Explore the vast range of titles available.

The success of Transformer architecture has seen increased interest in machine translation (MT). The translation quality of neural network-based MT transcends that of translations derived using statistical methods. This growth in MT research has entailed the development of accurate automatic evaluation metrics that allow us to track the performance of MT. However, automatically evaluating and comparing MT systems is a challenging task. Several studies have shown that traditional metrics (e.g., BLEU, TER) show poor performance in capturing semantic similarity between MT outputs and human reference translations. To date, to improve performance, various evaluation metrics have been proposed using the Transformer architecture. However, a systematic and comprehensive literature review on these metrics is still missing. Therefore, it is necessary to survey the existing automatic evaluation metrics of MT to enable both established and new researchers to quickly understand the trend of MT evaluation over the past few years. In this survey, we present the trend of automatic evaluation metrics. To better understand the developments in the field, we provide the taxonomy of the automatic evaluation metrics. Then, we explain the key contributions and shortcomings of the metrics. In addition, we select the representative metrics from the taxonomy, and conduct experiments to analyze related problems. Finally, we discuss the limitation of the current automatic metric studies through the experimentation and our suggestions for further research to improve the automatic evaluation metrics.

BlenderBot 2.0 represents a significant advancement in open-domain chatbots by incorporating real-time information and retaining user information across multiple sessions through an internet search module. Despite its innovations, there are still areas for improvement. This paper examines BlenderBot 2.0’s limitations and errors from three perspectives: model, data, and user interaction. From the data perspective, we highlight the challenges associated with the crowdsourcing process, including unclear guidelines for workers, insufficient measures for filtering hate speech, and the lack of a robust process for verifying the accuracy of internet-sourced information. From the user perspective, we identify nine types of limitations and conduct a thorough investigation into their causes. For each perspective, we propose practical methods for improvement and discuss potential directions for future research. Additionally, we extend our analysis to include perspectives in the era of large language models (LLMs), further broadening our understanding of the challenges and opportunities present in current AI technologies. This multifaceted analysis not only sheds light on BlenderBot 2.0’s current limitations but also charts a path forward for the development of more sophisticated and reliable open-domain chatbots within the broader context of LLM advancements.

Most bowel intussusceptions in adults have a leading point. However, there have been few reports of jejunojejunal intussusception secondary to a solitary juvenile polyp in adult. We report herein the case of a 19-year-old female with a solitary juvenile polyp in the jejunum causing intussusception. Laparoscopic-assisted reduction and segmental resection of the jejunum were successfully done for the patient.

The notion of topological entropy dimension for a Z -action has been introduced to measure the subexponential complexity of zero entropy systems. Given a Z 2 -action, along with a Z 2 -entropy dimension, we also consider a finer notion of directional entropy dimension arising from its subactions. The entropy dimension of a Z 2 -action and the directional entropy dimensions of its subactions satisfy certain inequalities. We present several constructions of strictly ergodic Z 2 -subshifts of positive entropy dimension with diverse properties of their subgroup actions. In particular, we show that there is a Z 2 -subshift of full dimension in which every direction has entropy 0.

The notion of topological entropy dimension for a Z -action has been introduced to measure the subexponential complexity of zero entropy systems. Given a Z 2 -action, along with a Z 2 -entropy dimension, we also consider a finer notion of directional entropy dimension arising from its subactions. The entropy dimension of a Z 2 -action and the directional entropy dimensions of its subactions satisfy certain inequalities. We present several constructions of strictly ergodic Z 2 -subshifts of positive entropy dimension with diverse properties of their subgroup actions. In particular, we show that there is a Z 2 -subshift of full dimension in which every direction has entropy 0.

With the increasing accessibility and utilization of multilingual documents, Cross-Lingual Information Retrieval (CLIR) has emerged as an important research area. Conventionally, CLIR tasks have been conducted under settings where the language of documents differs from that of queries, and typically, the documents are composed in a single coherent language. In this paper, we highlight that in such a setting, the cross-lingual alignment capability may not be evaluated adequately. Specifically, we observe that, in a document pool where English documents coexist with another language, most multilingual retrievers tend to prioritize unrelated English documents over the related document written in the same language as the query. To rigorously analyze and quantify this phenomenon, we introduce various scenarios and metrics designed to evaluate the cross-lingual alignment performance of multilingual retrieval models. Furthermore, to improve cross-lingual performance under these challenging conditions, we propose a novel training strategy aimed at enhancing cross-lingual alignment. Using only a small dataset consisting of 2.8k samples, our method significantly improves the cross-lingual retrieval performance while simultaneously mitigating the English inclination problem. Extensive analyses demonstrate that the proposed method substantially enhances the cross-lingual alignment capabilities of most multilingual embedding models.

Introduction Aspirin-intolerant asthma (AIA), a major clinical presentation of aspirin hypersensitivity, affects 10% of adult asthmatics. The genetic risk factors involved in the susceptibility to AIA have recently been investigated, but multilocus single-nucleotide polymorphisms (SNPs) associated with this susceptibility has not been evaluated. Methods We examined 246 asthmatic patients: 94 having aspirin intolerance and 152 having aspirin tolerance. We selected 23 SNPs of 13 candidate genes and genotyped each SNP using a primer extension method. Multilocus genetic interactions were examined using multifactor dimensionality reduction (MDR) to test all multilocus SNP combinations to identify a useful SNP set for predicting the AIA phenotype. Results We identified the best model using the MDR method, which consisted of a four-locus gene–gene interaction with 65.16% balanced accuracy and a cross-validation consistency of 70% in predicting AIA disease risk among asthmatic patients. This model included four SNPs such as B2ADR 46A>G, CCR3 –520T>G, CysLTR1 –634C>T, and FCER1B –109T>C. Discussion These results suggest that a multilocus SNP acts in combination to influence the susceptibility to aspirin intolerance in asthmatics and could be a useful genetic marker for the diagnosis of AIA.

Adapting large language models to other languages typically employs supervised fine-tuning (SFT) as a standard approach. However, it often suffers from an overemphasis on English performance, a phenomenon that is especially pronounced in data-constrained environments. To overcome these challenges, we propose \\textbf{Cross-Lingual Optimization (CLO)} that efficiently transfers an English-centric LLM to a target language while preserving its English capabilities. CLO utilizes publicly available English SFT data and a translation model to enable cross-lingual transfer. We conduct experiments using five models on six languages, each possessing varying levels of resource. Our results show that CLO consistently outperforms SFT in both acquiring target language proficiency and maintaining English performance. Remarkably, in low-resource languages, CLO with only 3,200 samples surpasses SFT with 6,400 samples, demonstrating that CLO can achieve better performance with less data. Furthermore, we find that SFT is particularly sensitive to data quantity in medium and low-resource languages, whereas CLO remains robust. Our comprehensive analysis emphasizes the limitations of SFT and incorporates additional training strategies in CLO to enhance efficiency.

A recent result of Griffin, Ono, Rolen and Zagier on Jensen polynomials related with the Riemann zeta function is improved.

We prove that the best constant in the Turán-Kubilius inequality for additive functions is 3/2 in any sufficiently large range.