Related papers: Bilingual Rhetorical Structure Parsing with Large …

Human communication is a collaborative process. Speakers, on top of conveying their own intent, adjust the content and language expressions by taking the listeners into account, including their knowledge background, personalities, and…

End-to-end speech-to-speech (S2S) dialogue systems have recently garnered increasing research attention for their lower latency and more natural integration of nonverbal cues such as emotion and speaker identity. However, these systems face…

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…

Matching natural language sentences is central for many applications such as information retrieval and question answering. Existing deep models rely on a single sentence representation or multiple granularity representations for matching.…

Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence…

In the era of increasingly sophisticated natural language processing (NLP) systems, large language models (LLMs) have demonstrated remarkable potential for diverse applications, including tasks requiring nuanced textual understanding and…

Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text,…

In this study, we present synchronous bilingual Connectionist Temporal Classification (CTC), an innovative framework that leverages dual CTC to bridge the gaps of both modality and language in the speech translation (ST) task. Utilizing…

Previous attempts at RST-style discourse segmentation typically adopt features centered on a single token to predict whether to insert a boundary before that token. In contrast, we develop a discourse segmenter utilizing a set of pairing…

Semantic similarity between two sentences depends on the aspects considered between those sentences. To study this phenomenon, Deshpande et al. (2023) proposed the Conditional Semantic Textual Similarity (C-STS) task and annotated a…

Large Language Models produce sequences learned as statistical patterns from large corpora. In order not to reproduce corpus biases, after initial training models must be aligned with human values, preferencing certain continuations over…

Recent advancements in large language models (LLMs) have highlighted their potential across a variety of tasks, but their performance still heavily relies on the design of effective prompts. Existing methods for automatic prompt…

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or…

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems. Multi-task training enables the sharing of the neural network layers…

Simultaneous speech translation (SST) outputs translations in parallel with streaming speech input, balancing translation quality and latency. While large language models (LLMs) have been extended to handle the speech modality, streaming…

Modern sentence-level NMT systems often produce plausible translations of isolated sentences. However, when put in context, these translations may end up being inconsistent with each other. We propose a monolingual DocRepair model to…

Given the great success of large language models (LLMs) across various tasks, in this paper, we introduce LLM-ST, a novel and effective speech translation model constructed upon a pre-trained LLM. By integrating the large language model…

This paper presents a challenge to the community: given a large corpus of written text aligned to its normalized spoken form, train an RNN to learn the correct normalization function. We present a data set of general text where the…

Semantic parsing offers many opportunities to improve natural language understanding. We present a semantically annotated parallel corpus for English, German, Italian, and Dutch where sentences are aligned with scoped meaning…

We introduce LibriTTS-P, a new corpus based on LibriTTS-R that includes utterance-level descriptions (i.e., prompts) of speaking style and speaker-level prompts of speaker characteristics. We employ a hybrid approach to construct prompt…