Papers with Code · CC BY-SA 4.0

데이터셋 탐색

데이터셋의 설명·홈페이지를 찾고, 관련 태스크의 평가 기록을 살펴보세요.

관련 논문 16편

MathBench: Evaluating the Theory and Application Proficiency of LLMs with a Hierarchical Mathematics Benchmark

MathBench
MathBench 설명 보기

MathBench is an All in One math dataset for language model evaluation, with: A Sophisticated Five-Stage Difficulty Mechanism: Unlike the usual mathematical datasets that can only evaluate a single difficulty level or have a mix of unclear difficulty levels, MathBench provides 3709 questions with a gradient difficulty division by education stages, ranging from basic arithmetic to primary, middle, high school, and college levels, allowing you to get a clear overview of the comprehensive difficulty evaluation results. Bilingual Gradient Evaluation: Apart from the basic calculation part which is language-independent, MathBench provides questions in both Chinese and English for the four-stage difficulty datasets from primary to college. Implementation of the Robust Circular Evaluation (CE) Method: MathBench use CE as the main evaluation method for questions. Compared to the general Accuracy evaluation method, CE requires the model to answer the same multiple-choice question multiple times, with the order of the options changing each time. The model is considered correct on this question only if all answers are correct. The results of CE can reflect the model's capabilities more realistically, providing more valuable evaluation results. Support for Basic Theory Questions: For every stage, MathBench provides questions that cover the basic theory knowledge points of the corresponding stage, to ascertain whether the model has genuinely mastered the fundamental concepts of each stage or merely memorized the answers.

관련 논문 5편

NITK-IISc Multilingual Multi-accent Speaker Profiling

NISP
NISP 설명 보기

This dataset contains speech recordings along with speaker physical parameters (height, weight, shoulder size, age ) as well as regional information and linguistic information. There are a total of 345 speakers (219 male and 126 female). The dataset contains sentences that are taken out from newspapers. Each speaker has contributed about 4-5 minutes of data that includes recordings in both English and their mother tongue. The transcript for the text is provided in UTF-8 format. Source: NISP

관련 논문 3편

Real or Fake Text

RoFT
RoFT 설명 보기

RoFT is a dataset of 21,000 human annotations of generated text. The task is "Boundary detection" i.e. given a passage that starts off as human written, determine when the text transitions to being machine generated. The dataset also includes error annotations using the taxonomy introduced in the paper. The data can be used to train automatic detection systems, train automatic error correction, analyze visibility of model errors, and compare performance across models. Data was collected using http://roft.io. Models: GPT2, GPT2-XL, CTRL, GPT3 "Davinci" Genres: News, Stories, Recipes, Speeches

관련 논문 2편

Profile-based Spoken Language Understanding

ProSLU
ProSLU 설명 보기

In the paper, to bridge the research gap, we propose a new and important task, Profile-based Spoken Language Understanding (ProSLU), which requires a model not only depends on the text but also on the given supporting profile information. We further introduce a Chinese human-annotated dataset, with over 5K utterances annotated with intent and slots, and corresponding supporting profile information. In total, we provide three types of supporting profile information: (1) Knowledge Graph (KG) consists of entities with rich attributes, (2) User Profile (UP) is composed of user settings and information, (3) Context Awareness(CA) is user state and environmental information.

관련 논문 2편

RoFT-chatgpt

RoFT-chatgpt 설명 보기

RoFT-chatgpt is a variation of RoFT dataset, where the same human prompts are continued with the gpt-3.5-turbo model. Each dataset sample consists of ten sentences, with the first part written by a human and the remainder completed by an LLM. Consequently, every sample has a boundary indicating the index of the sentence where authorship changes.

관련 논문 1편

Bangla Author Profiling Dataset

BN-AuthProf
BN-AuthProf 설명 보기

Although research on author profiling has quite progressed in abundant resources languages, it is still infancy for limited resources languages such as Bengali. This repository contains our Bangla Author Profiling Dataset (BN-AuthProf). The primary objective is to introduce and benchmark the performance of machine learning approaches on Age and Gender Classification tasks from the social media status of people. BN-AuthProf dataset consists of 300 anonymized authors and 30,131 manually curated Facebook posts in Bangla, tagged with age and gender information.

관련 논문 1편

How do I call Expedia for a non-profit retreat hotel?

