uppsala, Sweden, pp

    Nilsson, M., Nivre, J.: Towards a data-driven model of eye movement control in reading. In: Proceedings of the 2010 Workshop on Cognitive Modeling and Computational Linguistics, ACL, Uppsala, Sweden, pp. 63–71 (2010)

    2010

  57. [57]

    In: Proceedings of the 8th International NLPCS Workshop, Copenhagen, Denmark, pp

    Nilsson, M., Nivre, J.: Entropy-driven evaluation of models of eye movement control in reading. In: Proceedings of the 8th International NLPCS Workshop, Copenhagen, Denmark, pp. 201–212 (2011)

    2011

  58. [58]

    In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, pp

    Matthies, F., Søgaard, A.: With blinkers on: Robust prediction of eye movements across readers. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, Seattle, Washington, USA, pp. 803–807 (2013)

    2013

  59. [59]

    In: Proceedings of the First Workshop on Eye-tracking and Natural Language Processing, Mumbai, India, pp

    Hara, T., Mochihashi, D., Kano, Y., Aizawa, A.: Predicting word fixations in text with a CRF model for capturing general reading strategies among readers. In: Proceedings of the First Workshop on Eye-tracking and Natural Language Processing, Mumbai, India, pp. 55–70 (2012)

    2012

  60. [60]

    In: Proceedings of the 39th Annual Conference on Neural Information Processing Systems (2025)

    D’Agostino, F., Schwetlick, L., Bethge, M., Kuemmerer, M.: What moves the eyes: Doubling mechanistic model performance using deep networks to discover and test cognitive hypotheses. In: Proceedings of the 39th Annual Conference on Neural Information Processing Systems (2025)

    2025

  61. [61]

    Journal of Mathematical Psychology95, 102313 (2020)

    Seelig, S.A., Rabe, M.M., Malem-Shinitski, N., Risse, S., Reich, S., Engbert, R.: 38 Bayesian parameter estimation for the SWIFT model of eye-movement control during reading. Journal of Mathematical Psychology95, 102313 (2020)

    2020

  62. [62]

    Journal of Vision22(5), 7–7 (2022)

    K¨ ummerer, M., Bethge, M., Wallis, T.S.: Deepgaze iii: Modeling free-viewing human scanpaths with deep learning. Journal of Vision22(5), 7–7 (2022)

    2022

  63. [63]

    In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol

    Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 1. Minneapolis, MN, USA, pp. 4171–4186 (2019)

    2019

  64. [64]

    RoBERTa: A Robustly Optimized BERT Pretraining Approach

    Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V.: Roberta: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 1907

  65. [65]

    Neural Computation 9(8), 1735–1780 (1997)

    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Computation 9(8), 1735–1780 (1997)

    1997

  66. [66]

    Neural Networks18(5-6), 602–610 (2005)

    Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirec- tional lstm and other neural network architectures. Neural Networks18(5-6), 602–610 (2005)

    2005

  67. [67]

    In: Proceedings of the 31th Conference on Neural Information Processing Systems, vol

    Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., Polosukhin, I.: Attention is all you need. In: Proceedings of the 31th Conference on Neural Information Processing Systems, vol. 30. Long Beach, CA, USA (2017)

    2017

  68. [68]

    Bargary, G., Bosten, J.M., Goodbourn, P.T., Lawrance-Owen, A.J., Hogg, R.E., Mollon, J.D.: Individual differences in human eye movements: An oculomotor signature? Vision research141, 157–169 (2017)

    2017

  69. [69]

    In: Brefeld, Fromont, Knobbe, Hotho, Maathuis, Robardet (eds.) Machine Learning and Knowledge Discovery in Databases

    J¨ ager, L.A., Makowski, S., Prasse, P., Sascha, L., Seidler, M., Scheffer, T.: Deep Eyedentification: Biometric identification using micro-movements of the eye. In: Brefeld, Fromont, Knobbe, Hotho, Maathuis, Robardet (eds.) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019. Lecture Notes in Computer Science, vol. 11907, pp. 299–314. S...

