Related papers: Encoding Multi-Domain Scientific Papers by Ensembl…
Code-switching (CS) occurs when a speaker alternates words of two or more languages within a single sentence or across sentences. Automatic speech recognition (ASR) of CS speech has to deal with two or more languages at the same time. In…
For many text classification tasks, there is a major problem posed by the lack of labeled data in a target domain. Although classifiers for a target domain can be trained on labeled text data from a related source domain, the accuracy of…
We investigate pre-training techniques for abstractive multi-document summarization (MDS), which is much less studied than summarizing single documents. Though recent work has demonstrated the effectiveness of highlighting information…
Clinical trials are central to medical progress because they help improve understanding of human health and the healthcare system. They play a key role in discovering new ways to detect, prevent, or treat diseases, and it is essential that…
Ensembling BERT models often significantly improves accuracy, but at the cost of significantly more computation and memory footprint. In this work, we propose Multi-CLS BERT, a novel ensembling method for CLS-based prediction tasks that is…
Figures are essential channels for densely communicating complex ideas in scientific papers. Previous work in automatically generating figure captions has been largely unsuccessful and has defaulted to using single-layer LSTMs, which no…
Structured text understanding on Visually Rich Documents (VRDs) is a crucial part of Document Intelligence. Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task. Most existing…
International Classification of Diseases (ICD) coding assigns diagnosis codes to clinical documents and is essential for healthcare billing and clinical analysis. Reliable coding requires that each predicted code be supported by explicit…
Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…
The recent vision transformer(i.e.for image classification) learns non-local attentive interaction of different patch tokens. However, prior arts miss learning the cross-scale dependencies of different pixels, the semantic correspondence of…
The emergence of knowledge graphs in the scholarly communication domain and recent advances in artificial intelligence and natural language processing bring us closer to a scenario where intelligent systems can assist scientists over a…
Open-domain extractive question answering works well on textual data by first retrieving candidate texts and then extracting the answer from those candidates. However, some questions cannot be answered by text alone but require information…
Legal documents pose unique challenges for text classification due to their domain-specific language and often limited labeled data. This paper proposes a hybrid approach for classifying legal texts by combining unsupervised topic and graph…
Text alignment finds application in tasks such as citation recommendation and plagiarism detection. Existing alignment methods operate at a single, predefined level and cannot learn to align texts at, for example, sentence and document…
Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…
Citation text plays a pivotal role in elucidating the connection between scientific documents, demanding an in-depth comprehension of the cited paper. Constructing citations is often time-consuming, requiring researchers to delve into…
This paper summarizes the CLaC submission for the MultiCoNER 2 task which concerns the recognition of complex, fine-grained named entities. We compare two popular approaches for NER, namely Sequence Labeling and Span Prediction. We find…
Objective: Translational science aims at "translating" basic scientific discoveries into clinical applications. The identification of translational science has practicality such as evaluating the effectiveness of investments made into large…
Recent advancements in deep learning techniques have transformed the area of semantic text matching. However, most state-of-the-art models are designed to operate with short documents such as tweets, user reviews, comments, etc. These…
Tagging news articles or blog posts with relevant tags from a collection of predefined ones is coined as document tagging in this work. Accurate tagging of articles can benefit several downstream applications such as recommendation and…