Holl-E is a dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie.
30 PAPERS • NO BENCHMARKS YET
The Open Table-and-Text Question Answering (OTT-QA) dataset contains open questions which require retrieving tables and text from the web to answer. This dataset is re-annotated from the previous HybridQA dataset. The dataset is collected by UCSB NLP group and issued under MIT license.
30 PAPERS • 1 BENCHMARK
The StockNet dataset is a comprehensive dataset for stock movement prediction from tweets and historical stock prices. It consists of two-year price movements from 01/01/2014 to 01/01/2016 of 88 stocks, coming from all the 8 stocks in the Conglomerates sector and the top 10 stocks in capital size in each of the other 8 sectors.
The WCEP dataset for multi-document summarization (MDS) consists of short, human-written summaries about news events, obtained from the Wikipedia Current Events Portal (WCEP), each paired with a cluster of news articles associated with an event. These articles consist of sources cited by editors on WCEP, and are extended with articles automatically obtained from the Common Crawl News dataset.
The Actor-Action Dataset (A2D) by Xu et al. [29] serves as the largest video dataset for the general actor and action segmentation task. It contains 3,782 videos from YouTube with pixel-level labeled actors and their actions. The dataset includes eight different actions, while a total of seven actor classes are considered to perform those actions. We follow [29], who split the dataset into 3,036 training videos and 746 testing videos.
29 PAPERS • 1 BENCHMARK
ArtEmis is a large-scale dataset aimed at providing a detailed understanding of the interplay between visual content, its emotional effect, and explanations for the latter in language. In contrast to most existing annotation datasets in computer vision, this dataset focuses on the affective experience triggered by visual artworks an the annotators were asked to indicate the dominant emotion they feel for a given image and, crucially, to also provide a grounded verbal explanation for their emotion choice. This leads to a rich set of signals for both the objective content and the affective impact of an image, creating associations with abstract concepts (e.g., “freedom” or “love”), or references that go beyond what is directly visible, including visual similes and metaphors, or subjective references to personal experiences.
29 PAPERS • NO BENCHMARKS YET
The Dialog State Tracking Challenges 2 & 3 (DSTC2&3) were research challenge focused on improving the state of the art in tracking the state of spoken dialog systems. State tracking, sometimes called belief tracking, refers to accurately estimating the user's goal as a dialog progresses. Accurate state tracking is desirable because it provides robustness to errors in speech recognition, and helps reduce ambiguity inherent in language within a temporal process like dialog. In these challenges, participants were given labelled corpora of dialogs to develop state tracking algorithms. The trackers were then evaluated on a common set of held-out dialogs, which were released, un-labelled, during a one week period.
29 PAPERS • 2 BENCHMARKS
ECtHR is a dataset comprising European Court of Human Rights cases, including annotations for paragraph-level rationales. This dataset comprises 11k ECtHR cases and can be viewed as an enriched version of the ECtHR dataset of Chalkidis et al. (2019), which did not provide ground truth for alleged article violations (articles discussed) and rationales. It is released with silver rationales obtained from references in court decisions, and gold rationales provided by ECHR-experienced lawyers
ImageNet-P consists of noise, blur, weather, and digital distortions. The dataset has validation perturbations; has difficulty levels; has CIFAR-10, Tiny ImageNet, ImageNet 64 × 64, standard, and Inception-sized editions; and has been designed for benchmarking not training networks. ImageNet-P departs from ImageNet-C by having perturbation sequences generated from each ImageNet validation image. Each sequence contains more than 30 frames, so to counteract an increase in dataset size and evaluation time only 10 common perturbations are used.
MAD (Movie Audio Descriptions) is an automatically curated large-scale dataset for the task of natural language grounding in videos or natural language moment retrieval. MAD exploits available audio descriptions of mainstream movies. Such audio descriptions are redacted for visually impaired audiences and are therefore highly descriptive of the visual content being displayed. MAD contains over 384,000 natural language sentences grounded in over 1,200 hours of video, and provides a unique setup for video grounding as the visual stream is truly untrimmed with an average video duration of 110 minutes. 2 orders of magnitude longer than legacy datasets.
MeQSum is a dataset for medical question summarization. It contains 1,000 summarized consumer health questions.
PMC-VQA is a large-scale medical visual question-answering dataset that contains 227k VQA pairs of 149k images that cover various modalities or diseases. The question-answer pairs are generated from PMC-OA.
29 PAPERS • 3 BENCHMARKS
The HELP dataset is an automatically created natural language inference (NLI) dataset that embodies the combination of lexical and logical inferences focusing on monotonicity (i.e., phrase replacement-based reasoning). The HELP (Ver.1.0) has 36K inference pairs consisting of upward monotone, downward monotone, non-monotone, conjunction, and disjunction.
28 PAPERS • 1 BENCHMARK
The Hallmarks of Cancer (*HOC) corpus consists of 1852 PubMed publication abstracts manually annotated by experts according to the Hallmarks of Cancer taxonomy. The taxonomy consists of 37 classes in a hierarchy. Zero or more class labels are assigned to each sentence in the corpus.
