The MNIST database (Modified National Institute of Standards and Technology database) is a large collection of handwritten digits. It has a training set of 60,000 examples, and a test set of 10,000 examples. It is a subset of a larger NIST Special Database 3 (digits written by employees of the United States Census Bureau) and Special Database 1 (digits written by high school students) which contain monochrome images of handwritten digits. The digits have been size-normalized and centered in a fixed-size image. The original black and white (bilevel) images from NIST were size normalized to fit in a 20x20 pixel box while preserving their aspect ratio. The resulting images contain grey levels as a result of the anti-aliasing technique used by the normalization algorithm. the images were centered in a 28x28 image by computing the center of mass of the pixels, and translating the image so as to position this point at the center of the 28x28 field.
5,751 PAPERS • 42 BENCHMARKS
CoNLL-2003 is a named entity recognition dataset released as a part of CoNLL-2003 shared task: language-independent named entity recognition. The data consists of eight files covering two languages: English and German. For each of the languages there is a training file, a development file, a test file and a large file with unannotated data.
486 PAPERS • 11 BENCHMARKS
The Universal Dependencies (UD) project seeks to develop cross-linguistically consistent treebank annotation of morphology and syntax for multiple languages. The first version of the dataset was released in 2015 and consisted of 10 treebanks over 10 languages. Version 2.7 released in 2020 consists of 183 treebanks over 104 languages. The annotation consists of UPOS (universal part-of-speech tags), XPOS (language-specific part-of-speech tags), Feats (universal morphological features), Lemmas, dependency heads and universal dependency labels.
471 PAPERS • 8 BENCHMARKS
The NCBI Disease corpus consists of 793 PubMed abstracts, which are separated into training (593), development (100) and test (100) subsets. The NCBI Disease corpus is annotated with disease mentions, using concept identifiers from either MeSH or OMIM.
93 PAPERS • 2 BENCHMARKS
This shared task focuses on identifying unusual, previously-unseen entities in the context of emerging discussions. Named entities form the basis of many modern approaches to other tasks (like event clustering and summarisation), but recall on them is a real problem in noisy text - even among annotators. This drop tends to be due to novel entities and surface forms. Take for example the tweet “so.. kktny in 30 mins?” - even human experts find entity kktny hard to detect and resolve. This task will evaluate the ability to detect and classify novel, emerging, singleton named entities in noisy text.
75 PAPERS • 2 BENCHMARKS
The shared task of CoNLL-2002 concerns language-independent named entity recognition. The types of named entities include: persons, locations, organizations and names of miscellaneous entities that do not belong to the previous three groups. The participants of the shared task were offered training and test data for at least two languages. Information sources other than the training data might have been used in this shared task.
64 PAPERS • 3 BENCHMARKS
The Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME) benchmark was introduced to encourage more research on multilingual transfer learning,. XTREME covers 40 typologically diverse languages spanning 12 language families and includes 9 tasks that require reasoning about different levels of syntax or semantics.
34 PAPERS • 2 BENCHMARKS
Consists of a dataset with 1000 whole scanned receipt images and annotations for the competition on scanned receipts OCR and key information extraction (SROIE).
33 PAPERS • 2 BENCHMARKS
OCR is inevitably linked to NLP since its final output is in text. Advances in document intelligence are driving the need for a unified technology that integrates OCR with various NLP tasks, especially semantic parsing. Since OCR and semantic parsing have been studied as separate tasks so far, the datasets for each task on their own are rich, while those for the integrated post-OCR parsing tasks are relatively insufficient. In this study, we publish a consolidated dataset for receipt parsing as the first step towards post-OCR parsing tasks. The dataset consists of thousands of Indonesian receipts, which contains images and box/text annotations for OCR, and multi-level semantic labels for parsing. The proposed dataset can be used to address various OCR and parsing tasks.
32 PAPERS • 2 BENCHMARKS
CoNLL++ is a corrected version of the CoNLL03 NER dataset where 5.38% of the test sentences have been fixed.
30 PAPERS • 3 BENCHMARKS
WikiAnn is a dataset for cross-lingual name tagging and linking based on Wikipedia articles in 295 languages.
