Neural machine translation (NMT) systems amplify lexical biases present in their training data, leading to artificially impoverished language in output translations.These language-level characteristics render automatic translations different from text originally written in a language and human translations, which hinders their usefulness in for example creating evaluation datasets.Attempts to increase naturalness in NMT can fall short in terms of content preservation, where increased lexical diversity comes at the cost of translation accuracy.Inspired by the reinforcement learning from human feedback framework, we introduce a novel method that rewards both naturalness and content preservation.We experiment with multiple perspectives to produce more natural translations, aiming at reducing machine and human translationese.We evaluate our method on English-to-Dutch literary translation, and find that our best model produces translations that are lexically richer and exhibit more properties of human-written language, without loss in translation accuracy.

Cancer survival prediction is an important direction in precision medicine, aiming to help clinicians tailor treatment regimens for patients. With the rapid development of high-throughput sequencing and computational pathology technologies, survival prediction has shifted from clinical features to joint modeling of multi-omics data and pathology images. However, existing multimodal learning methods struggle to effectively learn pathology-omics interactions due to the lack of proper alignment of multimodal data before fusion. In this paper, we propose POMP, a pathology-omics multimodal pre-training framework jointly learned with three training tasks for integrating pathological images and omics data for cancer survival prediction. To better perform cross-modal learning, we introduce a pathology-omics contrastive learning method to align the pathology and omics information. POMP leverages the principle of pre-trained models and explores the benefit of aligning multimodal information from the same patient, achieving state-of-the-art results on six cancer datasets from the Cancer Genome Atlas (TCGA). We also show that our contrastive learning method allows us to exploit the cosine similarity of pathological images and omics data as the survival risk score, which can further boost prediction performance compared with other commonly used methods. The code is available at https://github.com/SuixueWang/POMP.

Large language models (LLMs) with Chainof-thought (CoT) have recently emerged as a powerful technique for eliciting reasoning to improve various downstream tasks.As most research mainly focuses on English, with few explorations in a multilingual context, the question of how reliable this reasoning capability is in different languages is still open.To address it directly, we study multilingual reasoning consistency across multiple languages, using popular open-source LLMs.First, we compile the first large-scale multilingual math reasoning dataset, mCoT-MATH, covering eleven diverse languages.Then, we introduce multilingual CoT instruction tuning to boost reasoning capability across languages, thereby improving model consistency.While existing LLMs show substantial variation across the languages we consider, and especially low performance for lesser resourced languages, our 7B parameter model mCoT achieves impressive consistency across languages, and superior or comparable performance to close-and open-source models even of much larger sizes.

With the rapid advancement in multimodal fusion technology, the integration of pathological images with genomics data has achieved promising results in cancer survival prediction. However, most existing multimodal models are not pre-trained by combining pathology and genomics modalities, ignoring the inherent task-agnostic associations between different modalities. While some self-supervised methods align multimodal information through pre-training objectives such as correlation and mean square error, they lack in-depth multimodal interaction. To address these issues, we propose ContraMAE, a contrastive alignment masked autoencoder framework, to fuse pathological images and genomics data for cancer survival prediction. Concretely, we introduce a contrastive objective to align multimodality and construct their intrinsic consistency. Besides, we design two reconstruction objectives to capture the complex relationships between multi-modalities by mutually compensating for the information that each side lacks. In survival prediction, the pathology and genomics encodings from the ContraMAE encoder are concatenated as the final representation to generate a survival risk score. Experimental results demonstrate that ContraMAE outperforms existing state-of-the-art methods on five cancer datasets sourced from The Cancer Genome Atlas (TCGA). The code is available at https://github.com/SuixueWang/ContraMAE.

Machine translations are found to be lexically poorer than human translations. The loss of lexical diversity through MT poses an issue in the automatic translation of litrature, where it matters not only what is written, but also how it is written. Current methods for increasing lexical diversity in MT are rigid. Yet, as we demonstrate, the degree of lexical diversity can vary considerably across different novels. Thus, rather than aiming for the rigid increase of lexical diversity, we reframe the task as recovering what is lost in the machine translation process. We propose a novel approach that consists of reranking translation candidates with a classifier that distinguishes between original and translated text. We evaluate our approach on 31 English-to-Dutch book translations, and find that, for certain books, our approach retrieves lexical diversity scores that are close to human translation.

Figurative language generation is the task of reformulating a given text in the desired figure of speech while still being faithful to the original context. We take the first step towards multi-figurative language modelling by providing a benchmark for the automatic generation of five common figurative forms in English. We train mFLAG employing a scheme for multi-figurative language pre-training on top of BART, and a mechanism for injecting the target figurative information into the encoder; this enables the generation of text with the target figurative form from another figurative form without parallel figurative-figurative sentence pairs. Our approach outperforms all strong baselines. We also offer some qualitative analysis and reflections on the relationship between the different figures of speech.

Style transfer aims to rewrite a source text in a different target style while preserving its content.We propose a novel approach to this task that leverages generic resources, and without using any task-specific parallel (source-target) data outperforms existing unsupervised approaches on the two most popular style transfer tasks: formality transfer and polarity swap.In practice, we adopt a multistep procedure which builds on a generic pretrained sequence-to-sequence model (BART).First, we strengthen the model's ability to rewrite by further pre-training BART on both an existing collection of generic paraphrases, as well as on synthetic pairs created using a general-purpose lexical resource.Second, through an iterative back-translation approach, we train two models, each in a transfer direction, so that they can provide each other with synthetically generated pairs, dynamically in the training process.Lastly, we let our best resulting model generate static synthetic pairs to be used in a supervised training regime.Besides methodology and state-of-the-art results, a core contribution of this work is a reflection on the nature of the two tasks we address, and how their differences are highlighted by their response to our approach.