To address this, et al., 2017) and becomes an even more critical our methodology, MetaSend, incorporates a metalearning challenge with large-scale NMT models. The result is depicted multilingual NMT performance over an FL system by the blue thresholds for the cases in Figure 1. A premise doing so, MetaSend considers translation quality for our work is that exchanging complete NMT and communication efficiency as important objectives engines in FL might not be necessary, similar to in multilingual NMT training. We can develop MetaSend, we make three major contributions: some intuition around this through a small We conduct the first research on the communication FL experiment using the well-known FedAVG algorithm efficiency of FL in multilingual NMT, (McMahan et al., 2017). In Figure 1, we perform and study the relationship between translation FL on the UN Corpus dataset (see Section 4 quality and the volume of transmitted parameters for details) distributed across three clients (each in multilingual NMT engines.

Business and consumer surveys are an essential tool used by policy-makers and practitioners to monitor and forecast the economy. Their most valuable feature is to provide timely information about the current and expected state of economic activity that is relevant to integrate the sluggish release of macroeconomic indicators. Interestingly, surveys are often interpreted as measures of economic sentiment in the sense of providing the pulse of different aspects of the economy, such as the consumers' attitude toward spending or the expectation of purchasing managers about inflation. Some prominent examples are represented by the Survey of Consumers of the University of Michigan (MCS) for the United States (Curtin and Dechaux, 2015) and the Business and Consumer Survey (BCS) for the European Union (European Commission, 2016). Although surveys are very valuable and accurate proxies of economic activity, they are typically released at the monthly frequency which might limit their usefulness in high-frequency nowcasting of economic variables (Aguilar et al., 2021; Algaba et al., 2023).

Neural Machine Translation (NMT) has become a significant technology in natural language processing through extensive research and development. However, the deficiency of high-quality bilingual language pair data still poses a major challenge to improving NMT performance. Recent studies have been exploring the use of contextual information from pre-trained language model (PLM) to address this problem. Yet, the issue of incompatibility between PLM and NMT model remains unresolved. This study proposes PLM-integrated NMT (PiNMT) model to overcome the identified problems. PiNMT model consists of three critical components, PLM Multi Layer Converter, Embedding Fusion, and Cosine Alignment, each playing a vital role in providing effective PLM information to NMT. Furthermore, two training strategies, Separate Learning Rates and Dual Step Training, are also introduced in this paper. By implementing the proposed PiNMT model and training strategy, we achieve state-of-the-art performance on the IWSLT'14 En$\leftrightarrow$De dataset. This study's outcomes are noteworthy as they demonstrate a novel approach for efficiently integrating PLM with NMT to overcome incompatibility and enhance performance.

Misgendering is the act of referring to someone in a way that does not reflect their gender identity. Translation systems, including foundation models capable of translation, can produce errors that result in misgendering harms. To measure the extent of such potential harms when translating into and out of English, we introduce a dataset, MiTTenS, covering 26 languages from a variety of language families and scripts, including several traditionally underpresented in digital resources. The dataset is constructed with handcrafted passages that target known failure patterns, longer synthetically generated passages, and natural passages sourced from multiple domains. We demonstrate the usefulness of the dataset by evaluating both dedicated neural machine translation systems and foundation models, and show that all systems exhibit errors resulting in misgendering harms, even in high resource languages.

Detecting the translation direction of parallel text has applications for machine translation training and evaluation, but also has forensic applications such as resolving plagiarism or forgery allegations. In this work, we explore an unsupervised approach to translation direction detection based on the simple hypothesis that $p(\text{translation}|\text{original})>p(\text{original}|\text{translation})$, motivated by the well-known simplification effect in translationese or machine-translationese. In experiments with massively multilingual machine translation models across 20 translation directions, we confirm the effectiveness of the approach for high-resource language pairs, achieving document-level accuracies of 82-96% for NMT-produced translations, and 60-81% for human translations, depending on the model used. Code and demo are available at https://github.com/ZurichNLP/translation-direction-detection

Ten years ago a single metric, BLEU, governed progress in machine translation research. For better or worse, there is no such consensus today, and consequently it is difficult for researchers to develop and retain the kinds of heuristic intuitions about metric deltas that drove earlier research and deployment decisions. This paper investigates the "dynamic range" of a number of modern metrics in an effort to provide a collective understanding of the meaning of differences in scores both within and among metrics; in other words, we ask what point difference X in metric Y is required between two systems for humans to notice? We conduct our evaluation on a new large dataset, ToShip23, using it to discover deltas at which metrics achieve system-level differences that are meaningful to humans, which we measure by pairwise system accuracy. We additionally show that this method of establishing delta-accuracy is more stable than the standard use of statistical p-values in regards to testset size. Where data size permits, we also explore the effect of metric deltas and accuracy across finer-grained features such as translation direction, domain, and system closeness.

