相关论文: Guiding Corpus-based Set Expansion by Auxiliary Se…

Unsupervised semantic segmentation aims to achieve high-quality semantic grouping without human-labeled annotations. With the advent of self-supervised pre-training, various frameworks utilize the pre-trained features to train prediction…

Information Retrieval (IR) is concerned with the identification of documents in a collection that are relevant to a given information need, usually represented as a query containing terms or keywords, which are supposed to be a good…

In this paper, we propose a linguistically-motivated query expansion framework that recognizes and en-codes significant query constituents that characterize query intent in order to improve retrieval performance. Concepts-of-Interest are…

Query expansion is a method for alleviating the vocabulary mismatch problem present in information retrieval tasks. Previous works have shown that terms selected for query expansion by traditional methods such as pseudo-relevance feedback…

Contrastive learning produces coherent semantic feature embeddings by encouraging positive samples to cluster closely while separating negative samples. However, existing contrastive learning methods lack principled guarantees on coverage…

The goal of confidence-set learning in the binary classification setting is to construct two sets, each with a specific probability guarantee to cover a class. An observation outside the overlap of the two sets is deemed to be from one of…

Co-speech gesture generation has significantly advanced human-computer interaction, yet speaker movements remain constrained due to the omission of text-driven non-spontaneous gestures (e.g., bowing while talking). Existing methods face two…

In specialized fields like the scientific domain, constructing large-scale human-annotated datasets poses a significant challenge due to the need for domain expertise. Recent methods have employed large language models to generate synthetic…

We present a co-segmentation technique for space-time co-located image collections. These prevalent collections capture various dynamic events, usually by multiple photographers, and may contain multiple co-occurring objects which are not…

Core-sets refer to subsets of data that maximize some function that is commonly a diversity or group requirement. These subsets are used in place of the original data to accomplish a given task with comparable or even enhanced performance…

Text-to-image generation models are powerful but difficult to use. Users craft specific prompts to get better images, though the images can be repetitive. This paper proposes a Prompt Expansion framework that helps users generate…

Given a small corpus $\mathcal D_T$ pertaining to a limited set of focused topics, our goal is to train embeddings that accurately capture the sense of words in the topic in spite of the limited size of $\mathcal D_T$. These embeddings may…

Retrieval-Augmented Generation (RAG) has emerged as a crucial framework in natural language processing (NLP), improving factual consistency and reducing hallucinations by integrating external document retrieval with large language models…

Semi-supervised bootstrapping techniques for relationship extraction from text iteratively expand a set of initial seed instances. Due to the lack of labeled data, a key challenge in bootstrapping is semantic drift: if a false positive…

Federated learning aims to collaboratively model by integrating multi-source information to obtain a model that can generalize across all client data. Existing methods often leverage knowledge distillation or data augmentation to mitigate…

Deep learning models often learn and exploit spurious correlations in training data, using these non-target features to inform their predictions. Such reliance leads to performance degradation and poor generalization on unseen data. To…

Users try to articulate their complex information needs during search sessions by reformulating their queries. To make this process more effective, search engines provide related queries to help users in specifying the information need in…

Entity alignment aims to use pre-aligned seed pairs to find other equivalent entities from different knowledge graphs (KGs) and is widely used in graph fusion-related fields. However, as the scale of KGs increases, manually annotating…

Accurately typing entity mentions from text segments is a fundamental task for various natural language processing applications. Many previous approaches rely on massive human-annotated data to perform entity typing. Nevertheless,…

Machine learning models are increasingly used in areas such as loan approvals and hiring, yet they often function as black boxes, obscuring their decision-making processes. Transparency is crucial, and individuals need explanations to…