**Robustness and limitations of natural language processing models**


This special issue of the TAL journal calls for papers on the topic of the robustness and limitations of natural language processing (NLP) models (written text).

Call for submission: http://tal-64-2.sciencesconf.org/

Paper submission deadline : May 12th, 2023


THE TAL JOURNAL

Since 1960, ATALA has been publishing the international journal Traitement Automatique des Langues (formerly La Traduction Automatique, then TA Informations), with the support of the CNRS. This journal is published three times a year.

The journal is open-access: free to submit, free to publish and free to read. Published articles will be available on the ATALA* website and on the ACL Anthology**.

Manuscripts may be submitted in English or French. French-speaking authors are requested to submit their contributions in French.

* https://www.atala.org/revuetal
** aclanthology.org/


GUEST EDITORS

- Caio Corro (Université Paris-Saclay, CNRS, LISN)
- Gaël Lejeune (Sorbonne Université, STIH)
- Vlad Niculae (Language Technology Lab, University of Amsterdam)


FOCUS OF THE ISSUE

Machine learning methods have made it possible to achieve spectacular results on numerous NLP tasks and benchmarks, giving the impression that many problems related to NLP are "solved" or soon to be solved. Nevertheless, it is still an open question as whether or not these models are really effective, or even usable, in non-controlled environments.

This thematic issue of the TAL journal aims at questioning the robustness and limits of modern NLP models, in particular related to the following aspects:

1. "Non-standard" data: the use of models on non-standard data, that is data presenting variations with respect to language (diachronic language variation, diatopic variations, variation in word order, code-switching, user-generated content, inconsistent spelling, accidentally noisy data due to pre-processing, incomplete data, presence of specialized domain vocabulary...).
2. Out-of-domain data: the use of models on data from a different domain that the one seen during training;
3. Linguistic structures unseen during training: compositional generalization [1], structural generalization [2], or generalization related to gender bias [3], among others.


Relevant topics for this thematic issue include, but are not limited to, the following areas :

- identification and evaluation of linguistic phenomena that are problematic for neural networks and other NLP systems;
- analysis and correction of error propagation in NLP systems (cascading error analysis);
- feedback on the use of NLP systems that have been found to be non-functional on specific types of data;
- critical analysis of datasets used for learning or evaluation;
- construction of datasets to evaluate robustness with respect to linguistic variations;
- data augmentation to improve robustness;
- out-of-domain adaptation or learning with domains that are underrepresented in the data;
- neural architectures or training methods that improve robustness.

All standard NLP tasks can be considered. Works on other languages than French and English are warmly welcomed.


IMPORTANT DATES

- Paper submission deadline : May 12th, 2023 via https://tal-64-2.sciencesconf.org/
- Notification to the authors after first review : July 2023
- Notification to the authors after second review : November 2023
- Publication : February 2024


LANGUAGE

Articles are written in English or French. Submissions in English are
accepted only if one of the co-authors is not French speaking.



SUBMISSION FORMAT


The length of the papers must be between 20 and 25 pages.

The TAL journal has a double-blind review process. It is necessary to anonymize the article, the name of the file, and to avoid
self-references.

Style sheets are available on the journal's website: https://www.atala.org/content/instruction-authors-style-files-0

Authors are invited to submit their paper by clicking on the menu "Paper submission" (PDF
article" menu (PDF format). To do so, you will need to have an account on the sciencesconf platform ( http://www.sciencesconf.org ). Click on "create account" next to the
"Connect" button at the top of the page. To submit, come back to the
page https://tal-64-2.sciencesconf.org/, connect to your account and upload your submission.


CONTACT

tal-64-2@sciencesconf.org


REFERENCES

[1] COGS: A Compositional Generalization Challenge Based on Semantic Interpretation (Najoung Kim, Tal Linzen), EMNLP 2020 https://aclanthology.org/2020.emnlp-main.731/
[2] Structural generalization is hard for sequence-to-sequence models (Yuekun Yao, Alexander Koller), EMNLP 2022 https://arxiv.org/abs/2210.13050
[3] Evaluating Gender Bias in Machine Translation (Gabriel Stanovsky, Noah A. Smith, Luke Zettlemoyer), ACL 2019 https://aclanthology.org/P19-1164/