相关论文: JAMES: Normalizing Job Titles with Multi-Aspect Gr…

Named entity recognition (NER) systems that perform well require task-related and manually annotated datasets. However, they are expensive to develop, and are thus limited in size. As there already exists a large number of NER datasets that…

Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based methods, their effectiveness and generalizability across…

This paper describes a hypernym discovery system for our participation in the SemEval-2018 Task 9, which aims to discover the best (set of) candidate hypernyms for input concepts or entities, given the search space of a pre-defined…

In this work, we reimagine classical probing to evaluate knowledge transfer from simple source to more complex target tasks. Instead of probing frozen representations from a complex source task on diverse simple target probing tasks (as…

To generate summaries that include multiple aspects or topics for text documents, most approaches use clustering or topic modeling to group relevant sentences and then generate a summary for each group. These approaches struggle to optimize…

Reward models are critical for reinforcement learning from human feedback, as they determine the alignment quality and reliability of generative models. For complex tasks such as image editing, reward models are required to capture global…

Two questions regarding practitioners' use of patent embeddings arise: (i) Does one fine-tuning recipe suffice for all downstream applications? (ii) Is fine-tuning on one patent landscape sufficient for downstream application on other…

Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…

A central question in computational vision is whether human-like visual representations are better explained by discriminative or generative learning. Existing comparisons, however, often confound the learning objective with architecture,…

Depth estimation is an essential component in understanding the 3D geometry of a scene, with numerous applications in urban and indoor settings. These scenes are characterized by a prevalence of human made structures, which in most of the…

In our study, we propose a self-supervised neural topic model (NTM) that combines the power of NTMs and regularized self-supervised learning methods to improve performance. NTMs use neural networks to learn latent topics hidden behind the…

Knowledge graphs have gained popularity for their ability to organize and analyze complex data effectively. When combined with graph embedding techniques, such as graph neural networks (GNNs), knowledge graphs become a potent tool in…

The task of completing knowledge triplets has broad downstream applications. Both structural and semantic information plays an important role in knowledge graph completion. Unlike previous approaches that rely on either the structures or…

Embedding-based neural topic models could explicitly represent words and topics by embedding them to a homogeneous feature space, which shows higher interpretability. However, there are no explicit constraints for the training of…

We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined…

Task embedding, a meta-learning technique that captures task-specific information, has gained popularity, especially in areas such as multi-task learning, model editing, and interpretability. However, it faces challenges with the emergence…

Topic models uncover latent thematic structures in text corpora, yet evaluating their quality remains challenging, particularly in specialized domains. Existing methods often rely on automated metrics like topic coherence and diversity,…

The goal of graph summarization is to represent large graphs in a structured and compact way. A graph summary based on equivalence classes preserves pre-defined features of a graph's vertex within a $k$-hop neighborhood such as the vertex…

In NLP, fine-tuning LLMs is effective for various applications but requires high-quality annotated data. However, manual annotation of data is labor-intensive, time-consuming, and costly. Therefore, LLMs are increasingly used to automate…

Due to the manifold ranking method has a significant effect on the ranking of unknown data based on known data by using a weighted network, many researchers use the manifold ranking method to solve the document summarization task. However,…