The IMAGE-CHAT dataset is a large collection of (image, style trait for speaker A, style trait for speaker B, dialogue between A & B) tuples that we collected using crowd-workers, Each dialogue consists of consecutive turns by speaker A and B. No particular constraints are placed on the kinds of utterance, only that we ask the speakers to both use the provided style trait, and to respond to the given image and dialogue history in an engaging way. The goal is not just to build a diagnostic dataset but a basis for training models that humans actually want to engage with.
28 PAPERS • 2 BENCHMARKS
The MQ2008 dataset is a dataset for Learning to Rank. It contains 800 queries with labelled documents.
28 PAPERS • NO BENCHMARKS YET
MiniF2F is a dataset of formal Olympiad-level mathematics problems statements intended to provide a unified cross-system benchmark for neural theorem proving. The miniF2F benchmark currently targets Metamath, Lean, and Isabelle and consists of 488 problem statements drawn from the AIME, AMC, and the International Mathematical Olympiad (IMO), as well as material from high-school and undergraduate mathematics courses.
The COmmonsense Dataset Adversarially-authored by Humans (CODAH) is an evaluation set for commonsense question-answering in the sentence completion style of SWAG. As opposed to other automatically generated NLI datasets, CODAH is adversarially constructed by humans who can view feedback from a pre-trained model and use this information to design challenging commonsense questions. It contains 2801 questions in total, and uses 5-fold cross validation for evaluation.
27 PAPERS • 2 BENCHMARKS
Contract Understanding Atticus Dataset (CUAD) is a dataset for legal contract review. CUAD was created with dozens of legal experts from The Atticus Project and consists of over 13,000 annotations. The task is to highlight salient portions of a contract that are important for a human to review.
27 PAPERS • NO BENCHMARKS YET
A human-to-human Chinese dialog dataset (about 10k dialogs, 156k utterances), which contains multiple sequential dialogs for every pair of a recommendation seeker (user) and a recommender (bot).
EVALution dataset is evenly distributed among the three classes (hypernyms, co-hyponyms and random) and involves three types of parts of speech (noun, verb, adjective). The full dataset contains a total of 4,263 distinct terms consisting of 2,380 nouns, 958 verbs and 972 adjectives.
It contains manually verified 183K question-answer pairs about more than 18K persons and 24K images. The questions in this dataset require multi-entity, multi-relation and multi-hop reasoning over KG to arrive at an answer. To enable visual named entity linking, it also provides a support set containing reference images of 69K persons harvested from Wikidata as part of the dataset.
Abstract Meaning Representation (AMR) Annotation Release 2.0 was developed by the Linguistic Data Consortium (LDC), SDL/Language Weaver, Inc., the University of Colorado's Computational Language and Educational Research group and the Information Sciences Institute at the University of Southern California. It contains a sembank (semantic treebank) of over 39,260 English natural language sentences from broadcast conversations, newswire, weblogs and web discussion forums.
MR Movie Reviews is a dataset for use in sentiment-analysis experiments. Available are collections of movie-review documents labeled with respect to their overall sentiment polarity (positive or negative) or subjective rating (e.g., "two and a half stars") and sentences labeled with respect to their subjectivity status (subjective or objective) or polarity.
27 PAPERS • 3 BENCHMARKS
Multi-Modal-CelebA-HQ is a large-scale face image dataset that has 30,000 high-resolution face images selected from the CelebA dataset by following CelebA-HQ. Each image has high-quality segmentation mask, sketch, descriptive text, and image with transparent background.
The Query-based Video Highlights (QVHighlights) dataset is a dataset for detecting customized moments and highlights from videos given natural language (NL). It consists of over 10,000 YouTube videos, covering a wide range of topics, from everyday activities and travel in lifestyle vlog videos to social and political activities in news videos. Each video in the dataset is annotated with: (1) a human-written free-form NL query, (2) relevant moments in the video w.r.t. the query, and (3) five-point scale saliency scores for all query-relevant clips.
27 PAPERS • 4 BENCHMARKS
Sentiment analysis of codemixed tweets.
The TIMIT Acoustic-Phonetic Continuous Speech Corpus is a standard dataset used for evaluation of automatic speech recognition systems. It consists of recordings of 630 speakers of 8 dialects of American English each reading 10 phonetically-rich sentences. It also comes with the word and phone-level transcriptions of the speech.
27 PAPERS • 5 BENCHMARKS
WI-LOCNESS is part of the Building Educational Applications 2019 Shared Task for Grammatical Error Correction. It consists of two datasets:
WikiEvents is a document-level event extraction benchmark dataset which includes complete event and coreference annotation.
The WoZ 2.0 dataset is a newer dialogue state tracking dataset whose evaluation is detached from the noisy output of speech recognition systems. Similar to DSTC2, it covers the restaurant search domain and has identical evaluation.
