Related papers: BERT's output layer recognizes all hidden layers? …
We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience. Much like in NLP and speech recognition, this Transformer enables classifying complex concepts,…
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural…
Large-scale pre-trained language model such as BERT has achieved great success in language understanding tasks. However, it remains an open question how to utilize BERT for language generation. In this paper, we present a novel approach,…
Large scale self-supervised pre-training of Transformer language models has advanced the field of Natural Language Processing and shown promise in cross-application to the biological `languages' of proteins and DNA. Learning effective…
Pre-training Transformer from large-scale raw texts and fine-tuning on the desired task have achieved state-of-the-art results on diverse NLP tasks. However, it is unclear what the learned attention captures. The attention computed by…
This paper introduces a novel modification of the transformer architecture, tailored for the data-efficient pretraining of language models. This aspect is evaluated by participating in the BabyLM challenge, where our solution won both the…
We introduce the metric using BERT (Bidirectional Encoder Representations from Transformers) (Devlin et al., 2019) for automatic machine translation evaluation. The experimental results of the WMT-2017 Metrics Shared Task dataset show that…
Pre-trained language models (e.g., BERT) have achieved significant success in various natural language processing (NLP) tasks. However, high storage and computational costs obstruct pre-trained language models to be effectively deployed on…
Language Models (LMs) such as BERT, have been shown to perform well on the task of identifying Named Entities (NE) in text. A BERT LM is typically used as a classifier to classify individual tokens in the input text, or to classify spans of…
We study whether in-domain pretraining of Bidirectional Encoder Representations from Transformer (BERT) model improves subdomain-level detection of exfiltration at low false positive rates. While previous work mostly examines fine-tuned…
Newly-introduced deep learning architectures, namely BERT, XLNet, RoBERTa and ALBERT, have been proved to be robust on several NLP tasks. However, the datasets trained on these architectures are fixed in terms of size and generalizability.…
Currently, the most widespread neural network architecture for training language models is the so called BERT which led to improvements in various Natural Language Processing (NLP) tasks. In general, the larger the number of parameters in a…
Language models like BERT excel at sentence classification tasks due to extensive pre-training on general data, but their robustness to parameter corruption is unexplored. To understand this better, we look at what happens if a language…
Since the popularization of the Transformer as a general-purpose feature encoder for NLP, many studies have attempted to decode linguistic structure from its novel multi-head attention mechanism. However, much of such work focused almost…
Pre-trained models have brought significant improvements to many NLP tasks and have been extensively analyzed. But little is known about the effect of fine-tuning on specific tasks. Intuitively, people may agree that a pre-trained model…
Large pre-trained neural networks such as BERT have had great recent success in NLP, motivating a growing body of research investigating what aspects of language they are able to learn from unlabeled data. Most recent analysis has focused…
Pre-trained Transformer-based models have achieved state-of-the-art performance for various Natural Language Processing (NLP) tasks. However, these models often have billions of parameters, and, thus, are too resource-hungry and…
Language exhibits structure at different scales, ranging from subwords to words, sentences, paragraphs, and documents. To what extent do deep models capture information at these scales, and can we force them to better capture structure…
Transformer-based models have led to significant innovation in classical and practical subjects as varied as speech processing, natural language processing, and computer vision. On top of the Transformer, attention-based end-to-end…
Contextual word embeddings obtained from pre-trained language model (PLM) have proven effective for various natural language processing tasks at the word level. However, interpreting the hidden aspects within embeddings, such as syntax and…