Machine translation quality has steadily improved over the years, achieving near-perfect translations in recent benchmarks. These high-quality outputs make it difficult to distinguish between state-of-the-art models and to identify areas for future improvement. In this context, automatically identifying texts where machine translation systems struggle holds promise for developing more discriminative evaluations and guiding future research. In this work, we address this gap by formalizing the task of translation difficulty estimation, defining a text's difficulty based on the expected quality of its translations. We introduce a new metric to evaluate difficulty estimators and use it to assess both baselines and novel approaches. Finally, we demonstrate the practical utility of difficulty estimators by using them to construct more challenging benchmarks for machine translation. Our results show that dedicated models outperform both heuristic-based methods and LLM-as-a-judge approaches, with Sentinel-src achieving the best performance. Thus, we release two improved models for difficulty estimation, Sentinel-src-24 and Sentinel-src-25, which can be used to scan large collections of texts and select those most likely to challenge contemporary machine translation systems.

As one of the world's most populous countries, with 700 languages spoken, Indonesia is behind in terms of NLP progress. We introduce LoraxBench, a benchmark that focuses on low-resource languages of Indonesia and covers 6 diverse tasks: reading comprehension, open-domain QA, language inference, causal reasoning, translation, and cultural QA. Our dataset covers 20 languages, with the addition of two formality registers for three languages. We evaluate a diverse set of multilingual and region-focused LLMs and found that this benchmark is challenging. We note a visible discrepancy between performance in Indonesian and other languages, especially the low-resource ones. There is no clear lead when using a region-specific model as opposed to the general multilingual model. Lastly, we show that a change in register affects model performance, especially with registers not commonly found in social media, such as high-level politeness `Krama' Javanese.

This paper examines the impact of fiscal incentives on industrial investment in Uruguay from 1974 to 2010. Using a mixed-method approach that combines econometric models with machine learning techniques, the study investigates both the short-term and long-term effects of fiscal benefits on industrial investment. The results confirm the significant role of fiscal incentives in driving long-term industrial growth, while also highlighting the importance of a stable macroeconomic environment, public investment, and access to credit. Machine learning models provide additional insights into nonlinear interactions between fiscal benefits and other macroeconomic factors, such as exchange rates, emphasizing the need for tailored fiscal policies. The findings have important policy implications, suggesting that fiscal incentives, when combined with broader economic reforms, can effectively promote industrial development in emerging economies.

Multilingual large language models (MLLMs) struggle to answer questions posed in non-dominant languages, even though they have acquired the relevant knowledge from their dominant language corpus. In contrast, human multilinguals can overcome such non-native language context limitations through Positive Native Language Transfer (PNLT). Inspired by the process of PNLT, we analogize the dominant language of MLLMs to the native language of human multilinguals, and propose Native Language Prompting (NatLan) to simulate the PNLT observed in human multilinguals. It explicitly creates native language contexts for MLLMs to facilitate the elicitation of the rich native language knowledge during question-answering, unlocking the limitations imposed by non-native language contexts. By employing multi-MLLM collaboration, NatLan reduces the workload on each MLLM in simulating PNLT and refines semantic transfer. On the C-Eval benchmark, NatLan provides up to a 10.1% average accuracy improvement and up to a 5.0% increase in the hard-level subset across five MLLMs, surpassing all top-notch related methods. Our code is available at https://github.com/AnonyNLP/NatLan.

Indonesia's linguistic landscape is remarkably diverse, encompassing over 700 languages and dialects, making it one of the world's most linguistically rich nations. This diversity, coupled with the widespread practice of code-switching and the presence of low-resource regional languages, presents unique challenges for modern pre-trained language models. In response to these challenges, we developed NusaBERT, building upon IndoBERT by incorporating vocabulary expansion and leveraging a diverse multilingual corpus that includes regional languages and dialects. Through rigorous evaluation across a range of benchmarks, NusaBERT demonstrates state-of-the-art performance in tasks involving multiple languages of Indonesia, paving the way for future natural language understanding research for under-represented languages.

In patent prosecution, timely and effective responses to Office Actions (OAs) are crucial for acquiring patents, yet past automation and AI research have scarcely addressed this aspect. To address this gap, our study introduces the Patent Office Action Response Intelligence System (PARIS) and its advanced version, the Large Language Model Enhanced PARIS (LE-PARIS). These systems are designed to expedite the efficiency of patent attorneys in collaboratively handling OA responses. The systems' key features include the construction of an OA Topics Database, development of Response Templates, and implementation of Recommender Systems and LLM-based Response Generation. Our validation involves a multi-paradigmatic analysis using the USPTO Office Action database and longitudinal data of attorney interactions with our systems over six years. Through five studies, we examine the constructiveness of OA topics (studies 1 and 2) using topic modeling and the proposed Delphi process, the efficacy of our proposed hybrid recommender system tailored for OA (both LLM-based and non-LLM-based) (study 3), the quality of response generation (study 4), and the practical value of the systems in real-world scenarios via user studies (study 5). Results demonstrate that both PARIS and LE-PARIS significantly meet key metrics and positively impact attorney performance.

Solving this problem can improve precision by removing duplicates, and can enrich detail by (for example) merging a phone Location matters in many businesses and services today, number from one record with the hours of operation particularly for transportation and delivery, scenarios from another, once these records are known to refer in which it is important to find the correct pickup to the same thing. This problem is referred to as entity and drop-off locations very quickly. User experience resolution (see (Talburt, 2011)), and it occurs with can be negatively affected if the location information various datasets, including those representing people, is inaccurate or insufficient. Inaccuracies products, works of literature, etc. can originate from imprecise GPS data, manual error happening in the process of data entry, or the lack of For Grab, one entity resolution problem that arises effective data quality control. Insufficiencies can also for spatial data is the alignment of transportation destinations take many forms, including lack of coverage, and lack and restaurants. Currently Grab maintains of detail -- for example, we may know the latitude two tables separately for transportation and food delivery, and longitude of a restaurant location in a mall, but because each use case requires some specific this might not include information about where passengers features, i.e., food delivery needs information about should be dropped off, or where a delivery the estimated delivery time, cuisine types, and opening courier should park to collect food for delivery. Or hours which are absent in the POI table. However, the location of a business may be known, but not its it is highly likely that some entities from both tables contact details or opening hours.

Reanalysis datasets combining numerical physics models and limited observations to generate a synthesised estimate of variables in an Earth system, are prone to biases against ground truth. Biases identified with the NASA Modern-Era Retrospective Analysis for Research and Applications, Version 2 (MERRA-2) aerosol optical depth (AOD) dataset, against the Aerosol Robotic Network (AERONET) ground measurements in previous studies, motivated the development of a deep learning based AOD prediction model globally. This study combines a convolutional neural network (CNN) with MERRA-2, tested against all AERONET sites. The new hybrid CNN-based model provides better estimates validated versus AERONET ground truth, than only using MERRA-2 reanalysis.

Don't fly near airports or airfields. Remember to stay below 400ft (120m).

Flocks of robotic birds are taking to the skies of China equipped with high-tech surveillance technology, according to a report. The so-called "spy bird" programme, first reported by the South China Morning Post, is already in operation in at least five provinces and provides another tendril in the country's already advanced surveillance network. The dove-like drones are being developed by researchers at Northwestern Polytechnical University in the Shaanxi province, who have previously worked on stealth fighter jets used by China's airforce. One of the researchers involved said the roll out of the technology was still in its early stages. "The scale is still small," said Yang Wenqing, an associate professor at the university's School of Aeronautics who worked on the programme.