Essay writing is a skill commonly taught and practised in schools. The ability to write a fluent and persuasive essay is often a major component of formal assessment. In natural language processing and education technology we may work with essays in their final form, for example to carry out automated assessment or grammatical error correction. In this work we collect and analyse data representing the essay writing process from start to finish, by recording every key stroke from multiple writers participating in our study. We describe our data collection methodology, the characteristics of the resulting dataset, and the assignment of proficiency levels to the texts. We discuss the ways the keystroke data can be used – for instance seeking to identify patterns in the keystrokes which might act as features in automated assessment or may enable further advancements in writing assistance – and the writing support technology which could be built with such information, if we can detect when writers are struggling to compose a section of their essay and offer appropriate intervention. We frame this work in the context of English language learning, but we note that keystroke logging is relevant more broadly to text authoring scenarios as well as cognitive or linguistic analyses of the writing process.

This paper explores the use of L2-specific grammatical microsystems as elements of the domain knowledge of an Intelligent Computer-assisted Language Learning (ICALL) system. We report on the design of new grammatico-functional measures and their association with proficiency. We illustrate the approach with the design of the IT, THIS, THAT proform microsystem. The measures rely on the paradigmatic relations between words of the same linguistic functions. They are operationalised with one frequency-based and two probabilistic methods, i.e., the relative proportions of the forms and their likelihood of occurrence. Ordinal regression models show that the measures are significant in terms of association with CEFR levels, paving the way for their introduction in a specific proform microsystem expert model.

In the context of this biomedical shared task, we have implemented data filters to enhance the selection of relevant training data for fine- tuning from the available training data sources. Specifically, we have employed textometric analysis to detect repetitive segments within the test set, which we have then used for re- fining the training data used to fine-tune the mBart-50 baseline model. Through this approach, we aim to achieve several objectives: developing a practical fine-tuning strategy for training biomedical in-domain fr<>en models, defining criteria for filtering in-domain training data, and comparing model predictions, fine-tuning data in accordance with the test set to gain a deeper insight into the functioning of Neural Machine Translation (NMT) systems.

This paper describes the MAKE-NMTVIZ Systems trained for the WMT 2023 Literary task. As a primary submission, we used Train, Valid1, test1 as part of the GuoFeng corpus (Wang et al., 2023) to fine-tune the mBART50 model with Chinese-English data. We followed very similar training parameters to (Lee et al. 2022) when fine-tuning mBART50. We trained for 3 epochs, using gelu as an activation function, with a learning rate of 0.05, dropout of 0.1 and a batch size of 16. We decoded using a beam search of size 5. For our contrastive1 submission, we implemented a fine-tuned concatenation transformer (Lupo et al., 2023). The training was developed in two steps: (i) a sentence-level transformer was implemented for 10 epochs trained using general, test1, and valid1 data (more details in contrastive2 system); (ii) second, we fine-tuned at document-level using 3-sentence concatenation for 4 epochs using train, test2, and valid2 data. During the fine-tuning, we used ReLU as an activation function, with an inverse square root learning rate, dropout of 0.1, and a batch size of 64. We decoded using a beam search of size. Four our contrastive2 and last submission, we implemented a sentence-level transformer model (Vaswani et al., 2017). The model was trained with general data for 10 epochs using general-purpose, test1, and valid 1 data. The training parameters were an inverse square root scheduled learning rate, a dropout of 0.1, and a batch size of 64. We decoded using a beam search of size 4. We then compared the three translation outputs from an interdisciplinary perspective, investigating some of the effects of sentence- vs document-based training. Computer scientists, translators and corpus linguists discussed the linguistic remaining issues for this discourse-level literary translation.

