This paper introduces ArtELingo, a new benchmark and dataset, designed to encourage work on diversity across languages and cultures. Following ArtEmis, a collection of 80k artworks from WikiArt with 0.45M emotion labels and English-only captions, ArtELingo adds another 0.79M annotations in Arabic and Chinese, plus 4.8K in Spanish to evaluate "cultural-transfer" performance. More than 51K artworks have 5 annotations or more in 3 languages. This diversity makes it possible to study similarities and differences across languages and cultures. Further, we investigate captioning tasks, and find diversity improves the performance of baseline models. ArtELingo is publicly available at https://www.artelingo.org/ with standard splits and baseline models. We hope our work will help ease future research on multilinguality and culturally-aware AI.

While bio-inspired and biomimetic systems draw inspiration from living materials, biohybrid systems incorporate them with synthetic devices, allowing the exploitation of both organic and artificial advantages inside a single entity. In the challenging development of centimeter-scaled mobile robots serving unstructured territory navigations, biohybrid systems appear as a potential solution in the forms of terrestrial insect-machine hybrid systems, which are the fusion of living ambulatory insects and miniature electronic devices. Although their maneuver can be deliberately controlled via artificial electrical stimulation, these hybrid systems still inherit the insects' outstanding locomotory skills, orchestrated by a sophisticated central nervous system and various sensory organs, favoring their maneuvers in complex terrains. However, efficient autonomous navigation of these hybrid systems is challenging. The struggle to optimize the stimulation parameters for individual insects limits the reliability and accuracy of navigation control. This study overcomes this problem by implementing a feedback control system with an insight view of tunable navigation control for an insectmachine hybrid system based on a living darkling beetle. Via a thrust controller for acceleration and a proportional controller for turning, the system regulates the stimulation parameters based on the instantaneous status of the hybrid robot. While the system can provide an overall success rate of ~71% for path-following navigations, fine-tuning its control parameters could further improve the outcome's reliability and precision to up to ~94% success rate and ~1/2 body length accuracy, respectively. Such tunable performance of the feedback control system provides flexibility to navigation applications of insect-machine hybrid systems. Keywords Biohybrid systems; Insect-machine hybrid systems; Zophobas morio; Autonomous navigation; Feedback control; Path-following 1. Introduction Terrestrial insect-scale mobile robots have become prominent candidates for post-disaster search-and-rescue missions. Their tiny size and light weight would help them easily penetrate deep into the rubbles of collapsed buildings without causing additional collapses. While there are growing efforts to achieve insect-level autonomy in these robots, it is still a challenge to match their natural-born counterparts, i.e., living ambulatory insects. While control autonomy was achieved in various insect-scale mobile robots (Chen et al. 2020; de Rivaz et al. 2018; Goldberg et al. 2018; St. Pierre and Bergbreiter 2019; Yang et al. 2020), power autonomy was demonstrated only in a few platforms, like HAMR-F (Goldberg et al. 2018) or Robeetle (Yang et al. 2020). Furthermore, although inverted and vertical climbing was demonstrated (Chen et al. 2020; de Rivaz et al. 2018), maneuvering across complex terrains is still a conundrum for these artificial robots.

In the study, we empirically compare the two recently proposed decoding methods, i.e. Contrastive Search (CS) and Contrastive Decoding (CD), for open-ended text generation. The automatic evaluation results suggest that, while CS performs worse than CD on the MAUVE metric, it substantially surpasses CD on the diversity and coherence metrics. More notably, extensive human evaluations across three different domains demonstrate that human annotators are universally more in favor of CS over CD with substantial margins. The contradicted results between MAUVE and human evaluations reveal that MAUVE does not accurately reflect human preferences. Therefore, we call upon the research community to develop better evaluation metrics for open-ended text generation. To ensure the reproducibility of our work, we have open-sourced all our code, evaluation results, as well as human annotations at https://github.com/yxuansu/Contrastive_Search_versus_Contrastive_Decoding.

Since the beginning of the vaccination trial, social media has been flooded with anti-vaccination comments and conspiracy beliefs. As the day passes, the number of COVID- 19 cases increases, and online platforms and a few news portals entertain sharing different conspiracy theories. The most popular conspiracy belief was the link between the 5G network spreading COVID-19 and the Chinese government spreading the virus as a bioweapon, which initially created racial hatred. Although some disbelief has less impact on society, others create massive destruction. For example, the 5G conspiracy led to the burn of the 5G Tower, and belief in the Chinese bioweapon story promoted an attack on the Asian-Americans. Another popular conspiracy belief was that Bill Gates spread this Coronavirus disease (COVID-19) by launching a mass vaccination program to track everyone. This Conspiracy belief creates distrust issues among laypeople and creates vaccine hesitancy. This study aims to discover the conspiracy theory against the vaccine on social platforms. We performed a sentiment analysis on the 598 unique sample comments related to COVID-19 vaccines. We used two different models, BERT and Perspective API, to find out the sentiment and toxicity of the sentence toward the COVID-19 vaccine.

