Related papers: Unsupervised Pre-training for Biomedical Question …
Semi-supervised learning approaches train on small sets of labeled data along with large sets of unlabeled data. Self-training is a semi-supervised teacher-student approach that often suffers from the problem of "confirmation bias" that…
Supervised models trained to predict properties from representations have been achieving high accuracy on a variety of tasks. For instance, the BERT family seems to work exceptionally well on the downstream task from NER tagging to the…
Predicting drug response in patients from preclinical data remains a major challenge in precision oncology due to the substantial biological gap between in vitro cell lines and patient tumors. Rather than aiming to improve absolute in vitro…
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases. Although recent studies explored using neural network…
Substantial improvements have been made in machine reading comprehension, where the machine answers questions based on a given context. Current state-of-the-art models even surpass human performance on several benchmarks. However, their…
The overwhelming amount of biomedical scientific texts calls for the development of effective language models able to tackle a wide range of biomedical natural language processing (NLP) tasks. The most recent dominant approaches are…
Pre-trained self-supervised models such as BERT have achieved striking success in learning sequence representations, especially for natural language processing. These models typically corrupt the given sequences with certain types of noise,…
Emotion recognition is a challenging task due to limited availability of in-the-wild labeled datasets. Self-supervised learning has shown improvements on tasks with limited labeled datasets in domains like speech and natural language.…
This work presents biomedical and clinical language models for Spanish by experimenting with different pretraining choices, such as masking at word and subword level, varying the vocabulary size and testing with domain data, looking for…
We present ViLBERT (short for Vision-and-Language BERT), a model for learning task-agnostic joint representations of image content and natural language. We extend the popular BERT architecture to a multi-modal two-stream model, pro-cessing…
Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks. However, existing models require a large amount of parallel image-caption data for pre-training. Such data are costly to…
We present \emph{TabRet}, a pre-trainable Transformer-based model for tabular data. TabRet is designed to work on a downstream task that contains columns not seen in pre-training. Unlike other methods, TabRet has an extra learning step…
Question-answering (QA) data often encodes essential information in many facets. This paper studies a natural question: Can we get supervision from QA data for other tasks (typically, non-QA ones)? For example, {\em can we use QAMR (Michael…
Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain corpora, such as newswire and Web. A prevailing…
The amount of labeled data to train models for speech tasks is limited for most languages, however, the data scarcity is exacerbated for speech translation which requires labeled data covering two different languages. To address this issue,…
Biomedical literature is a rapidly expanding field of science and technology. Classification of biomedical texts is an essential part of biomedicine research, especially in the field of biology. This work proposes the fine-tuned DistilBERT,…
Training a neural network-based biomedical named entity recognition (BioNER) model usually requires extensive and costly human annotations. While several studies have employed multi-task learning with multiple BioNER datasets to reduce…
We present ReasonBert, a pre-training method that augments language models with the ability to reason over long-range relations and multiple, possibly hybrid contexts. Unlike existing pre-training methods that only harvest learning signals…
We present two approaches that use unlabeled data to improve sequence learning with recurrent networks. The first approach is to predict what comes next in a sequence, which is a conventional language model in natural language processing.…
We present MetricBERT, a BERT-based model that learns to embed text under a well-defined similarity metric while simultaneously adhering to the ``traditional'' masked-language task. We focus on downstream tasks of learning similarities for…