The proceedings contain 280 papers. The topics discussed include: PiC: a phrase-in-context dataset for phrase understanding and semantic search; enhancing dialogue summarization with topic-aware global- and local- level centrality; exploiting summarization data to help text simplification; Shironaam: Bengali news headline generation using auxiliary information; PCC: paraphrasing with bottom-k sampling and cyclic learning for curriculum data augmentation; investigating data partitioning strategies for crosslinguistic low-resource ASR evaluation; shortcomings of question answering based factuality frameworks for error localization; Socratic question generation: a novel dataset, models, and evaluation; do we need label regularization to fine-tune pre-trained language models?; multimodal graph transformer for multimodal question answering; retrieval enhanced data augmentation for question answering on privacy policies; and friend-training: learning from models of different but related tasks.