23 citations · 66 across the 16 of their papers we have counts for
7 papers · 1 filter
Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding
Guangyu Yang, Jinghong Chen, Weizhe Lin +1
Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensiv…
Improving Hateful Meme Detection through Retrieval-Guided Contrastive Learning
Jingbiao Mei, Jinghong Chen, Weizhe Lin +2
Hateful memes have emerged as a significant concern on the Internet. Detecting hateful memes requires the system to jointly understand the visual and textual modalities. Our invest…
Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering
Weizhe Lin, Jinghong Chen, Jingbiao Mei +2
Knowledge-based Visual Question Answering (KB-VQA) requires VQA systems to utilize knowledge from external knowledge bases to answer visually-grounded questions. Retrieval-Augmente…
Grounding Description-Driven Dialogue State Trackers with Knowledge-Seeking Turns
Alexandru Coca, Bo-Hsiang Tseng, Jinghong Chen +4
Schema-guided dialogue state trackers can generalise to new domains without further training, yet they are sensitive to the writing style of the schemata. Augmenting the training s…
FVQA 2.0: Introducing Adversarial Samples into Fact-based Visual Question Answering
Weizhe Lin, Zhilin Wang, Bill Byrne
The widely used Fact-based Visual Question Answering (FVQA) dataset contains visually-grounded questions that require information retrieval using common sense knowledge graphs to a…
More Robust Schema-Guided Dialogue State Tracking via Tree-Based Paraphrase Ranking
A. Coca, B. H. Tseng, W. Lin +1
The schema-guided paradigm overcomes scalability issues inherent in building task-oriented dialogue (TOD) agents with static ontologies. Instead of operating on dialogue context al…
Schema-Guided Semantic Accuracy: Faithfulness in Task-Oriented Dialogue Response Generation
Jinghong Chen, Weizhe Lin, Bill Byrne
Ensuring that generated utterances are faithful to dialogue actions is crucial for Task-Oriented Dialogue Response Generation. Slot Error Rate (SER) only partially measures generat…