Related papers: Improving Cross-lingual Representation for Semanti…

Large language models (LLMs) are increasingly applied in multilingual contexts, yet their capacity for consistent, logically grounded alignment across languages remains underexplored. We present a controlled evaluation framework for…

Multilingual speech recognition for both monolingual and code-switching speech is a challenging task. Recently, based on the Mixture of Experts (MoE), many works have made good progress in multilingual and code-switching ASR, but present…

With the massive developments of end-to-end (E2E) neural networks, recent years have witnessed unprecedented breakthroughs in automatic speech recognition (ASR). However, the codeswitching phenomenon remains a major obstacle that hinders…

Code switching (CS) refers to the phenomenon of interchangeably using words and phrases from different languages. CS can pose significant accuracy challenges to NLP, due to the often monolingual nature of the underlying systems. In this…

Pre-trained language models have demonstrated powerful capabilities in the field of natural language processing (NLP). Recently, code pre-trained model (PTM), which draw from the experiences of the NLP field, have also achieved…

Code-switching, or switching between languages, occurs for many reasons and has important linguistic, sociological, and cultural implications. Multilingual speakers code-switch for a variety of purposes, such as expressing emotions,…

Recent work on Speech-to-Text Translation (S2TT) has focused on LLM-based models, introducing the increasingly adopted Chain-of-Thought (CoT) prompting, where the model is guided to first transcribe the speech and then translate it. CoT…

Multilingual code-switching research is often hindered by the lack and linguistically biased status of available datasets. To expand language representation, we synthesize code-switching data by replacing intonation units detected through…

In this work we present a systematic empirical study focused on the suitability of the state-of-the-art multilingual encoders for cross-lingual document and sentence retrieval tasks across a number of diverse language pairs. We first treat…

This thesis focuses on improving the pre-training of natural language models using unsupervised raw data to make them more efficient and aligned with downstream applications. In the first part, we introduce three alternative pre-training…

End-to-end spoken language understanding (SLU) remains elusive even with current large pretrained language models on text and speech, especially in multilingual cases. Machine translation has been established as a powerful pretraining…

We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We…

Traditional approaches to semantic parsing (SP) work by training individual models for each available parallel dataset of text-meaning pairs. In this paper, we explore the idea of polyglot semantic translation, or learning semantic parsing…

Multilingual transformer language models have recently attracted much attention from researchers and are used in cross-lingual transfer learning for many NLP tasks such as text classification and named entity recognition. However, similar…

Conversational search has been regarded as the next-generation search paradigm. Constrained by data scarcity, most existing methods distill the well-trained ad-hoc retriever to the conversational retriever. However, these methods, which…

In the realm of Sign Language Translation (SLT), reliance on costly gloss-annotated datasets has posed a significant barrier. Recent advancements in gloss-free SLT methods have shown promise, yet they often largely lag behind gloss-based…

Research in multilingual speech-to-text translation is topical. Having a single model that supports multiple translation tasks is desirable. The goal of this work it to improve cross-lingual transfer learning in multilingual speech-to-text…

Multilingual semantic parsing is a cost-effective method that allows a single model to understand different languages. However, researchers face a great imbalance of availability of training data, with English being resource rich, and other…

Semantic retrieval, which retrieves semantically matched items given a textual query, has been an essential component to enhance system effectiveness in e-commerce search. In this paper, we study the multimodal retrieval problem, where the…

Recent advances have enabled Large Language Models (LLMs) to tackle reasoning tasks by generating chain-of-thought (CoT) rationales, yet these gains have largely applied to high-resource languages, leaving low-resource languages behind. In…