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 presents Lingua Custodia’s submission to the WMT23 shared task on Terminology shared task. Ensuring precise translation of technical terms plays a pivotal role in gauging the final quality of machine translation results. Our goal is to follow the terminology constraint while applying the machine translation system. Inspired by the recent work of terminology control, we propose to annotate the machine learning training data by leveraging a synthetic dictionary extracted in a fully non supervised way from the give parallel corpora. The model learned with this training data can then be then used to translate text with a given terminology in a flexible manner. In addition, we introduce a careful annotated data re-sampling step in order to guide the model to see different terminology types enough times. In this task we consider all the three language directions: Chinese to English, English to Czech and German to English. Our automatic evaluation metrics with the submitted systems show the effectiveness of the proposed method.

Natural language processing (NLP) has recently gained relevance within financial institutions by providing highly valuable insights into companies and markets’ financial documents. However, the landscape of the financial domain presents extra challenges for NLP, due to the complexity of the texts and the use of specific terminology. Generalist language models tend to fall short in tasks specifically tailored for finance, even when using large language models (LLMs) with great natural language understanding and generative capabilities. This paper presents a study on LLM adaptation methods targeted at the financial domain and with high emphasis on financial sentiment analysis. To this purpose, two foundation models with less than 1.5B parameters have been adapted using a wide range of strategies. We show that through careful fine-tuning on both financial documents and instructions, these foundation models can be adapted to the target domain. Moreover, we observe that small LLMs have comparable performance to larger scale models, while being more efficient in terms of parameters and data. In addition to the models, we show how to generate artificial instructions through LLMs to augment the number of samples of the instruction dataset.

Ces dernières années l’évaluation de la traduction automatique, qu’elle soit humaine ou automatique,a rencontré des difficultés. Face aux importantes avancées en matière de traduction automatiqueneuronale, l’évaluation s’est montrée peu fiable. De nombreuses nouvelles approches ont été pro-posées pour améliorer les protocoles d’évaluation. L’objectif de ce travail est de proposer une vued’ensemble sur l’état global de l’évaluation de la Traduction Automatique (TA). Nous commenceronspar exposer les approches d’évaluation humaine, ensuite nous présenterons les méthodes d’évaluationautomatiques tout en différenciant entre les familles d’approches (métriques superficielles et apprises)et nous prêterons une attention particulière à l’évaluation au niveau du document qui prend comptedu contexte. Pour terminer, nous nous concentrerons sur la méta-évaluation des méthodes.