相关论文: Talk2Ref: A Dataset for Reference Prediction from …
Relevant information in documents is often summarized in tables, helping the reader to identify useful facts. Most benchmark datasets support either document layout analysis or table understanding, but lack in providing data to apply both…
Identifying keyphrases (KPs) from text documents is a fundamental task in natural language processing and information retrieval. Vast majority of the benchmark datasets for this task are from the scientific domain containing only the…
Open conversations are one of the most engaging forms of teaching. However, creating those conversations in educational software is a complex endeavor, especially if we want to address the needs of different audiences. While language models…
In this paper, we introduce SciGen, a new challenge dataset for the task of reasoning-aware data-to-text generation consisting of tables from scientific articles and their corresponding descriptions. Describing scientific tables goes beyond…
Learned representations of scientific documents can serve as valuable input features for downstream tasks without further fine-tuning. However, existing benchmarks for evaluating these representations fail to capture the diversity of…
In an article written five years ago [arXiv:0809.0522], we described a method for predicting which scientific papers will be highly cited in the future, even if they are currently not highly cited. Applying the method to real citation data…
While acoustic expressiveness has long been studied in expressive text-to-speech (ETTS), the inherent expressiveness in text lacks sufficient attention, especially for ETTS of artistic works. In this paper, we introduce StoryTTS, a highly…
Comparing research papers is a conventional method to demonstrate progress in experimental research. We present COMPARE, a taxonomy and a dataset of comparison discussions in peer reviews of research papers in the domain of experimental…
Pre-training on larger datasets with ever increasing model size is now a proven recipe for increased performance across almost all NLP tasks. A notable exception is information retrieval, where additional pre-training has so far failed to…
Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety of language understanding tasks. However, it is yet unclear…
DBLP is the largest open-access repository of scientific articles on computer science and provides metadata associated with publications, authors, and venues. We retrieved more than 6 million publications from DBLP and extracted pertinent…
A citation is a well-established mechanism for connecting scientific artifacts. Citation networks are used by citation analysis for a variety of reasons, prominently to give credit to scientists' work. However, because of current citation…
Conversion of spoken mathematical expressions is a challenging task that involves transcribing speech into a strictly structured symbolic representation while addressing the ambiguity inherent in the pronunciation of equations. Although…
Existing text simplification or paraphrase datasets mainly focus on sentence-level text generation in a general domain. These datasets are typically developed without using domain knowledge. In this paper, we release a novel dataset,…
Political discourse datasets are important for gaining political insights, analyzing communication strategies or social science phenomena. Although numerous political discourse corpora exist, comprehensive, high-quality, annotated datasets…
This work presents a speech-to-text system "Pisets" for scientists and journalists which is based on a three-component architecture aimed at improving speech recognition accuracy while minimizing errors and hallucinations associated with…
Citations are the cornerstone of knowledge propagation and the primary means of assessing the quality of research, as well as directing investments in science. Science is increasingly becoming "data-intensive", where large volumes of data…
Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the…
We introduce and analyse a simple probabilistic model of article production and citation behavior that explicitly assumes that there is no decline in citability of a given article over time. It makes predictions about the number and age of…
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing language-model generation pipelines rely on unconstrained text…