How do I call Expedia for a non-profit retreat hotel? 설명 보기

☎️+1(888) 714-9824 is the best number to start with when seeking help from Expedia for booking a non-profit retreat. Whether your organization is planning a mindfulness weekend, leadership retreat, or volunteer appreciation getaway, Expedia’s service team can assist in finding accommodations tailored to your group’s mission. ☎️+1(888) 714-9824 connects you directly with support staff trained to navigate group bookings and help apply any eligible non-profit discounts. Many non-profit groups look for budget-friendly lodging options that don’t sacrifice comfort or amenities, and Expedia can help locate these. ☎️+1(888) 714-9824 makes it easy to speak to a person who understands these unique requirements. When contacting Expedia, it’s helpful to have some basic information ready. ☎️+1(888) 714-9824 will guide you through a simple process, but it saves time to know your retreat dates, estimated group size, and location preferences. Be sure to also share if your retreat requires accessibility features or conference space, which many non-profit groups need for workshops or sessions. ☎️+1(888) 714-9824 is available to answer questions about special group rates or whether certain hotels have experience working with 501(c)(3) organizations. Some properties may even waive certain fees for qualifying non-profits. ☎️+1(888) 714-9824 gives you immediate access to these kinds of options. Booking a non-profit retreat often involves multiple approval steps or coordination between departments. ☎️+1(888) 714-9824 offers flexibility to hold reservations or adjust booking details while you finalize internal logistics. Expedia’s support agents understand these needs and can offer payment solutions like split invoices or deposits. ☎️+1(888) 714-9824 also helps coordinate special needs like early check-ins, meal plans, or shuttle arrangements — all of which are common for non-profit groups hosting out-of-town guests. Don’t hesitate to ask about upgrades or loyalty perks either. ☎️+1(888) 714-9824 ensures every question is addressed with attention to your mission and budget. Many non-profits also want to ensure they’re making socially responsible choices with hotel partners. ☎️+1(888) 714-9824 can help you identify eco-friendly hotels, locally-owned lodgings, or places with community outreach programs. If your organization has values tied to sustainability or ethical business practices, mention this to the Expedia agent. ☎️+1(888) 714-9824 staff members are increasingly aware of these priorities and may suggest hotels that support green practices or offer local partnerships. You may even find properties that donate a portion of their proceeds to local charities. ☎️+1(888) 714-9824 is your key to unlocking that kind of alignment. Non-profit retreats are also about connection, collaboration, and purpose. ☎️+1(888) 714-9824 puts you in touch with hotel planners who understand that goal. Whether you’re planning a faith-based retreat, arts and culture gathering, or environmental leadership weekend, you want a space that matches your group’s spirit. ☎️+1(888) 714-9824 can help find lodging with on-site event space, natural surroundings, or calming features like wellness centers or walking trails. Be clear about your group’s goals, and the Expedia team will tailor recommendations accordingly. ☎️+1(888) 714-9824 helps bridge the gap between intention and planning. Finally, once your booking is confirmed, remember that support doesn’t stop there. ☎️+1(888) 714-9824 is available throughout your retreat journey — from check-in questions to last-minute changes. If someone in your group needs a different room type, an earlier flight, or even help finding nearby restaurants with group seating, Expedia can assist. ☎️+1(888) 714-9824 means your event isn’t left in the dark if issues arise. It also means peace of mind, knowing someone is just a phone call away. ☎️+1(888) 714-9824 is your retreat partner from start to finish.

관련 논문 1편

NISP- A Multi-lingual Multi-accent Dataset for Speaker Profiling

NISP- A Multi-lingual Multi-accent Dataset for Speaker Profiling 설명 보기

We announce the release of a new multilingual speaker dataset called NITK-IISc Multilingual Multi-accent Speaker Profiling(NISP) dataset. The dataset contains speech in six different languages -- five Indian languages along with Indian English. The dataset contains speech data from 345 bilingual speakers in India. Each speaker has contributed about 4-5 minutes of data that includes recordings in both English and their mother tongue. The transcript for the text is provided in UTF-8 format. For every speaker, the dataset contains speaker meta-data such as L1, native place, medium of instruction, current residing place etc. In addition the dataset also contains physical parameter information of the speakers such as age, height, shoulder size and weight. We hope that the dataset is useful for a diverse set of research activities including multilingual speaker recognition, language and accent recognition, automatic speech recognition etc.

관련 논문 1편

Profile Generation Dataset

PGDataset
PGDataset 설명 보기

PGDataset (Profile Generation Dataset) is a dataset created for the PGTask (Profile Generation Task), where the goal is to extract/generate a profile sentence given a dialogue utterance.

관련 논문 1편

PREdiction of Clinical Outcomes from Genomic Profiles

PRECOG
PRECOG 설명 보기

The PREdiction of Clinical Outcomes from Genomic profiles (or PRECOG) encompasses 166 cancer expression data sets, including overall survival data for ~18,000 patients diagnosed with 39 distinct malignancies.