This paper examines some of the effects of prosodic boundaries on ASR outputs and Spoken Language Translations into English for two competing French structures (“c’est” dislocation vs. “c’est” parentheticals). One native speaker of French read 104 test sentences that were then submitted to two systems. We compared the outputs of two toolkits, SYSTRAN Pure Neural Server (SPNS9) (Crego et al., 2016) and Whisper. For SPNS9, we compared the translation of the text file used for the reading with the translation of the transcription generated through Vocapia ASR. We also tested the transcription engine for speech recognition uploading an MP3 file and used the same procedure for AI Whisper’s Web-scale Supervised Pretraining for Speech Recognition system (Radford et al., 2022). We reported WER for the transcription tasks and the BLEU scores for the different models. We evidenced the variability of the punctuation in the ASR outputs and discussed it in relation to the duration of the utterance. We discussed the effects of the prosodic boundaries. We described the status of the boundary in the speech-to-text systems, discussing the consequence for the neural machine translation of the rendering of the prosodic boundary by a comma, a full stop, or any other punctuation symbol. We used the reference transcript of the reading phase to compute the edit distance between the reference transcript and the ASR output. We also used textometric analyses with iTrameur (Fleury and Zimina, 2014) for insights into the errors that can be attributed to ASR or to Neural Machine translation.

In this paper, we discuss the improvements brought by the fine-tuning of mBART50 for the translation of a specific Farsi dataset of dislocations. Given our BLEU scores, our evaluation is mostly qualitative: we assess the improvements of our fine-tuning in the translations into French of our test dataset of Farsi. We describe the fine-tuning procedure and discuss the quality of the results in the translations from Farsi. We assess the sentences in the French translations that contain English tokens and for the English translations, we examine the ability of the fine- tuned system to translate Farsi dislocations into English without replicating the dislocated item as a double subject. We scrutinized the Farsi training data used to train for mBART50 (Tang et al., 2021). We fine-tuned mBART50 with samples from an in-house French-Farsi aligned translation of a short story. In spite of the scarcity of available resources, we found that fine- tuning with aligned French-Farsi data dramatically improved the grammatical well-formedness of the predictions for French, even if serious semantic issues remained. We replicated the experiment with the English translation of the same Farsi short story for a Farsi-English fine-tuning and found out that similar semantic inadequacies cropped up, and that some translations were worse than our mBART50 baseline. We showcased the fine-tuning of mBART50 with supplementary data and discussed the asymmetry of the situation, adding little data in the fine-tuning is sufficient to improve morpho-syntax for one language pair but seems to degrade translation to English.

Ce travail présente deux séries d’expériences visant à identifier les flux d’information dans les systèmes de traduction neuronaux. La première série s’appuie sur une comparaison des décisions d’un modèle de langue et d’un modèle de traduction pour mettre en évidence le flux d’information provenant de la source. La seconde série met en évidence l’impact de ces flux sur l’apprentissage du système dans le cas particulier du transfert de l’information de genre.

Multiple studies have shown that existing NMT systems demonstrate some kind of “gender bias”. As a result, MT output appears to err more often for feminine forms and to amplify social gender misrepresentations, which is potentially harmful to users and practioners of these technologies. This paper continues this line of investigations and reports results obtained with a new test set in strictly controlled conditions. This setting allows us to better understand the multiple inner mechanisms that are causing these biases, which include the linguistic expressions of gender, the unbalanced distribution of masculine and feminine forms in the language, the modelling of morphological variation and the training process dynamics. To counterbalance these effects, we formulate several proposals and notably show that modifying the training loss can effectively mitigate such biases.

This paper describes the SPECTRANS submission for the WMT 2022 biomedical shared task. We present the results of our experiments using the training corpora and the JoeyNMT (Kreutzer et al., 2019) and SYSTRAN Pure Neural Server/ Advanced Model Studio toolkits for the language directions English to French and French to English. We compare the pre- dictions of the different toolkits. We also use JoeyNMT to fine-tune the model with a selection of texts from WMT, Khresmoi and UFAL data sets. We report our results and assess the respective merits of the different translated texts.

This paper discusses the WMT 2021 terminology shared task from a “meta” perspective. We present the results of our experiments using the terminology dataset and the OpenNMT (Klein et al., 2017) and JoeyNMT (Kreutzer et al., 2019) toolkits for the language direction English to French. Our experiment 1 compares the predictions of the two toolkits. Experiment 2 uses OpenNMT to fine-tune the model. We report our results for the task with the evaluation script but mostly discuss the linguistic properties of the terminology dataset provided for the task. We provide evidence of the importance of text genres across scores, having replicated the evaluation scripts.

