Related papers: Dolphin: A Spoken Language Proficiency Assessment …

Most Chinese pre-trained models take character as the basic unit and learn representation according to character's external contexts, ignoring the semantics expressed in the word, which is the smallest meaningful utterance in Chinese.…

Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluations aligned with formal curricula and certification…

Previous approaches of analyzing spontaneously spoken language often have been based on encoding syntactic and semantic knowledge manually and symbolically. While there has been some progress using statistical or connectionist language…

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their…

Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-training paradigm for Chinese -- Lattice-BERT, which explicitly…

Research in dolphin communication and cognition requires detailed inspection of audible dolphin signals. The manual analysis of these signals is cumbersome and time-consuming. We seek to automate parts of the analysis using modern deep…

This study aims to develop an online Greek language learning platform via a learning management system based on the WordPress platform for primary school pupils with Russian as a mother tongue. The subject was chosen with a view to aid both…

This paper proposes a novel lip-reading driven deep learning framework for speech enhancement. The proposed approach leverages the complementary strengths of both deep learning and analytical acoustic modelling (filtering based approach) as…

Self-reflection on learning experiences constitutes a fundamental cognitive process, essential for the consolidation of knowledge and the enhancement of learning efficacy. However, traditional methods to facilitate reflection often face…

Most existing Visual Question Answering (VQA) systems tend to overly rely on language bias and hence fail to reason from the visual clue. To address this issue, we propose a novel Language-Prior Feedback (LPF) objective function, to…

We introduce SIFT (Speech Instruction Fine-Tuning), a 50M-example dataset designed for instruction fine-tuning and pre-training of speech-text large language models (LLMs). SIFT-50M is built from publicly available speech corpora, which…

Large Language Models (LLMs) have become integral to daily life, especially advancing as intelligent assistants through on-device deployment on smartphones. However, existing LLM evaluation benchmarks predominantly focus on objective tasks…

Design of dialogue systems has witnessed many advances lately, yet acquiring huge set of data remains an hindrance to their fast development for a new task or language. Besides, training interactive systems with batch data is not…

Widely used language models (LMs) are typically built by scaling up a two-stage training pipeline: a pre-training stage that uses a very large, diverse dataset of text and a fine-tuning (sometimes, 'alignment') stage that uses targeted…

We introduce Language Feedback Models (LFMs) that identify desirable behaviour - actions that help achieve tasks specified in the instruction - for imitation learning in instruction following. To train LFMs, we obtain feedback from Large…

Quantitative risk assessment in high-stakes domains relies on structured expert elicitation to estimate unobservable properties. The gold standard - the Delphi method - produces calibrated, auditable judgments but requires months of…

The evaluation of large language models is an essential task in the field of language understanding and generation. As language models continue to advance, the need for effective benchmarks to assess their performance has become imperative.…

Spoken language models (SLMs) have emerged as a unified paradigm for speech understanding and generation, enabling natural human machine interaction. However, while most progress has focused on semantic accuracy and instruction following,…

Pronouns are often dropped in Chinese conversations and recovering the dropped pronouns is important for NLP applications such as Machine Translation. Existing approaches usually formulate this as a sequence labeling task of predicting…

Large language models excel at instruction-following in English, but their performance in low-resource languages like Thai remains underexplored. Existing benchmarks often rely on translations, missing cultural and domain-specific nuances…