24 PAPERS • 7 BENCHMARKS
Korean Language Understanding Evaluation (KLUE) benchmark is a series of datasets to evaluate natural language understanding capability of Korean language models. KLUE consists of 8 diverse and representative tasks, which are accessible to anyone without any restrictions. With ethical considerations in mind, we deliberately design annotation guidelines to obtain unambiguous annotations for all datasets. Furthermore, we build an evaluation system and carefully choose evaluations metrics for every task, thus establishing fair comparison across Korean language models.
14 PAPERS • 2 BENCHMARKS
XGLUE is an evaluation benchmark XGLUE,which is composed of 11 tasks that span 19 languages. For each task, the training data is only available in English. This means that to succeed at XGLUE, a model must have a strong zero-shot cross-lingual transfer capability to learn from the English data of a specific task and transfer what it learned to other languages. Comparing to its concurrent work XTREME, XGLUE has two characteristics: First, it includes cross-lingual NLU and cross-lingual NLG tasks at the same time; Second, besides including 5 existing cross-lingual tasks (i.e. NER, POS, MLQA, PAWS-X and XNLI), XGLUE selects 6 new tasks from Bing scenarios as well, including News Classification (NC), Query-Ad Matching (QADSM), Web Page Ranking (WPR), QA Matching (QAM), Question Generation (QG) and News Title Generation (NTG). Such diversities of languages, tasks and task origin provide a comprehensive benchmark for quantifying the quality of a pre-trained model on cross-lingual natural lan
14 PAPERS • 3 BENCHMARKS
JNLPBA is a biomedical dataset that comes from the GENIA version 3.02 corpus (Kim et al., 2003). It was created with a controlled search on MEDLINE. From this search 2,000 abstracts were selected and hand annotated according to a small taxonomy of 48 classes based on a chemical classification. 36 terminal classes were used to annotate the GENIA corpus.
13 PAPERS • 3 BENCHMARKS
Is an acronym disambiguation (AD) dataset for scientific domain with 62,441 samples which is significantly larger than the previous scientific AD dataset.
8 PAPERS • 1 BENCHMARK
A dataset of financial agreements made public through U.S. Security and Exchange Commission (SEC) filings. Eight documents (totalling 54,256 words) were randomly selected for manual annotation, based on the four NE types provided in the CoNLL-2003 dataset: LOCATION (LOC), ORGANISATION (ORG), PERSON (PER), and MISCELLANEOUS (MISC).
4 PAPERS • 1 BENCHMARK
Paper: Improved automatic keyword extraction given more linguistic knowledge Doi: 10.3115/1119355.1119383
4 PAPERS • 4 BENCHMARKS
Introduced by Krallinger et al. in The CHEMDNER corpus of chemicals and drugs and its annotation principles
3 PAPERS • 2 BENCHMARKS
TaPaCo is a freely available paraphrase corpus for 73 languages extracted from the Tatoeba database.
3 PAPERS • 1 BENCHMARK
WikiNEuRal is a high-quality automatically-generated dataset for Multilingual Named Entity Recognition.
2 PAPERS • 9 BENCHMARKS
Dataset of Legal Documents consists of court decisions from 2017 and 2018 were selected for the dataset, published online by the Federal Ministry of Justice and Consumer Protection. The documents originate from seven federal courts: Federal Labour Court (BAG), Federal Fiscal Court (BFH), Federal Court of Justice (BGH), Federal Patent Court (BPatG), Federal Social Court (BSG), Federal Constitutional Court (BVerfG) and Federal Administrative Court (BVerwG).
1 PAPER • 1 BENCHMARK
FiNER-139 is comprised of 1.1M sentences annotated with eXtensive Business Reporting Language (XBRL) tags extracted from annual and quarterly reports of publicly-traded companies in the US. Unlike other entity extraction tasks, like named entity recognition (NER) or contract element extraction, which typically require identifying entities of a small set of common types (e.g., persons, organizations), FiNER-139 uses a much larger label set of 139 entity types. Another important difference from typical entity extraction is that FiNER focuses on numeric tokens, with the correct tag depending mostly on context, not the token itself.
1 PAPER • 1 BENCHMARK
LeNER-Br is a dataset for named entity recognition (NER) in Brazilian Legal Text.
1 PAPER • 3 BENCHMARKS
PLOD: An Abbreviation Detection Dataset
1 PAPER • 2 BENCHMARKS