257 citations · 625 across the 31 of their papers we have counts for
7 papers · 1 filter
Go-tuning: Improving Zero-shot Learning Abilities of Smaller Language Models
Jingjing Xu, Qingxiu Dong, Hongyi Liu +1
With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3. However, thes…
Lego-MT: Learning Detachable Models for Massively Multilingual Machine Translation
Fei Yuan, Yinquan Lu, WenHao Zhu +4
Multilingual neural machine translation (MNMT) aims to build a unified model for many language directions. Existing monolithic models for MNMT encounter two challenges: parameter i…
BigText-QA: Question Answering over a Large-Scale Hybrid Knowledge Graph
Jingjing Xu, Maria Biryukov, Martin Theobald +1
Answering complex questions over textual resources remains a challenge, particularly when dealing with nuanced relationships between multiple entities expressed within natural-lang…
Enhancing and Adversarial: Improve ASR with Speaker Labels
Wei Zhou, Haotian Wu, Jingjing Xu +4
ASR can be improved by multi-task learning (MTL) with domain enhancing or domain adversarial training, which are two opposite objectives with the aim to increase/decrease domain va…
Calibrating Factual Knowledge in Pretrained Language Models
Qingxiu Dong, Damai Dai, Yifan Song +3
Previous literature has proved that Pretrained Language Models (PLMs) can store factual knowledge. However, we find that facts stored in the PLMs are not always correct. It motivat…
Improving the Training Recipe for a Robust Conformer-based Hybrid Model
Mohammad Zeineldeen, Jingjing Xu, Christoph Lüscher +2
Speaker adaptation is important to build robust automatic speech recognition (ASR) systems. In this work, we investigate various methods for speaker adaptive training (SAT) based o…