相关论文: Learning Analogies and Semantic Relations

For sequence transduction tasks like speech recognition, a strong structured prior model encodes rich information about the target space, implicitly ruling out invalid sequences by assigning them low probability. In this work, we propose…

This paper provides an insight into the possibility of how to find ontologies most relevant to scientific texts using artificial neural networks. The basic idea of the presented approach is to select a representative paragraph from a source…

With hundreds of multilingual embedding models available, practitioners lack clear guidance on which provide genuine cross-lingual semantic alignment versus task performance through language-specific patterns. Task-driven benchmarks (MTEB)…

The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of…

Humans judge the similarity of two objects not just based on their visual appearance but also based on their semantic relatedness. However, it remains unclear how humans learn about semantic relationships between objects and categories. One…

In vision-language models (VLMs), prompt tuning has shown its effectiveness in adapting models to downstream tasks. However, learned prompts struggle to generalize to unseen classes, as they tend to overfit to the classes that are targeted…

A group of transition probability functions form a Shannon's channel whereas a group of truth functions form a semantic channel. Label learning is to let semantic channels match Shannon's channels and label selection is to let Shannon's…

Word embedding, which encodes words into vectors, is an important starting point in natural language processing and commonly used in many text-based machine learning tasks. However, in most current word embedding approaches, the similarity…

Applying deep learning to solve real-life instances of hard combinatorial problems has tremendous potential. Research in this direction has focused on the Boolean satisfiability (SAT) problem, both because of its theoretical centrality and…

Contextual spelling correction models are an alternative to shallow fusion to improve automatic speech recognition (ASR) quality given user vocabulary. To deal with large user vocabularies, most of these models include candidate retrieval…

Learning a joint language-visual embedding has a number of very appealing properties and can result in variety of practical application, including natural language image/video annotation and search. In this work, we study three different…

A text-mining-based word class categorization method and LSTM-based vocabulary pattern prediction method are introduced in this paper. A preprocessing method based on simple text appearance frequency analysis is first described. This method…

Advances in vision-language models (VLMs) have enabled effective cross-modality retrieval. However, when both text and images exist in the database, similarity scores would differ in scale by modality. This phenomenon, known as the modality…

Curriculum learning can improve neural network training by guiding the optimization to desirable optima. We propose a novel curriculum learning approach for image classification that adapts the loss function by changing the label…

Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…

Word embeddings are an essential component in a wide range of natural language processing applications. However, distributional semantic models are known to struggle when only a small number of context sentences are available. Several…

The relevance between a query and a document in search can be represented as matching degree between the two objects. Latent space models have been proven to be effective for the task, which are often trained with click-through data. One…

The rising cost of acquiring supervised data has driven significant interest in self-improvement for large language models (LLMs). Straightforward unsupervised signals like majority voting have proven effective in generating pseudo-labels…

Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the…

Language identification (LID) recognizes the language of a spoken utterance automatically. According to recent studies, LID models trained with an automatic speech recognition (ASR) task perform better than those trained with a LID task…