Neural machine translation systems estimate probabilities of target sentences given source sentences, yet these estimates may not align with human preferences. This work introduces QE-fusion, a method utilizing a quality estimation metric (QE) that better correlates with human judgments to synthesize improved translations. QE-fusion leverages a candidate pool sampled from a model, combining spans from different candidates using QE metrics such as CometKiwi. We compare QE-fusion against beam search and recent reranking techniques, such as Minimum Bayes Risk decoding or QE-reranking. Our method consistently improves translation quality in terms of COMET and BLEURT scores when applied to large language models (LLMs) used for translation (PolyLM, XGLM, Llama2, and Mistral) and to multilingual translation models (NLLB), over five language pairs. Notably, QE-fusion exhibits larger improvements for LLMs due to their ability to generate diverse outputs. We demonstrate that our approach generates novel translations in over half of the cases and consistently outperforms other methods across varying numbers of candidates (5-200). Furthermore, we empirically establish that QE-fusion scales linearly with the number of candidates in the pool. QE-fusion proves effective in enhancing LLM-based translation without the need for costly retraining of LLMs.

There are 293 scripts representing over 7,000 languages in the written form. Due to various reasons, many closely related languages use different scripts, which poses difficulty for multilingual pretrained language models (mPLMs) in learning crosslingual knowledge through lexical overlap. As a result, mPLMs present a script barrier: representations from different scripts are located in different subspaces, which is a strong indicator of why crosslingual transfer involving languages of different scripts shows sub-optimal performance. To address this problem, we propose a simple framework TransliCo that contains Transliteration Contrastive Modeling (TCM) to fine-tune an mPLM by contrasting sentences in its training data and their transliterations in a unified script (Latn, in our case), which ensures uniformity in the representation space for different scripts. Using Glot500-m, an mPLM pretrained on over 500 languages, as our source model, we find-tune it on a small portion (5\%) of its training data, and refer to the resulting model as Furina. We show that Furina not only better aligns representations from distinct scripts but also outperforms the original Glot500-m on various crosslingual transfer tasks. Additionally, we achieve consistent improvement in a case study on the Indic group where the languages are highly related but use different scripts. We make our code and models publicly available.

Large Language Models (LLMs) have achieved remarkable results in the machine translation evaluation task, yet there remains a gap in knowledge regarding how they utilize the provided data to conduct evaluations. This study aims to explore how LLMs leverage source and reference information in evaluating translations, with the ultimate goal of better understanding the working mechanism of LLMs. To this end, we design the controlled experiments across various input modes and model types, and employ both coarse-grained and fine-grained prompts to discern the utility of source versus reference information. Surprisingly, we find that reference information significantly enhances the evaluation accuracy, while source information sometimes is counterproductive, indicating a lack of cross-lingual capability when using LLMs to evaluate translations. We further conduct a meta-evaluation for translation error detection of LLMs, observing a similar phenomenon. These findings also suggest a potential research direction for LLMs that fully exploits the cross-lingual capability of LLMs to achieve better performance in machine translation evaluation tasks.

The conversion of content from one language to another utilizing a computer system is known as Machine Translation (MT). Various techniques have come up to ensure effective translations that retain the contextual and lexical interpretation of the source language. End-to-end Neural Machine Translation (NMT) is a popular technique and it is now widely used in real-world MT systems. Massive amounts of parallel datasets (sentences in one language alongside translations in another) are required for MT systems. These datasets are crucial for an MT system to learn linguistic structures and patterns of both languages during the training phase. One such dataset is Samanantar, the largest publicly accessible parallel dataset for Indian languages (ILs). Since the corpus has been gathered from various sources, it contains many incorrect translations. Hence, the MT systems built using this dataset cannot perform to their usual potential. In this paper, we propose an algorithm to remove mistranslations from the training corpus and evaluate its performance and efficiency. Two Indic languages (ILs), namely, Hindi (HIN) and Odia (ODI) are chosen for the experiment. A baseline NMT system is built for these two ILs, and the effect of different dataset sizes is also investigated. The quality of the translations in the experiment is evaluated using standard metrics such as BLEU, METEOR, and RIBES. From the results, it is observed that removing the incorrect translation from the dataset makes the translation quality better. It is also noticed that, despite the fact that the ILs-English and English-ILs systems are trained using the same corpus, ILs-English works more effectively across all the evaluation metrics.