📝 Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap 📚👾👋

"Text-to-OverpassQL is a task to generate Overpass queries from natural language inputs and to execute them against OpenStreetMap's database in order to retrieve results." [gal30b+] 🤖 #CL #AI #CY #DB #HC

⚙️ https://github.com/raphael-sch/OverpassNL
🔗 https://arxiv.org/abs/2308.16060v1 #arxiv

📝 A Critical Analysis of the What3Words Geocoding Algorithm 👋

"Uses triples of words to identify locations and it has grown rapidly in popularity over the past few years and is used in logistical applications worldwide, including by emergency services." [gal30b+] 🤖 #HC #CY

⚙️ https://github.com/rudyarthur/w3wanalysis
🔗 https://arxiv.org/abs/2308.16025v1 #arxiv

📝 AI-Based Facial Emotion Recognition Solutions for Education: A Study of Teacher-User and Other Categories 👾🔭👋

"Artificial intelligence-based facial emotion recognition (FER) systems are computer software programs that are designed to detect, recognise and interpret human facial expressions in digital images or video." [gal30b+] 🤖 #AI #CV #CY #HC

🔗 https://arxiv.org/abs/2308.15119v1 #arxiv

📝 Uncovering the Unseen: Discover Hidden Intentions by Micro-Behavior Graph Reasoning 🔭

"First extracts the micro-behavior features and uses a graph structure to reason about hidden intentions by using micro-behavior features, which is different from most previous works that directly use micro-behavior features to predict hidden intentions." [gal30b+] 🤖 #CV #CY

🔗 https://arxiv.org/abs/2308.15169v1 #arxiv

📝 Redefining Computer Science Education: Code-Centric to Natural Language Programming with AI-Based No-Code Platforms 👋

"AI-based no-code platforms allow users to ask and answer questions, with the hope of getting a response, in the form of code, from a computer." [gal30b+] 🤖 #HC #CY

🔗 https://arxiv.org/abs/2308.13539v1 #arxiv

📝 Prediction Without Preclusion: Recourse Verification with Reachable Sets 🧠

"Develops tools to verify a model’s recourse by checking the existence of a path of actions that leads to an alternate prediction under a set of user-specified actionability constraints." [gal30b+] 🤖 #LG #CY

🔗 https://arxiv.org/abs/2308.12820v1 #arxiv

📝 The Challenges of Machine Learning for Trust and Safety: A Case Study on Misinformation Detection 🧠📚

"Analyzes 270 well-cited papers and identify shortcomings in the literature that call into question claimed performance and practicality of automated misinformation detection models." [gal30b+] 🤖 #LG #CL #CY

⚙️ https://github.com/citp/sok_misinformation
🔗 https://arxiv.org/abs/2308.12215v1 #arxiv

📝 From Instructions to Intrinsic Human Values -- A Survey of Alignment Goals for Big Models 👾📚

"Investigates related works from two perspectives: the definition of alignment goals and alignment evaluation, encompassing three distinct levels of alignment goals and revealing a goal transformation from fundamental abilities to value orientation." [gal30b+] 🤖 #AI #CL #CY

⚙️ https://github.com/ValueCompass/AlignmentGoal-Survey
🔗 https://arxiv.org/abs/2308.12014v1 #arxiv

📝 When Are Two Lists Better Than One?: Benefits and Harms in Joint Decision-Making 🧠👋

"By choosing a subset of size k, the human-algorithm team can increase the probability of picking the best item out of the n items over that of either the human or algorithm acting alone." [gal30b+] 🤖 #LG #CY #HC

⚙️ https://github.com/kpdonahue/benefits_harms_joint_decision_making
🔗 https://arxiv.org/abs/2308.11721v1 #arxiv

📝 Addressing Selection Bias in Computerized Adaptive Testing: A User-Wise Aggregate Influence Function Approach 🧠

"Shows that this poses a unique challenge due to the inherent selection bias introduced by CAT, i, e, more proficient students will receive harder questions." [gal30b+] 🤖 #LG #CY

