Related papers: ConFit: Improving Resume-Job Matching using Data A…

Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classes. Training with CAD enhances model robustness against…

Contrastive learning is commonly used as a method of self-supervised learning with the "anchor" and "positive" being two random augmentations of a given input image, and the "negative" is the set of all other images. However, the…

As AI systems become more embedded in everyday life, the development of fair and unbiased models becomes more critical. Considering the social impact of AI systems is not merely a technical challenge but a moral imperative. As evidenced in…

In reinforcement learning (RL), it is easier to solve a task if given a good representation. While deep RL should automatically acquire such good representations, prior work often finds that learning representations in an end-to-end fashion…

This paper presents a solution to the challenges faced by contrastive learning in sequential recommendation systems. In particular, it addresses the issue of false negative, which limits the effectiveness of recommendation algorithms. By…

Contrastive learning has been used to learn a high-quality representation of the image in computer vision. However, contrastive learning is not widely utilized in natural language processing due to the lack of a general method of data…

The recruitment process is a slow and inefficient one at best, and a potentially ineffective one at worst. Matching candidates to jobs is one thing, but matching candidates with jobs alongside appropriate expectations and taking into…

Neural network based speech recognition systems suffer from performance degradation due to accented speech, especially unfamiliar accents. In this paper, we study the supervised contrastive learning framework for accented speech…

Deep candidate generation (DCG) that narrows down the collection of relevant items from billions to hundreds via representation learning has become prevalent in industrial recommender systems. Standard approaches approximate maximum…

Few-shot text classification has recently been promoted by the meta-learning paradigm which aims to identify target classes with knowledge transferred from source classes with sets of small tasks named episodes. Despite their success,…

The prompt has become an effective linguistic tool for utilizing pre-trained language models. However, in few-shot scenarios, subtle changes in the prompt design always make the result widely different, and the prompt learning methods also…

Existing online recruitment platforms depend on automatic ways of conducting the person-job fit, whose goal is matching appropriate job seekers with job positions. Intuitively, the previous successful recruitment records contain important…

Representation learning methods utilizing the InfoNCE loss have demonstrated considerable capacity in reducing human annotation effort by training invariant neural feature extractors. Although different variants of the training objective…

A data augmentation module is utilized in contrastive learning to transform the given data example into two views, which is considered essential and irreplaceable. However, the predetermined composition of multiple data augmentations brings…

Contrastive learning -- a modern approach to extract useful representations from unlabeled data by training models to distinguish similar samples from dissimilar ones -- has driven significant progress in foundation models. In this work, we…

Recommender systems are designed to learn user preferences from observed feedback and comprise many fundamental tasks, such as rating prediction and post-click conversion rate (pCVR) prediction. However, the observed feedback usually suffer…

Self-supervised contrastive learning heavily relies on the view variance brought by data augmentation, so that it can learn a view-invariant pre-trained representation. Beyond increasing the view variance for contrast, this work focuses on…

Efficiently ranking relevant items from large candidate pools is a cornerstone of modern information retrieval systems -- such as web search, recommendation, and retrieval-augmented generation. Listwise rerankers, which improve relevance by…

Using responses generated by high-performing large language models (LLMs) for instruction tuning has become a widely adopted approach. However, the existing literature overlooks a property of LLM-generated responses: they conflate world…

The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of…