Related papers: Isotropy-Optimized Contrastive Learning for Semant…

Sequential recommender systems (SRSs) aim to predict the subsequent items which may interest users via comprehensively modeling users' complex preference embedded in the sequence of user-item interactions. However, most of existing SRSs…

We introduce a simple yet effective method of integrating contextual embeddings with commonsense graph embeddings, dubbed BERT Infused Graphs: Matching Over Other embeDdings. First, we introduce a preprocessing method to improve the speed…

Recommender systems increasingly incorporate textual reviews to enrich user and item representations. However, most review-aware models remain optimized for rating prediction rather than ranking quality. This misalignment limits their…

Sequential recommendation methods are increasingly important in cutting-edge recommender systems. Through leveraging historical records, the systems can capture user interests and perform recommendations accordingly. State-of-the-art…

Despite their promising performance across various natural language processing (NLP) tasks, current NLP systems are vulnerable to textual adversarial attacks. To defend against these attacks, most existing methods apply adversarial training…

Contrastive learning has achieved remarkable success in self-supervised representation learning, often guided by information-theoretic objectives such as mutual information maximization. Motivated by the limitations of static augmentations…

Selecting radiology examination protocol is a repetitive, and time-consuming process. In this paper, we present a deep learning approach to automatically assign protocols to computer tomography examinations, by pre-training a…

The purpose of the study is to investigate the relative effectiveness of four different sentiment analysis techniques: (1) unsupervised lexicon-based model using Sent WordNet; (2) traditional supervised machine learning model using logistic…

Multilingual BERT (mBERT), XLM-RoBERTa (XLMR) and other unsupervised multilingual encoders can effectively learn cross-lingual representation. Explicit alignment objectives based on bitexts like Europarl or MultiUN have been shown to…

The current state-of-the-art task-oriented semantic parsing models use BERT or RoBERTa as pretrained encoders; these models have huge memory footprints. This poses a challenge to their deployment for voice assistants such as Amazon Alexa…

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning. They are not suitable for exploiting the rich…

Contrastive self-supervised learning methods famously produce high quality transferable representations by learning invariances to different data augmentations. Invariances established during pre-training can be interpreted as strong…

Efficient document retrieval heavily relies on the technique of semantic hashing, which learns a binary code for every document and employs Hamming distance to evaluate document distances. However, existing semantic hashing methods are…

Trained classification models can unintentionally lead to biased representations and predictions, which can reinforce societal preconceptions and stereotypes. Existing debiasing methods for classification models, such as adversarial…

We introduce Three Towers (3T), a flexible method to improve the contrastive learning of vision-language models by incorporating pretrained image classifiers. While contrastive models are usually trained from scratch, LiT (Zhai et al.,…

We introduce a self-supervised approach for learning node and graph level representations by contrasting structural views of graphs. We show that unlike visual representation learning, increasing the number of views to more than two or…

In this work, we represent CMV-BERT, which improves the pretraining of a language model via two ingredients: (a) contrastive learning, which is well studied in the area of computer vision; (b) multiple vocabularies, one of which is…

For many computer vision applications such as image captioning, visual question answering, and person search, learning discriminative feature representations at both image and text level is an essential yet challenging problem. Its…

Domain adaptation or transfer learning using pre-trained language models such as BERT has proven to be an effective approach for many natural language processing tasks. In this work, we propose to formulate word sense disambiguation as a…

Objective: Biomedical Knowledge Graphs play a pivotal role in various biomedical research domains. Concurrently, term clustering emerges as a crucial step in constructing these knowledge graphs, aiming to identify synonymous terms. Due to a…