⚙️ https://github.com/riiid/UserAIF
🔗 https://arxiv.org/abs/2308.11912v1 #arxiv

📝 LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models 📚👾

"LegalBench consists of 162 tasks covering 6 different types of legal reasoning, designed and hand-crafted by legal professionals, and evaluated against 20 open-source and commercial language models." [gal30b+] 🤖 #CL #AI #CY

⚙️ https://github.com/HazyResearch/legalbench/
🔗 https://arxiv.org/abs/2308.11462v1 #arxiv

📝 A Comparative Analysis of the Capabilities of Nature-Inspired Feature Selection Algorithms in Predicting Student Performance 🧠👾

"The NIA-based ensemble approach leverages the ability of NIAs to identify a set of features that are highly correlated with the target variable and uncorrelated with one another, while also using the ability of traditional ML algorithms to build classification models." [gal30b+] 🤖 #LG #AI #CY

🔗 https://arxiv.org/abs/2308.08574v1 #arxiv

📝 Human-Centered NLP Fact-Checking: Co-Designing with Fact-Checkers Using Matchmaking for AI 👋📚

"Uses a co-design method, Matchmaking for AI, which facilitates professional fact-checkers, designers, and NLP researchers to collaboratively discover what fact-checker needs should be addressed by technology and how." [gal30b+] 🤖 #HC #CL #CY

🔗 https://arxiv.org/abs/2308.07213v1 #arxiv

📝 SST: A Simplified Swin Transformer-Based Model for Taxi Destination Prediction Based on Existing Trajectory 🔭

"Simplified Swin Transformer (SST) is an architecture that does not use the shifted window idea as in traditional Swin Transformer, as trajectory data is consecutive in nature, which makes SST more suitable to predict the destination of taxi trajectories." [gal30b+] 🤖 #CV #CY

🔗 https://arxiv.org/abs/2308.07555v1 #arxiv

📝 Analytical Techniques to Support Hospital Case Mix Planning 👾

"Supports the user in performing quantitative assessments of hospital capacity and provides further situational awareness around hospital capacity by reporting informative metrics of difference and reports the impact of case mix modifications on the other types of patient present." [gal30b+] 🤖 #AI #CY

🔗 https://arxiv.org/abs/2308.07323v1 #arxiv

📝 Finding Already Debunked Narratives via Multistage Retrieval: Enabling Cross-Lingual, Cross-Dataset and Zero-Shot Learning 📚💿🧠

"Proposes a novel multistage framework for cross-lingual retrieval of already debunked narratives from fact-checking articles written in English using tweets as queries, which divides the task into two stages: refinement and re-ranking." [gal30b+] 🤖 #CL #CY #IR #LG #SI

🔗 https://arxiv.org/abs/2308.05680v1 #arxiv

📝 Finding Already Debunked Narratives via Multistage Retrieval: Enabling Cross-Lingual, Cross-Dataset and Zero-Shot Learning 📚💿🧠

"The task of retrieving already debunked narratives aims to detect stories that have already been fact-checked (see Figure) using tweets as queries to a database of fact-checking articles." [gal30b+] 🤖 #CL #CY #IR #LG #SI

🔗 https://arxiv.org/abs/2308.05680v1 #arxiv

📝 AI4GCC -- Track 3: Consumption and the Challenges of Multi-Agent RL 👾

"It's very easy to explain, if you want to know how it works, you just have to read the paper, and if you want to know more, you can watch the video." [gal30b+] 🤖 #AI #CY

🔗 https://arxiv.org/abs/2308.05260v1 #arxiv

📝 AI4GCC -- Track 3: Consumption and the Challenges of Multi-Agent RL 👾

"The AI4GCC competition consists of a set of 25 negotiation scenarios, with a corresponding set of training, validation, and test data for each scenario." [gal30b+] 🤖 #AI #CY

🔗 https://arxiv.org/abs/2308.05260v1 #arxiv

📝 Why Data Science Projects Fail 🧠

"Data can be collected from various sources like sensors, websites, social networking sites etc, and they can be stored in the form of a database using the appropriate software." [gal30b+] 🤖 #LG #CY #DB

🔗 https://arxiv.org/abs/2308.04896v1 #arxiv