Related papers: Mitigating Semantic Leakage in Cross-lingual Embed…

Recent research demonstrates that word embeddings, trained on the human-generated corpus, have strong gender biases in embedding spaces, and these biases can result in the discriminative results from the various downstream tasks. Whereas…

Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semantic alignment in embedding models. Existing pipelines often…

Ontologies provide formal representation of knowledge shared within Semantic Web applications. Ontology learning involves the construction of ontologies from a given corpus. In the past years, ontology learning has traversed through shallow…

Ontologies usually suffer from the semantic heterogeneity when simultaneously used in information sharing, merging, integrating and querying processes. Therefore, the similarity identification between ontologies being used becomes a…

Biological memory solves a problem that eludes current AI: storing specific episodic facts without corrupting general semantic knowledge. Complementary Learning Systems theory explains this through two subsystems - a fast hippocampal system…

In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…

We propose an architecture to jointly learn word and label embeddings for slot filling in spoken language understanding. The proposed approach encodes labels using a combination of word embeddings and straightforward word-label association…

Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…

The Open Digital Rights Language (ODRL) represents policy constraints as triples of a left operand, an operator, and a value. Several spatial operands, however, range over multi-axis domains such as width, height, and depth, while the…

Large language models (LLMs) represent words through contextual word embeddings encoding different language properties like semantics and syntax. Understanding these properties is crucial, especially for researchers investigating language…

Semantic segmentation is one of the most fundamental problems in computer vision with significant impact on a wide variety of applications. Adversarial learning is shown to be an effective approach for improving semantic segmentation…

Large language models have recently pushed open domain question answering (ODQA) to new frontiers. However, prevailing retriever-reader pipelines often depend on multiple rounds of prompt level instructions, leading to high computational…

Large Language Models (LLMs) unlearning is crucial for removing hazardous or privacy-leaking information from the model. Practical LLM unlearning demands satisfying multiple challenging objectives simultaneously: removing undesirable…

Conditional representation learning aims to extract criterion-specific features for customized tasks. Recent studies project universal features onto the conditional feature subspace spanned by an LLM-generated text basis to obtain…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

Despite advances in multilingual neural machine translation (MNMT), we argue that there are still two major challenges in this area: data imbalance and representation degeneration. The data imbalance problem refers to the imbalance in the…

We relax the constraint of a shared language between agents in a semantic and goal-oriented communication system to explore the effect of language mismatch in distributed task solving. We propose a mathematical framework, which provides a…

We propose a novel approach for training large language models (LLMs) to adhere to objectives defined within a latent embedding space. Our method leverages reinforcement learning (RL), treating a pre-trained LLM as an environment. Our…

Relational data sources are still one of the most popular ways to store enterprise or Web data, however, the issue with relational schema is the lack of a well-defined semantic description. A common ontology provides a way to represent the…

Large Language Models (LLMs) are revolutionizing how users interact with information systems, yet their high inference cost poses serious scalability and sustainability challenges. Caching inference responses, allowing them to be retrieved…