We propose a new uniform framework for text classification and ranking that can automate the process of identifying check-worthy sentences in political debates and speech transcripts. Our framework combines the semantic analysis of the sentences, with additional entity embeddings obtained through the identified entities within the sentences. In particular, we analyse the semantic meaning of each sentence using state-of-the-art neural language models such as BERT, ALBERT, and RoBERTa, while embeddings for entities are obtained from knowledge graph (KG) embedding models. Specifically, we instantiate our framework using five different language models, entity embeddings obtained from six different KG embedding models, as well as two combination methods leading to several Entity-Assisted neural language models. We extensively evaluate the effectiveness of our framework using two publicly available datasets from the CLEF' 2019 & 2020 CheckThat! Labs. Our results show that the neural language models significantly outperform traditional TF.IDF and LSTM methods. In addition, we show that the ALBERT model is consistently the most effective model among all the tested neural language models. Our entity embeddings significantly outperform other existing approaches from the literature that are based on similarity and relatedness scores between the entities in a sentence, when used alongside a KG embedding.

Large language models (LLMs) transfer well to new tasks out-of-the-box simply given a natural language prompt that demonstrates how to perform the task and no additional training. Prompting is a brittle process wherein small modifications to the prompt can cause large variations in the model predictions, and therefore significant effort is dedicated towards designing a painstakingly "perfect prompt" for a task. To mitigate the high degree of effort involved in prompt-design, we instead ask whether producing multiple effective, yet imperfect, prompts and aggregating them can lead to a high quality prompting strategy. Our observations motivate our proposed prompting method, ASK ME ANYTHING (AMA). We first develop an understanding of the effective prompt formats, finding that question-answering (QA) prompts, which encourage open-ended generation ("Who went to the park?") tend to outperform those that restrict the model outputs ("John went to the park. Output True or False."). Our approach recursively uses the LLM itself to transform task inputs to the effective QA format. We apply the collected prompts to obtain several noisy votes for the input's true label. We find that the prompts can have very different accuracies and complex dependencies and thus propose to use weak supervision, a procedure for combining the noisy predictions, to produce the final predictions for the inputs. We evaluate AMA across open-source model families (e.g., EleutherAI, BLOOM, OPT, and T0) and model sizes (125M-175B parameters), demonstrating an average performance lift of 10.2% over the few-shot baseline. This simple strategy enables the open-source GPT-J-6B model to match and exceed the performance of few-shot GPT3-175B on 15 of 20 popular benchmarks. Averaged across these tasks, the GPT-J-6B model outperforms few-shot GPT3-175B. We release our code here: https://github.com/HazyResearch/ama_prompting

Kuda is a fintech company on a mission to make financial services accessible, affordable and rewarding for every African on the planet. We're a tribe of passionate and diverse people who dreamed of building an inclusive money app that Africans would love so it's only right that we ended up with the name'Kuda' which means'love' in Shona, a language spoken in the southern part of Africa. We're giving Africans around the world a better alternative to traditional finance by delivering free money transfers, smart budgeting and instant access to credit through digital devices. We've raised over $90 million from some of the world's most respected institutional investors, and we're rolling out our game-changing services globally from our offices in Nigeria, South Africa, and the UK. To support our rapid growth and reach 4M customers by the end of 2022, Kuda is looking for an experienced Data Analyst who can mine attribution, engagement and behavioral data to establish insights and ensure we make data-driven decisions around product and channel experimentations, ensuring we focus on the highest ROI growth tactics.

In many regions of the world, sparse data on key economic outcomes inhibit the development, targeting and evaluation of public policy1,2. We demonstrate how advancements in satellite imagery and machine learning (ML) can help ameliorate these data and inference challenges. In the context of an expansion of the electrical grid across Uganda, we show how a combination of satellite imagery and computer vision can be used to develop local-level livelihood measurements appropriate for inferring the causal impact of electricity access on livelihoods. We then show how ML-based inference techniques deliver more reliable estimates of the causal impact of electrification than traditional alternatives when applied to these data. We estimate that grid access improves village-level asset wealth in rural Uganda by up to 0.15 standard deviations, more than doubling the growth rate during our study period relative to untreated areas. Our results provide country-scale evidence on the impact of grid-based infrastructure investment and our methods provide a low-cost, generalizable approach to future policy evaluation in data-sparse environments. Advancements in satellite imagery and machine learning can be used to infer the causal impact of electricity access on livelihoods, providing a low-cost, generalizable approach to evaluating public policy in data-spare environments.

Just three days before England kick off their FIFA World Cup campaign against Iran, scientists have a rather pessimistic forecast. The experts, based at London's Alan Turing Institute, say Gareth Southgate's men have only a seven per cent chance of winning the World Cup for the first time since 1966. However, out of the 32 participating teams, England is the fifth mostly likely team to bring home the trophy, just behind the likes of France, Belgium and Brazil. Meanwhile, Wales, which is playing in its first World Cup since 1958, has only a 0.5 per cent chance of winning the tournament – and only a 46 per cent chance of making it out of the group stage. Brazil is most likely to win the World Cup this year, according to the team's research.

While all "metallic miniature humans" are termed as robots, there are distinctions and humanoids are one variation of a robot. Humanoids are generally termed non-living creatures with human features. The term was used to address indigenous people in European colonies. Globally, the first Al-humanoid was named Sophia. Sophia was first actuated on February 14, 2016.