Related papers: Bridging Discourse Treebanks with a Unified Rhetor…

RST-style discourse parsing plays a vital role in many NLP tasks, revealing the underlying semantic/pragmatic structure of potentially complex and diverse documents. Despite its importance, one of the most prevailing limitations in modern…

Chain-of-Thought (CoT) reasoning has been widely adopted to enhance Large Language Models (LLMs) by decomposing complex tasks into simpler, sequential subtasks. However, extending CoT to vision-language reasoning tasks remains challenging,…

Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the…

This paper presents a unified multi-speaker encoder (UME), a novel architecture that jointly learns representations for speaker diarization (SD), speech separation (SS), and multi-speaker automatic speech recognition (ASR) tasks using a…

Discourse understanding is essential for many NLP tasks, yet most existing work remains constrained by framework-dependent discourse representations. This work investigates whether large language models (LLMs) capture discourse knowledge…

Although the deep integration of the Automatic Speech Recognition (ASR) system with Large Language Models (LLMs) has significantly improved accuracy, the deployment of such systems in low-latency streaming scenarios remains challenging. In…

Recent parameter-efficient language model tuning (PELT) methods manage to match the performance of fine-tuning with much fewer trainable parameters and perform especially well when training data is limited. However, different PELT methods…

Distant supervision (DS) is a well established technique for creating large-scale datasets for relation extraction (RE) without using human annotations. However, research in DS-RE has been mostly limited to the English language.…

We present Maestro, a self-supervised training method to unify representations learnt from speech and text modalities. Self-supervised learning from speech signals aims to learn the latent structure inherent in the signal, while…

Existing long-document question answering systems typically process texts as flat sequences or use heuristic chunking, which overlook the discourse structures that naturally guide human comprehension. We present a discourse-aware…

We introduce the MultiLang Code Parser Dataset (MLCPD), a large-scale, language-agnostic dataset unifying syntactic and structural representations of code across ten major programming languages. MLCPD contains over seven million parsed…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Open-source large language models (LLMs) have gained significant strength across diverse fields. Nevertheless, the majority of studies primarily concentrate on English, with only limited exploration into the realm of multilingual abilities.…

Automated radiology report generation (RRG) for breast ultrasound (BUS) is limited by the lack of paired image-report datasets and the risk of hallucinations from large language models. We propose BUSTR, a multitask vision-language…

We describe a cross-lingual adaptation method based on syntactic parse trees obtained from the Universal Dependencies (UD), which are consistent across languages, to develop classifiers in low-resource languages. The idea of UD parsing is…

Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one…

Unsupervised cross-lingual speech representation learning (XLSR) has recently shown promising results in speech recognition by leveraging vast amounts of unlabeled data across multiple languages. However, standard XLSR model suffers from…

Pre-trained multilingual language models have become an important building block in multilingual natural language processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level…

In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this…

Large Language Models (LLMs) have demonstrated remarkable performance across various domains, including healthcare. However, their ability to effectively represent structured non-textual data, such as the alphanumeric medical codes used in…