Related papers: Query-focused Sentence Compression in Linear Time

Semantic communication has emerged as a promising paradigm to tackle the challenges of massive growing data traffic and sustainable data communication. It shifts the focus from data fidelity to goal-oriented or task-oriented semantic…

The growing popularity of dynamic applications such as social networks provides a promising way to detect valuable information in real time. Efficient analysis over high-speed data from dynamic applications is of great significance. Data…

The rapid advancement of Large Language Models (LLMs) has inaugurated a transformative epoch in natural language processing, fostering unprecedented proficiency in text generation, comprehension, and contextual scrutiny. Nevertheless,…

Sentence compression is the task of creating a shorter version of an input sentence while keeping important information. In this paper, we extend the task of compression by deletion with the use of contextual embeddings. Different from…

Long-context inputs in large language models (LLMs) often suffer from the "lost in the middle" problem, where critical information becomes diluted or ignored due to excessive length. Context compression methods aim to address this by…

Through reading the documentation in the context, tool-using language models can dynamically extend their capability using external tools. The cost is that we have to input lengthy documentation every time the model needs to use the tool,…

The softmax content-based attention mechanism has proven to be very beneficial in many applications of recurrent neural networks. Nevertheless it suffers from two major computational limitations. First, its computations for an attention…

Large reasoning models (LRMs) typically solve reasoning-intensive tasks by generating long chain-of-thought (CoT) traces, leading to substantial inference overhead. We identify a reproducible inference-time phenomenon, termed…

Thanks to the rapid proliferation of connected devices, sensor-generated time series constitute a large and growing portion of the world's data. Often, this data is collected from distributed, resource-constrained devices and centralized at…

Intent detection of spoken queries is a challenging task due to their noisy structure and short length. To provide additional information regarding the query and enhance the performance of intent detection, we propose a method for semantic…

Retrieving relevant evidence from visually rich documents such as textbooks, technical reports, and manuals is challenging due to long context, complex layouts, and weak lexical overlap between user questions and supporting pages. We…

Although Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in vision, language, and video understanding tasks, scaling them to long-form speech remains a critical bottleneck due to the explosive growth of…

The rapid growth of tabular datasets in data lakes, data spaces, and open data portals makes effective dataset search essential for reuse and analysis. Existing search systems rely mainly on metadata, which is often incomplete or low…

Several data warehouse and database providers have recently introduced extensions to SQL called AI Queries, enabling users to specify functions and conditions in SQL that are evaluated by LLMs, thereby broadening significantly the kinds of…

Recurrent neural networks have proved to be an effective method for statistical language modeling. However, in practice their memory and run-time complexity are usually too large to be implemented in real-time offline mobile applications.…

We propose a timed and soft extension of Concurrent Constraint Programming. The time extension is based on the hypothesis of bounded asynchrony: the computation takes a bounded period of time and is measured by a discrete global clock.…

Graph-based semi-supervised learning has proven to be an effective approach for query-focused multi-document summarization. The problem of previous semi-supervised learning is that sentences are ranked without considering the higher level…

Spoken language applications in natural dialogue settings place serious requirements on the choice of processing architecture. Especially under adverse phonetic and acoustic conditions parsing procedures have to be developed which do not…

Transformers are among the state of the art for many tasks in speech, vision, and natural language processing, among others. Self-attentions, which are crucial contributors to this performance have quadratic computational complexity, which…

Large Language Models (LLMs) excel in text classification, but their complexity hinders interpretability, making it difficult to understand the reasoning behind their predictions. Explainable AI (XAI) methods like LIME and SHAP offer local…