相关论文: Multimodal Prompt Learning for Product Title Gener…

Event Extraction bridges the gap between text and event signals. Based on the assumption of trigger-argument dependency, existing approaches have achieved state-of-the-art performance with expert-designed templates or complicated decoding…

The performance of computer vision models in certain real-world applications (e.g., rare wildlife observation) is limited by the small number of available images. Expanding datasets using pre-trained generative models is an effective way to…

Demonstration learning aims to guide the prompt prediction via providing answered demonstrations in the few shot settings. Despite achieving promising results, existing work only concatenates the answered examples as demonstrations to the…

Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over…

Pre-trained language models derive substantial linguistic and factual knowledge from the massive corpora on which they are trained, and prompt engineering seeks to align these models to specific tasks. Unfortunately, existing prompt…

Traditional neural topic models are typically optimized by reconstructing the document's Bag-of-Words (BoW) representations, overlooking contextual information and struggling with data sparsity. In this work, we propose a novel approach to…

Labeling training datasets has become a key barrier to building medical machine learning models. One strategy is to generate training labels programmatically, for example by applying natural language processing pipelines to text reports…

Due to their architecture and vast pre-training data, large language models (LLMs) demonstrate strong text classification performance. However, LLM output - here, the category assigned to a text - depends heavily on the wording of the…

The item cold-start problem is crucial for online recommender systems, as the success of the cold-start phase determines whether items can transition into popular ones. Prompt learning, a powerful technique used in natural language…

Domain adaptation is an important task to enable learning when labels are scarce. While most works focus only on the image modality, there are many important multi-modal datasets. In order to leverage multi-modality for domain adaptation,…

Federated learning (FL) has emerged as a powerful paradigm for learning from decentralized data, and federated domain generalization further considers the test dataset (target domain) is absent from the decentralized training data (source…

Large-scale multimodal models have shown excellent performance over a series of tasks powered by the large corpus of paired multimodal training data. Generally, they are always assumed to receive modality-complete inputs. However, this…

Abstract. Automatically generating scientific literature surveys is a valuable task that can significantly enhance research efficiency. However, the diverse and complex nature of information within a literature survey poses substantial…

While most research on controllable text generation has focused on steering base Language Models, the emerging instruction-tuning and prompting paradigm offers an alternate approach to controllability. We compile and release ConGenBench, a…

For continual learning, text-prompt-based methods leverage text encoders and learnable prompts to encode semantic features for sequentially arrived classes over time. A common challenge encountered by existing works is how to learn unique…

Metaphors play a significant role in our everyday communication, yet detecting them presents a challenge. Traditional methods often struggle with improper application of language rules and a tendency to overlook data sparsity. To address…

Source-free domain adaptation has developed rapidly in recent years, where the well-trained source model is adapted to the target domain instead of the source data, offering the potential for privacy concerns and intellectual property…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

To provide better access of the inventory to buyers and better search engine optimization, e-Commerce websites are automatically generating millions of easily searchable browse pages. A browse page consists of a set of slot name/value pairs…

Missing modality issues are common in real-world applications, arising from factors such as equipment failures and privacy concerns. When fine-tuning pre-trained models on downstream datasets with missing modalities, performance can degrade…