Related papers: CIR at the NTCIR-17 ULTRE-2 Task

Self-supervised contrastive learning frameworks have progressed rapidly over the last few years. In this paper, we propose a novel loss function for contrastive learning. We model our pre-training task as a binary classification problem to…

Modern online advertising systems inevitably rely on personalization methods, such as click-through rate (CTR) prediction. Recent progress in CTR prediction enjoys the rich representation capabilities of deep learning and achieves great…

Based on an exponentially increasing number of academic articles, discovering and citing comprehensive and appropriate resources has become a non-trivial task. Conventional citation recommender methods suffer from severe information loss.…

Despite the popularity of the two-tower model for unbiased learning to rank (ULTR) tasks, recent work suggests that it suffers from a major limitation that could lead to its collapse in industry applications: the problem of logging policy…

Backdoor attack is a new AI security risk that has emerged in recent years. Drawing on the previous research of adversarial attack, we argue that the backdoor attack has the potential to tap into the model learning process and improve model…

Hard negatives are essential for training effective retrieval models. Hard-negative mining typically relies on ranking documents using cross-encoders or static embedding models based on similarity metrics such as cosine distance. Hard…

We present a new approach for mitigating unfairness in learned classifiers. In particular, we focus on binary classification tasks over individuals from two populations, where, as our criterion for fairness, we wish to achieve similar false…

Information Retrieval (IR) systems are designed to deliver relevant content, but traditional systems may not optimize rankings for fairness, neutrality, or the balance of ideas. Consequently, IR can often introduce indexical biases, or…

Model-based offline reinforcement learning (RL) has emerged as a promising approach for recommender systems, enabling effective policy learning by interacting with frozen world models. However, the reward functions in these world models,…

Contrastive learning (CL) methods effectively learn data representations in a self-supervision manner, where the encoder contrasts each positive sample over multiple negative samples via a one-vs-many softmax cross-entropy loss. By…

Long Document retrieval (DR) has always been a tremendous challenge for reading comprehension and information retrieval. The pre-training model has achieved good results in the retrieval stage and Ranking for long documents in recent years.…

Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques that mitigate such biases. In this work, we perform an…

Distantly supervised named entity recognition (DS-NER) has been proposed to exploit the automatically labeled training data by external knowledge bases instead of human annotations. However, it tends to suffer from a high false negative…

The FA team participated in the Table Data Extraction (TDE) and Text-to-Table Relationship Extraction (TTRE) tasks of the NTCIR-17 Understanding of Non-Financial Objects in Financial Reports (UFO). This paper reports our approach to solving…

We show that a critical vulnerability in adversarial imitation is the tendency of discriminator networks to learn spurious associations between visual features and expert labels. When the discriminator focuses on task-irrelevant features,…

Despite recent advancements, NLP models continue to be vulnerable to bias. This bias often originates from the uneven distribution of real-world data and can propagate through the annotation process. Escalated integration of these models in…

Fake orders pose increasing threats to sequential recommender systems by misleading recommendation results through artificially manipulated interactions, including click farming, context-irrelevant substitutions, and sequential…

We address the issue of estimation bias in deep reinforcement learning (DRL) by introducing solution mechanisms that include a new, twin TD-regularized actor-critic (TDR) method. It aims at reducing both over and under-estimation errors.…

As one of the most effective self-supervised representation learning methods, contrastive learning (CL) relies on multiple negative pairs to contrast against each positive pair. In the standard practice of contrastive learning, data…

Fact checking is an essential challenge when combating fake news. Identifying documents that agree or disagree with a particular statement (claim) is a core task in this process. In this context, stance detection aims at identifying the…