Related papers: An Efficient Architecture for Predicting the Case …

Self-supervised learning algorithms based on instance discrimination train encoders to be invariant to pre-defined transformations of the same instance. While most methods treat different views of the same image as positives for a…

This paper describes our submission (named clac) to the 2016 Discriminating Similar Languages (DSL) shared task. We participated in the closed Sub-task 1 (Set A) with two separate machine learning techniques. The first approach is a…

A picture is worth a thousand words. Not until recently, however, we noticed some success stories in understanding of visual scenes: a model that is able to detect/name objects, describe their attributes, and recognize their…

Feedforward Neural Network (FNN)-based language models estimate the probability of the next word based on the history of the last N words, whereas Recurrent Neural Networks (RNN) perform the same task based only on the last word and some…

In this paper, we present a fast and strong neural approach for general purpose text matching applications. We explore what is sufficient to build a fast and well-performed text matching model and propose to keep three key features…

We revisit language bottleneck models as an approach to ensuring the explainability of deep learning models for image classification. Because of inevitable information loss incurred in the step of converting images into language, the…

Modern language models are internally -- and mathematically -- distributions over $\it{token}$ strings rather than $\it{character}$ strings, posing numerous challenges for programmers building user applications on top of them. For example,…

Character-level features are currently used in different neural network-based natural language processing algorithms. However, little is known about the character-level patterns those models learn. Moreover, models are often compared only…

We investigate how to train a high quality optical character recognition (OCR) model for difficult historical typefaces on degraded paper. Through extensive grid searches, we obtain a neural network architecture and a set of optimal data…

Neural approaches to sequence labeling often use a Conditional Random Field (CRF) to model their output dependencies, while Recurrent Neural Networks (RNN) are used for the same purpose in other tasks. We set out to establish RNNs as an…

Recent advances in text-to-image generation models have unlocked vast potential for visual creativity. However, the users that use these models struggle with the generation of consistent characters, a crucial aspect for numerous real-world…

Fake news are nowadays an issue of pressing concern, given their recent rise as a potential threat to high-quality journalism and well-informed public discourse. The Fake News Challenge (FNC-1) was organized in 2017 to encourage the…

Convolutional Neural Networks (CNNs) have recently achieved remarkably strong performance on the practically important task of sentence classification (kim 2014, kalchbrenner 2014, johnson 2014). However, these models require practitioners…

The rise of neural networks, and particularly recurrent neural networks, has produced significant advances in part-of-speech tagging accuracy. One characteristic common among these models is the presence of rich initial word encodings.…

Having a sequence-to-sequence model which can operate in an online fashion is important for streaming applications such as Voice Search. Neural transducer is a streaming sequence-to-sequence model, but has shown a significant degradation in…

Despite the recent remarkable improvements in scene text recognition (STR), the majority of the studies focused mainly on the English language, which only includes few number of characters. However, STR models show a large performance…

Counterfactual fairness methods address the question: How would the prediction change if the sensitive identity attributes referenced in the text instance were different? These methods are entirely based on generating counterfactuals for…

Deep convolutional neural networks (CNNs) have greatly improved the Face Recognition (FR) performance in recent years. Almost all CNNs in FR are trained on the carefully labeled datasets containing plenty of identities. However, such…

Despite exciting progress in causal language models, the expressiveness of the representations is largely limited due to poor discrimination ability. To remedy this issue, we present ContraCLM, a novel contrastive learning framework at both…

We propose a novel convolutional architecture, named $gen$CNN, for word sequence prediction. Different from previous work on neural network-based language modeling and generation (e.g., RNN or LSTM), we choose not to greedily summarize the…