27 PAPERS • 1 BENCHMARK
The Extreme Summarization (XSum) dataset is a dataset for evaluation of abstractive single-document summarization systems. The goal is to create a short, one-sentence new summary answering the question “What is the article about?”. The dataset consists of 226,711 news articles accompanied with a one-sentence summary. The articles are collected from BBC articles (2010 to 2017) and cover a wide variety of domains (e.g., News, Politics, Sports, Weather, Business, Technology, Science, Health, Family, Education, Entertainment and Arts). The official random split contains 204,045 (90%), 11,332 (5%) and 11,334 (5) documents in training, validation and test sets, respectively.
27 PAPERS • 6 BENCHMARKS
Natural Language Decathlon Benchmark (decaNLP) is a challenge that spans ten tasks: question answering, machine translation, summarization, natural language inference, sentiment analysis, semantic role labeling, zero-shot relation extraction, goal-oriented dialogue, semantic parsing, and commonsense pronoun resolution. The tasks as cast as question answering over a context.
The 20 Newsgroups data set is a collection of approximately 20,000 newsgroup documents, partitioned (nearly) evenly across 20 different newsgroups.
26 PAPERS • 6 BENCHMARKS
ContractNLI is a dataset for document-level natural language inference (NLI) on contracts whose goal is to automate/support a time-consuming procedure of contract review. In this task, a system is given a set of hypotheses (such as “Some obligations of Agreement may survive termination.”) and a contract, and it is asked to classify whether each hypothesis is entailed by, contradicting to or not mentioned by (neutral to) the contract as well as identifying evidence for the decision as spans in the contract.
26 PAPERS • NO BENCHMARKS YET
ConvFinQA is a dataset designed to study the chain of numerical reasoning in conversational question answering. The dataset contains 3892 conversations containing 14115 questions where 2715 of the conversations are simple conversations, and the rest 1,177 are hybrid conversations.
26 PAPERS • 2 BENCHMARKS
Evidence Inference is a corpus for this task comprising 10,000+ prompts coupled with full-text articles describing RCTs.
FakeNewsNet is collected from two fact-checking websites: GossipCop and PolitiFact containing news contents with labels annotated by professional journalists and experts, along with social context information.
Current visual question answering (VQA) tasks mainly consider answering human-annotated questions for natural images in the daily-life context. Icon question answering (IconQA) is a benchmark which aims to highlight the importance of abstract diagram understanding and comprehensive cognitive reasoning in real-world diagram word problems. For this benchmark, a large-scale IconQA dataset is built that consists of three sub-tasks: multi-image-choice, multi-text-choice, and filling-in-the-blank. Compared to existing VQA benchmarks, IconQA requires not only perception skills like object recognition and text understanding, but also diverse cognitive reasoning skills, such as geometric reasoning, commonsense reasoning, and arithmetic reasoning.
26 PAPERS • 1 BENCHMARK
A new multitask action quality assessment (AQA) dataset, the largest to date, comprising of more than 1600 diving samples; contains detailed annotations for fine-grained action recognition, commentary generation, and estimating the AQA score. Videos from multiple angles provided wherever available.
PopQA is an open-domain QA dataset with 14k QA pairs with fine-grained Wikidata entity ID, Wikipedia page views, and relationship type information.
QuaRTz is a crowdsourced dataset of 3864 multiple-choice questions about open domain qualitative relationships. Each question is paired with one of 405 different background sentences (sometimes short paragraphs).
The SentiCap dataset contains several thousand images with captions with positive and negative sentiments. These sentimental captions are constructed by the authors by re-writing factual descriptions. In total there are 2000+ sentimental captions.
VALUE is a Video-And-Language Understanding Evaluation benchmark to test models that are generalizable to diverse tasks, domains, and datasets. It is an assemblage of 11 VidL (video-and-language) datasets over 3 popular tasks: (i) text-to-video retrieval; (ii) video question answering; and (iii) video captioning. VALUE benchmark aims to cover a broad range of video genres, video lengths, data volumes, and task difficulty levels. Rather than focusing on single-channel videos with visual information only, VALUE promotes models that leverage information from both video frames and their associated subtitles, as well as models that share knowledge across multiple tasks.
VisualMRC is a visual machine reading comprehension dataset that proposes a task: given a question and a document image, a model produces an abstractive answer.
WikiReading is a large-scale natural language understanding task and publicly-available dataset with 18 million instances. The task is to predict textual values from the structured knowledge base Wikidata by reading the text of the corresponding Wikipedia articles. The task contains a rich variety of challenging classification and extraction sub-tasks, making it well-suited for end-to-end models such as deep neural networks (DNNs).
Adversarial GLUE (AdvGLUE) is a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks. In particular, we systematically apply 14 textual adversarial attack methods to GLUE tasks to construct AdvGLUE, which is further validated by humans for reliable annotations.
25 PAPERS • 1 BENCHMARK
Dataset contains 33,010 molecule-description pairs split into 80\%/10\%/10\% train/val/test splits. The goal of the task is to retrieve the relevant molecule for a natural language description. It is defined as follows:
25 PAPERS • 4 BENCHMARKS