Search Results for author:
Found 10 papers, 6 papers with code
Clozer”:" Adaptable Data Augmentation for Cloze-style Reading Comprehension
Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task.
Contrastive Learning for Inference in Dialogue
Inference, especially those derived from inductive processes, is a crucial component in our conversation to complement the information implicitly or explicitly conveyed by a speaker.
InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems
We present InstructTODS, a novel off-the-shelf framework for zero-shot end-to-end task-oriented dialogue systems that can adapt to diverse domains without fine-tuning.
PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems
Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses.
Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition
In this work, we analyze the transferability of emotion recognition across three different languages--English, Mandarin Chinese, and Cantonese; and 2 different age groups--adults and the elderly.
InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning
Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting.
Learn What NOT to Learn: Towards Generative Safety in Chatbots
Our approach differs from the standard contrastive learning framework in that it automatically obtains positive and negative signals from the safe and unsafe language distributions that have been learned beforehand.
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
It is, for example, better at deductive than inductive reasoning.
Every picture tells a story: Image-grounded controllable stylistic story generation
Generating a short story out of an image is arduous.
Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension
Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task.
