相关论文: Behavior Tokens Speak Louder: Disentangled Explain…

Multi-agent systems must decide which agent is the most appropriate for a given task. We propose a novel architecture for recommending which LLM agent out of many should perform a task given a natural language prompt by extending the…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Language models that utilize extensive self-supervised pre-training from unlabeled text, have recently shown to significantly advance the state-of-the-art performance in a variety of language understanding tasks. However, it is yet unclear…

This paper presents new state-of-the-art models for three tasks, part-of-speech tagging, syntactic parsing, and semantic parsing, using the cutting-edge contextualized embedding framework known as BERT. For each task, we first replicate and…

Incorporating lexical knowledge into deep learning models has been proved to be very effective for sequence labeling tasks. However, previous works commonly have difficulty dealing with large-scale dynamic lexicons which often cause…

Multimodal recommendation systems have attracted increasing attention for their improved performance by leveraging items' multimodal information. Prior methods often build modality-specific item-item semantic graphs from raw modality…

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level…

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…

Providing accurate/suitable information on behaviors in sma\-rt environments is a challenging and crucial task in pervasive computing where context-awareness and pro-activity are of fundamental importance. Behavioral identifications enable…

Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…

Deploying LLMs in real-world applications requires controllable output that satisfies multiple desiderata at the same time. While existing work extensively addresses LLM steering for a single behavior, \textit{compositional steering} --…

State-of-the-art recommender system (RS) mostly rely on complex deep neural network (DNN) model structure, which makes it difficult to provide explanations along with RS decisions. Previous researchers have proved that providing…

Discrete audio representations are gaining traction in speech modeling due to their interpretability and compatibility with large language models, but are not always optimized for noisy or real-world environments. Building on existing works…

In the last decade, driven also by the availability of an unprecedented computational power and storage capabilities in cloud environments we assisted to the proliferation of new algorithms, methods, and approaches in two areas of…

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

In recent years, robots are used in an increasing variety of tasks, especially by small- and medium- sized enterprises. These tasks are usually fast-changing, they have a collaborative scenario and happen in unpredictable environments with…

With the development of AI-Generated Content (AIGC), text-to-audio models are gaining widespread attention. However, it is challenging for these models to generate audio aligned with human preference due to the inherent information density…

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e.g., click, add-to-cart, and purchase). Traditional collaborative filtering techniques typically assume that users only have a single type…

Generative recommendation (GR) models tokenize each action into a few discrete tokens (called semantic IDs) and autoregressively generate the next tokens as predictions, showing advantages such as memory efficiency, scalability, and the…

Self-supervised learning has become increasingly important to leverage the abundance of unlabeled data available on platforms like YouTube. Whereas most existing approaches learn low-level representations, we propose a joint…