People often imagine relevant scenes to aid in the writing process. In this work, we aim to
utilize visual information for composition in the same manner as humans. We propose a …

Creating engaging narratives from visual data is crucial for automated digital media
consumption, assistive technologies, and interactive entertainment. This survey covers …

Abstract Multimodal Argument Mining (MAM) is a recent area of research aiming to extend
argument analysis and improve discourse understanding by incorporating multiple …

Data-to-text (D2T) generation is a crucial task in many natural language understanding
(NLU) applications and forms the foundation of task-oriented dialog systems. In the context …

Interpreting ancient Chinese has been the key to comprehending vast Chinese literature,
tradition, and civilization. In this paper, we propose Erya for ancient Chinese translation …

Text generation is a vital natural language processing task that generates a sequence given
an input text. Most recent text generation models have mainly utilized the power of pre …

Nearest neighbor machine translation (k NN-MT), which interpolates target token
probabilities with estimates derived from additional examples, has achieved significant …

The advent of transformers and the subsequent development of Large Language Models
(LLMs) based on these technologies has revolutionized the field of Natural Language …

Demonstration selection, the process of selecting examples used in prompts, plays a critical
role in in-context learning. This paper explores demonstration selection methods for data-to …

Tables, ubiquitous in data-oriented documents like scientific papers and financial
statements, organize and convey relational information. Automatic table recognition from …