Related papers: DoCIA: An Online Document-Level Context Incorporat…

Speech-to-text translation (ST) is a cross-modal task that involves converting spoken language into text in a different language. Previous research primarily focused on enhancing speech translation by facilitating knowledge transfer from…

Despite extensions to speech inputs, effectively leveraging the rich knowledge and contextual understanding of large language models (LLMs) in automatic speech recognition (ASR) remains non-trivial, as the task primarily involves direct…

Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…

Document-level context has received lots of attention for compensating neural machine translation (NMT) of isolated sentences. However, recent advances in document-level NMT focus on sophisticated integration of the context, explaining its…

Neural machine translation (NMT) has arguably achieved human level parity when trained and evaluated at the sentence-level. Document-level neural machine translation has received less attention and lags behind its sentence-level…

Document Question Answering (DocQA) is a very common task. Existing methods using Large Language Models (LLMs) or Large Vision Language Models (LVLMs) and Retrieval Augmented Generation (RAG) often prioritize information from a single…

Document level Machine Translation (DocMT) approaches often struggle with effectively capturing discourse level phenomena. Existing approaches rely on heuristic rules to segment documents into discourse units, which rarely align with the…

Long-context modeling is one of the critical capabilities of language AI for digesting and reasoning over complex information pieces. In practice, long-context capabilities are typically built into a pre-trained language model~(LM) through…

Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main…

Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform developed to mitigate these issues.…

Speech Translation (ST) is a machine translation task that involves converting speech signals from one language to the corresponding text in another language; this task has two different approaches, namely the traditional cascade and the…

Text documents are structured on multiple levels of detail: individual words are related by syntax, but larger units of text are related by discourse structure. Existing language models generally fail to account for discourse structure, but…

Long-context language modeling is commonly framed as a scalability challenge of token-level attention, yet local-to-global information structuring remains largely implicit in existing approaches. Drawing on cognitive theories of discourse…

Lexical ambiguity is a challenging and pervasive problem in machine translation (\mt). We introduce a simple and scalable approach to resolve translation ambiguity by incorporating a small amount of extra-sentential context in neural \mt.…

Recent advancements in speech-language models have yielded significant improvements in speech tokenization and synthesis. However, effectively mapping the complex, multidimensional attributes of speech into discrete tokens remains…

It is well known that translations generated by an excellent document-level neural machine translation (NMT) model are consistent and coherent. However, existing sentence-level evaluation metrics like BLEU can hardly reflect the model's…

We propose a new architecture for adapting a sentence-level sequence-to-sequence transformer by incorporating multiple pretrained document context signals and assess the impact on translation performance of (1) different pretraining…

In the realm of spoken language understanding (SLU), numerous natural language understanding (NLU) methodologies have been adapted by supplying large language models (LLMs) with transcribed speech instead of conventional written text. In…

ASR systems often struggle with maintaining syntactic and semantic accuracy in long audio transcripts, impacting tasks like Named Entity Recognition (NER), capitalization, and punctuation. We propose a novel approach that enhances ASR by…

Document understanding with multimodal large language models (MLLMs) requires not only accurate answers but also explicit, evidence-grounded reasoning, especially in high-stakes scenarios. However, current document MLLMs still fall short of…