    2019

  70. [70]

    IEEE Transactions on Biometrics, Behavior, and Identity Science3(4), 506–518 (2021)

    Makowski, S., Prasse, P., Reich, D.R., Krakowczyk, D., J¨ ager, L.A., Schef- fer, T.: Deepeyedentificationlive: Oculomotoric biometric identification and presentation-attack detection using deep neural networks. IEEE Transactions on Biometrics, Behavior, and Identity Science3(4), 506–518 (2021)

    2021

  71. [71]

    Neural computation1(2), 270–280 (1989) 39

    Williams, R.J., Zipser, D.: A learning algorithm for continually running fully recurrent neural networks. Neural computation1(2), 270–280 (1989) 39

    1989

  72. [72]

    Behavior Research Methods2021(2021)

    Pan, J., Yan, M., Richter, E.M., Shu, H., Kliegl, R.: The Beijing Sentence Cor- pus: A Chinese sentence corpus with eye movement data and predictability norms. Behavior Research Methods2021(2021)

    2021

  73. [73]

    Open Mind, 1–10 (2022)

    Berzak, Y., Nakamura, C., Smith, A., Weng, E., Katz, B., Flynn, S., Levy, R.: CELER: A 365-participant corpus of eye movements in L1 and L2 English reading. Open Mind, 1–10 (2022)

    2022

  74. [74]

    Scientific Data5, 180291 (2018)

    Hollenstein, N., Rotsztejn, J., Troendle, M., Pedroni, A., Zhang, C., Langer, N.: Zuco, a simultaneous EEG and eye-tracking resource for natural sentence reading. Scientific Data5, 180291 (2018)

    2018

  75. [75]

    In: Proceed- ings of the Twelfth Language Resources and Evaluation Conference, Marseille, France, pp

    Hollenstein, N., Troendle, M., Zhang, C., Langer, N.: ZuCo 2.0: A dataset of physiological recordings during natural reading and annotation. In: Proceed- ings of the Twelfth Language Resources and Evaluation Conference, Marseille, France, pp. 138–146 (2020)

    2020

  76. [76]

    In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pp

    Bestgen, Y.: LAST at CMCL 2021 shared task: Predicting gaze data during reading with a gradient boosting decision tree approach. In: Proceedings of the Workshop on Cognitive Modeling and Computational Linguistics, pp. 90–96. Association for Computational Linguistics, Online (2021)

    2021

  77. [77]

    Cognitive Science31(6), 1021–1033 (2007)

    Rayner, K., Li, X., Pollatsek, A.: Extending the E-Z reader model of eye movement control to chinese readers. Cognitive Science31(6), 1021–1033 (2007)

    2007

  78. [78]

    Psychol Rev128, 803–823 (2021)

    Rabe, M.M., Chandra, J., Kr¨ ugel, A., Seelig, S.A., Vasishth, S., Engbert, R.: A bayesian approach to dynamical modeling of eye-movement control in reading of normal, mirrored, and scrambled texts. Psychol Rev128, 803–823 (2021)

    2021

  79. [79]

    In: Proceedings of the 2010 Symposium on Eye- Tracking Research and Applications

    Jarodzka, H., Holmqvist, K., Nystr¨ om, M.: A vector-based, multidimensional scanpath similarity measure. In: Proceedings of the 2010 Symposium on Eye- Tracking Research and Applications. ETRA ’10, pp. 211–218, Austin, Texas (2010)

    2010

  80. [80]

    Journal of Open Source Software 4(40), 1525 (2019)

    Wagner, A.S., Halchenko, Y.O., Hanke, M.: multimatch-gaze: The multimatch algorithm for gaze path comparison in python. Journal of Open Source Software 4(40), 1525 (2019)

    2019

Showing first 80 references.