Cet article présente les premiers résultats d’une étude en cours sur les biais de genre dans les corpus d’entraînements et dans les systèmes de traduction neuronale. Nous étudions en particulier un corpus minimal et contrôlé pour mesurer l’intensité de ces biais dans les deux directions anglais-français et français-anglais ; ce cadre contrôlé nous permet également d’analyser les représentations internes manipulées par le système pour réaliser ses prédictions lexicales, ainsi que de formuler des hypothèses sur la manière dont ce biais se distribue dans les représentations du système.

Cet article se propose d’envisager l’existence d’une grammaire spécifique aux interactions nasalisées (Chlébowski et Ballier, 2015). Notre proposition se fonde sur une annotation des composantes acoustiques de cette sous-catégorie de sons non-lexicaux (Ward, 2006) dans le corpus CID (Bertrand et al., 2008). Nous voudrions présenter les contraintes combinatoires et régularités qui semblent s’appliquer à ces composantes acoustiques, ainsi que discuter leur structuration. Les résultats préliminaires de l’analyse des composantes acoustiques semblent suggérer des plages de valeurs par défaut pour les réalisations des IN (notamment pour la durée). La violation de ces usages peut donner lieu à une analyse de type gricienne d’implicature.

Cet article décrit un prototype axé sur la prédiction du niveau de compétence des apprenants de l’anglais. Le système repose sur un modèle d’apprentissage supervisé, couplé à une interface web.

In this paper, we reproduce some of the experiments related to neural network training for Machine Translation as reported in (Vanmassenhove and Way, 2018). They annotated a sample from the EN-FR and EN-DE Europarl aligned corpora with syntactic and semantic annotations to train neural networks with the Nematus Neural Machine Translation (NMT) toolkit. Following the original publication, we obtained lower BLEU scores than the authors of the original paper, but on a more limited set of annotations. In the second half of the paper, we try to analyze the difference in the results obtained and suggest some methods to improve the results. We discuss the Byte Pair Encoding (BPE) used in the pre-processing phase and suggest feature ablation in relation to the granularity of syntactic and semantic annotations. The learnability of the annotated input is discussed in relation to existing resources for the target languages. We also discuss the feature representation likely to have been adopted for combining features.

This paper presents an annotation framework for nasal grunts of the whole French CID corpus (Bertrand et al., 2008). The acoustic components under scrutiny are justified and the annotation guidelines are described. We carefully characterise the acoustic cues and visual cues followed by the annotator, especially for non-modal phonation types. The conventions followed for the annotation of interactional and positional properties of grunts are explained. The resulting datasets after data extraction with Praat scripts (Boersma and Weenink, 2019) are analysed with R (R Core Team, 2017), focusing on duration. We analyse the effect of non-modal phonation (especially ingressive phonation) on duration and discuss a specialisation of grunts observed in the CID for grunts with ingressive phonation. The more general aim of this research is to establish putative core and additive properties of grunts and a tentative typology of grunts in spoken interactions.

This paper describes the workflow and architecture adopted by a linguistic research project. We report our experience and present the research outputs turned into resources that we wish to share with the community. We discuss the current limitations and the next steps that could be taken for the scaling and development of our research project. Allying NLP and language-centric AI, we discuss similar projects and possible ways to start collaborating towards potential platform interoperability.

Cette contribution analyse la segmentation syllabique des francophones du corpus d’apprenant d’anglais ANGLISH (Tortel 2009). A partir d’une méthode d’alignement par alignement forcé, on montre la pertinence d’une analyse de l’interlangue fondée sur la comparaison des durées des syllabes. La comparaison des réalisations est ici centrée sur une typologie des syllabes fondée sur des propriétés distributionnelles, accentuelles et où l’interlangue tient sa place (risques d’isosyllabicité les plus manifestes pour les réalisations des francophones). La variabilité des réalisations des syllabes est appréciée en fonction des propriétés positionnelles, accentuelles et structurelles des syllabes. L’étude démontre l’intérêt d’une approche fonctionnelle des syllabes, plus pertinente que les intervalles interconsonantiques et intervocaliques inspirés de Ramus et al. (1999) pour la discrimination du niveau des locuteurs.