Related papers: Longtonotes: OntoNotes with Longer Coreference Cha…
Knowledge graphs capture entities and relations from long documents and can facilitate reasoning in many downstream applications. Extracting compact knowledge graphs containing only salient entities and relations is important but…
Document structure is critical for efficient information consumption. However, it is challenging to encode it efficiently into the modern Transformer architecture. In this work, we present HIBRIDS, which injects Hierarchical Biases foR…
Multiple entities in a document generally exhibit complex inter-sentence relations, and cannot be well handled by existing relation extraction (RE) methods that typically focus on extracting intra-sentence relations for single entity pairs.…
Since their release, Transformers have revolutionized many fields from Natural Language Understanding to Computer Vision. Document Understanding (DU) was not left behind with first Transformer based models for DU dating from late 2019.…
We propose a dataset for event coreference resolution, which is based on random samples drawn from multiple sources, languages, and countries. Early scholarship on event information collection has not quantified the contribution of event…
The annotation of textual information is a fundamental activity in Linguistics and Computational Linguistics. This article presents various observations on annotations. It approaches the topic from several angles including Hypertext,…
Cross-referencing, which links passages of text to other related passages, can be a valuable study aid for facilitating comprehension of a text. However, cross-referencing requires first, a comprehensive thematic knowledge of the entire…
In this paper, we propose an alternative to deep neural networks for semantic information retrieval for the case of long documents. This new approach exploiting clustering techniques to take into account the meaning of words in Information…
Cross-Lingual SynthDocs is a large-scale synthetic corpus designed to address the scarcity of Arabic resources for Optical Character Recognition (OCR) and Document Understanding (DU). The dataset comprises over 2.5 million of samples,…
This paper proposes a medical text summarization method based on LongFormer, aimed at addressing the challenges faced by existing models when processing long medical texts. Traditional summarization methods are often limited by short-term…
Scientific document understanding is challenging as the data is highly domain specific and diverse. However, datasets for tasks with scientific text require expensive manual annotation and tend to be small and limited to only one or a few…
Large language models (LLMs) are widely applied to data analytics over documents, yet direct reasoning over long, noisy documents remains brittle and error-prone. Hence, we study document question answering (QA) that consolidates dispersed…
The proliferation of hour-long videos (e.g., lectures, podcasts, documentaries) has intensified demand for efficient content structuring. However, existing approaches are constrained by small-scale training with annotations that are typical…
Extending large language models to effectively handle long contexts requires instruction fine-tuning on input sequences of similar length. To address this, we present LongAlign -- a recipe of the instruction data, training, and evaluation…
Retrieval pipelines-an integral component of many machine learning systems-perform poorly in domains where documents are long (e.g., 10K tokens or more) and where identifying the relevant document requires synthesizing information across…
On a wide range of natural language processing and information retrieval tasks, transformer-based models, particularly pre-trained language models like BERT, have demonstrated tremendous effectiveness. Due to the quadratic complexity of the…
Reading comprehension models are based on recurrent neural networks that sequentially process the document tokens. As interest turns to answering more complex questions over longer documents, sequential reading of large portions of text…
How to efficiently generate an accurate, well-structured overview report (ORPT) over thousands of related documents is challenging. A well-structured ORPT consists of sections of multiple levels (e.g., sections and subsections). None of the…
This paper presents a new challenging information extraction task in the domain of materials science. We develop an annotation scheme for marking information on experiments related to solid oxide fuel cells in scientific publications, such…
Ontologies present an attractive technology for describing bio-medicine, because they can be shared, and have rich computational properties. However, they lack the rich expressivity of English and fit poorly with the current scientific…