Related papers: Solving the Class Diagram Restructuring Transforma…
Quantum circuit transformation aims to produce equivalent circuits while optimizing for various aspects such as circuit depth, gate count, and compatibility with modern Noisy Intermediate Scale Quantum (NISQ) devices. There are two…
We present lambeq, the first high-level Python library for Quantum Natural Language Processing (QNLP). The open-source toolkit offers a detailed hierarchy of modules and classes implementing all stages of a pipeline for converting sentences…
Adapting large language models to full document translation remains challenging due to the difficulty of capturing long-range dependencies and preserving discourse coherence throughout extended texts. While recent agentic machine…
Textbook question answering (TQA) is a challenging task in artificial intelligence due to the complex nature of context needed to answer complex questions. Although previous research has improved the task, there are still some limitations…
Generating questions along with associated answers from a text has applications in several domains, such as creating reading comprehension tests for students, or improving document search by providing auxiliary questions and answers based…
The left-corner transformation (Rosenkrantz and Lewis, 1970) is used to remove left recursion from context-free grammars, which is an important step towards making the grammar parsable top-down with simple techniques. This paper generalizes…
The aim of the Transformation Tool Contest (TTC) series is to compare the expressiveness, the usability and the performance of graph and model transformation tools along a number of selected case studies. Participants want to learn about…
\emph{Funnelling} (Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classifiers, each working…
This article details our participation (L3iTC) in the FinLLM Challenge Task 2024, focusing on two key areas: Task 1, financial text classification, and Task 2, financial text summarization. To address these challenges, we fine-tuned several…
Despite the success of existing instruction-tuned models, we find that they usually struggle to respond to queries with multiple instructions. This impairs their performance in complex problems whose solution consists of multiple…
Zero-Shot Cross-lingual Transfer (ZS-XLT) utilizes a model trained in a source language to make predictions in another language, often with a performance loss. To alleviate this, additional improvements can be achieved through subsequent…
In text-video retrieval, recent works have benefited from the powerful learning capabilities of pre-trained text-image foundation models (e.g., CLIP) by adapting them to the video domain. A critical problem for them is how to effectively…
The task of natural language table retrieval (NLTR) seeks to retrieve semantically relevant tables based on natural language queries. Existing learning systems for this task often treat tables as plain text based on the assumption that…
String constraint solving, and the underlying theory of word equations, are highly interesting research topics both for practitioners and theoreticians working in the wide area of satisfiability modulo theories. As string constraint solving…
Contextualizing problems to align with student interests can significantly improve learning outcomes. However, this task often presents scalability challenges due to resource and time constraints. Recent advancements in Large Language…
Quantization is an indispensable technique for serving Large Language Models (LLMs) and has recently found its way into LoRA fine-tuning. In this work we focus on the scenario where quantization and LoRA fine-tuning are applied together on…
Intermediate features of a pre-trained model have been shown informative for making accurate predictions on downstream tasks, even if the model backbone is kept frozen. The key challenge is how to utilize these intermediate features given…
Knowledge graphs offer an excellent solution for representing the lexical-semantic structures of lexicographic data. However, working with the SPARQL query language represents a considerable hurdle for many non-expert users who could…
Test-time finetuning (TTFT) is a rapidly evolving paradigm that adapts a language model to each prompt by retrieving related sequences, updating the model on them, and then evaluating the prompt. However, TTFT is only practical if it is…
Previous studies such as VizWiz find that Visual Question Answering (VQA) systems that can read and reason about text in images are useful in application areas such as assisting visually-impaired people. TextVQA is a VQA dataset geared…