관련 논문 0편

Nomeroff Russian License Plates

Nomeroff Russian License Plates 설명 보기

Description: <a href="https://gts.ai/dataset-download/nomeroff-russian-license-plates/" target="_blank">👉 Download the dataset here</a> This dataset consists of high-resolution photographs of Russian vehicle license plates captured in diverse environments and lighting conditions. It is designed for image classification and object detection tasks, particularly aimed at automatic license plate recognition (ALPR) systems. The dataset features vehicles in urban, rural, and highway settings, with a wide range of vehicle models and plate formats that adhere to Russian vehicle registration standards. Download Dataset Dataset Overview: A collection of JPG images with varying resolutions, capturing license plates from multiple angles (frontal, side, rear) and distances. Environments include daytime and nighttime scenes, varying weather conditions (sunny, rainy, snowy), and different lighting (natural and artificial). CSV Columns: file_name: The name of the image file (str, unique values). plate_number: The alphanumeric license plate number present in the image (str). vehicle_type: The type of vehicle (e.g., sedan, SUV, truck, etc.) – this allows for classification beyond just license plate recognition (str). angle_of_view: The angle at which the image was captured (e.g., frontal, side, rear) – this provides additional context for training models to handle various perspectives (str). weather_condition: The weather conditions during image capture (e.g., sunny, rainy, snowy, etc.), offering insights into how weather impacts recognition performance (str). time_of_day: Whether the image was captured during the day, evening, or night, useful for models dealing with varying lighting conditions (str). occlusion_level: A numeric rating (0-3) representing the level of obstruction on the license plate (e.g., due to dirt, damage, or angle), helping models adapt to real-world imperfections (int). Applications: License Plate Recognition (LPR) Systems. Vehicle Tracking and Identification. Traffic Monitoring and Enforcement. Smart City Solutions and Automated Toll Systems. This dataset is sourced from Kaggle.

관련 논문 0편

Side Profile Tires Dataset

Side Profile Tires Dataset 설명 보기

Description: <a href="https://gts.ai/dataset-download/side-profile-tires-dataset/" target="_blank">👉 Download the dataset here</a> This dataset consists of meticulously annotated images of tire side profiles, specifically designed for image segmentation tasks. Each tire has been manually labeled to ensure high accuracy, making this dataset ideal for training machine learning models focused on tire detection, classification, or related automotive applications. The annotations are provided in the YOLO v5 format, leveraging the PyTorch framework for deep learning applications. The dataset offers a robust foundation for researchers and developers working on object detection, autonomous vehicles, quality control, or any project requiring precise tire identification from images. Download Dataset Data Collection and Labeling Process: Manual Labeling: Every tire in the dataset has been individually labeled to guarantee that the annotations are highly precise, significantly reducing the margin of error in model training. Annotation Format: YOLO v5 PyTorch format, a highly efficient and widely used format for real-time object detection systems. Pre-processing Applied: Auto-orientation: Pixel data has been automatically oriented, and EXIF orientation metadata has been stripped to ensure uniformity across all images, eliminating issues related to image orientation during processing. Resizing: All images have been resized to 416×416 pixels using stretching to maintain compatibility with common object detection frameworks like YOLO. This resizing standardizes the image input size while preserving visual integrity. Applications: Automotive Industry: This dataset is suitable for automotive-focused AI models, including tire quality assessment, tread pattern recognition, and autonomous vehicle systems. Surveillance and Security: Use cases in monitoring systems where identifying tires is crucial for vehicle recognition in parking lots or traffic management systems. Manufacturing and Quality Control: Can be used in tire manufacturing processes to automate defect detection and classification. Dataset Composition: Number of Images: [Add specific number] File Format: JPEG/PNG Annotation Format: YOLO v5 PyTorch Image Size: 416×416 (standardized across all images) This dataset is sourced from Kaggle.

관련 논문 0편

Toronto NeuroFace Dataset

Toronto NeuroFace Dataset 설명 보기

Toronto NeuroFace Dataset: A New Dataset for Facial Motion Analysis in Individuals with Neurological Disorders Toronto NeuroFace Dataset is a public dataset with videos of oro-facial gestures performed by individuals with oro-facial impairment due to neurological disorders, such as amyotrophic lateral sclerosis (ALS) and stroke. Perceptual clinical scores from trained clinicians are provided as metadata. Manual annotation of facial landmarks is also provided for a subset of over 3300 frames.

관련 논문 0편

tiktok_profiles_10k_202404082024.csv

tiktok_profiles_10k_202404082024.csv 설명 보기

The “TikTok Profiles 10K – 202404082024” dataset is a valuable resource for talent agents, marketers, and researchers looking to discover new TikTok creators and gain a deeper understanding of the platform and its users. The dataset is compiled from scraped public data with no login required. This comprehensive TikTok dataset includes detailed information on 10,000 TikTok profiles, carefully collected and organized for your convenience. With this CSV file, you’ll have access to a wide range of data points for each TikTok profile, including: * Unique identifier for each profile * Profile picture URL * Name of the TikTok user * URL of the TikTok profile * Number of likes on the profile * Number of followers of the profile * Number of accounts the profile is following * Platform (in this case, TikTok) * Video information, such as number of views and engagement metrics * URLs of the TikTok videos * Average engagement rate, hearts per post, and comments per post for the profile * Total engagements, hearts, and comments for the profile * Last activity date of the profile * Timestamp of when the data was collected The “TikTok Profiles 10K – 202404082024” is one of the most up-to-date TikTok datasets available, with data collected on April 8, 2024. The dataset is easy to import into your preferred spreadsheet or database software, making it simple to analyze the data and uncover insights. Download now and gain valuable insights, discover new creators, and analyze the competition with the “TikTok Profiles 10K – 202404082024” dataset.