相关论文: Information retrieval for label noise document ran…

Long Context Language Models (LCLMs) have emerged as a new paradigm to perform Information Retrieval (IR), which enables the direct ingestion and retrieval of information by processing an entire corpus in their single context, showcasing…

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can…

Neural sentence embedding models for dense retrieval typically rely on binary relevance labels, treating query-document pairs as either relevant or irrelevant. However, real-world relevance often exists on a continuum, and recent advances…

Sparse document representations have been widely used to retrieve relevant documents via exact lexical matching. Owing to the pre-computed inverted index, it supports fast ad-hoc search but incurs the vocabulary mismatch problem. Although…

Given data with label noise (i.e., incorrect data), deep neural networks would gradually memorize the label noise and impair model performance. To relieve this issue, curriculum learning is proposed to improve model performance and…

Dense retrieval models, which aim at retrieving the most relevant document for an input query on a dense representation space, have gained considerable attention for their remarkable success. Yet, dense models require a vast amount of…

We present our method for tackling the legal case retrieval task of the Competition on Legal Information Extraction/Entailment 2019. Our approach is based on the idea that summarization is important for retrieval. On one hand, we adopt a…

Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples…

The main focus of information retrieval methods is to provide accurate and efficient results which are cost-effective too. LINGO (Label Induction Grouping Algorithm) is a clustering algorithm that aims to provide search results in form of…

Supervised ranking methods based on bi-encoder or cross-encoder architectures have shown success in multi-stage text ranking tasks, but they require large amounts of relevance judgments as training data. In this work, we propose Listwise…

Label noise may affect the generalization of classifiers, and the effective learning of main patterns from samples with noisy labels is an important challenge. Recent studies have shown that deep neural networks tend to prioritize the…

Label noise and class imbalance commonly coexist in real-world data. Previous works for robust learning, however, usually address either one type of the data biases and underperform when facing them both. To mitigate this gap, this work…

There is extensive interest in metric learning methods for image retrieval. Many metric learning loss functions focus on learning a correct ranking of training samples, but strongly overfit semantically inconsistent labels and require a…

In learning tasks with label noise, improving model robustness against overfitting is a pivotal challenge because the model eventually memorizes labels, including the noisy ones. Identifying the samples with noisy labels and preventing the…

We present our method for tackling a legal case retrieval task by introducing our method of encoding documents by summarizing them into continuous vector space via our phrase scoring framework utilizing deep neural networks. On the other…

Audio tagging aims to infer descriptive labels from audio clips. Audio tagging is challenging due to the limited size of data and noisy labels. In this paper, we describe our solution for the DCASE 2018 Task 2 general audio tagging…

Screening patients for enrollment is a well-known, labor-intensive bottleneck that leads to under-enrollment and, ultimately, trial failures. Recent breakthroughs in large language models (LLMs) offer a promising opportunity to use…

Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary labels is more robust when noisy labels intervene but with an…

List-wise learning to rank methods are considered to be the state-of-the-art. One of the major problems with these methods is that the ambiguous nature of relevance labels in learning to rank data is ignored. Ambiguity of relevance labels…

Despite the advantages of their low-resource settings, traditional sparse retrievers depend on exact matching approaches between high-dimensional bag-of-words (BoW) representations of both the queries and the collection. As a result,…