71 citations · 179 across the 16 of their papers we have counts for
17 papers
PandaGPT: One Model To Instruction-Follow Them All
Yixuan Su, Tian Lan, Huayang Li +3
We present PandaGPT, an approach to emPower large lANguage moDels with visual and Auditory instruction-following capabilities. Our pilot experiments show that PandaGPT can perform…
Multi-Task Instruction Tuning of LLaMa for Specific Scenarios: A Preliminary Study on Writing Assistance
Yue Zhang, Leyang Cui, Deng Cai +3
Proprietary Large Language Models (LLMs), such as ChatGPT, have garnered significant attention due to their exceptional capabilities in handling a diverse range of tasks. Recent st…
A Frustratingly Simple Decoding Method for Neural Text Generation
Haoran Yang, Deng Cai, Huayang Li +3
We introduce a frustratingly simple, super efficient and surprisingly effective decoding method, which we call Frustratingly Simple Decoding (FSD), for neural text generation. The…
LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup
Xiaohu Tang, Yang Wang, Ting Cao +5
On-device Deep Neural Network (DNN) inference consumes significant computing resources and development efforts. To alleviate that, we propose LUT-NN, the first system to empower in…
-gram Is Back: Residual Learning of Neural Text Generation with -gram Language Model
Huayang Li, Deng Cai, Jin Xu +1
-gram language models (LM) have been largely superseded by neural LMs as the latter exhibits better performance. However, we find that -gram models can achieve satisfactory p…
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
Deng Cai, Xin Li, Jackie Chun-Sing Ho +2
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a struct…
Automatic Prosody Annotation with Pre-Trained Text-Speech Model
Ziqian Dai, Jianwei Yu, Yan Wang +5
Prosodic boundary plays an important role in text-to-speech synthesis (TTS) in terms of naturalness and readability. However, the acquisition of prosodic boundary labels relies on…
Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation
Jin Xu, Xiaojiang Liu, Jianhao Yan +3
While large-scale neural language models, such as GPT2 and BART, have achieved impressive results on various text generation tasks, they tend to get stuck in undesirable sentence-l…
Frame-wise Action Representations for Long Videos via Sequence Contrastive Learning
Minghao Chen, Fangyun Wei, Chong Li +1
Prior works on action representation learning mainly focus on designing various architectures to extract the global representations for short video clips. In contrast, many practic…
Linearizing Transformer with Key-Value Memory
Yizhe Zhang, Deng Cai
Efficient transformer variants with linear time complexity have been developed to mitigate the quadratic computational overhead of the vanilla transformer. Among them are low-rank…
A Survey on Retrieval-Augmented Text Generation
Huayang Li, Yixuan Su, Deng Cai +2
Recently, retrieval-augmented text generation attracted increasing attention of the computational linguistics community. Compared with conventional generation models, retrieval-aug…
Measuring and Reducing Model Update Regression in Structured Prediction for NLP
Deng Cai, Elman Mansimov, Yi-An Lai +3
Recent advance in deep learning has led to the rapid adoption of machine learning-based NLP models in a wide range of applications. Despite the continuous gain in accuracy, backwar…
TopNet: Learning from Neural Topic Model to Generate Long Stories
Yazheng Yang, Boyuan Pan, Deng Cai +1
Long story generation (LSG) is one of the coveted goals in natural language processing. Different from most text generation tasks, LSG requires to output a long story of rich conte…
Multilingual AMR Parsing with Noisy Knowledge Distillation
Deng Cai, Xin Li, Jackie Chun-Sing Ho +2
We study multilingual AMR parsing from the perspective of knowledge distillation, where the aim is to learn and improve a multilingual AMR parser by using an existing English parse…
Exploring Dense Retrieval for Dialogue Response Selection
Tian Lan, Deng Cai, Yan Wang +3
Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to c…
Exploiting Reasoning Chains for Multi-hop Science Question Answering
Weiwen Xu, Yang Deng, Huihui Zhang +2
We propose a novel Chain Guided Retriever-reader ({\tt CGR}) framework to model the reasoning chain for multi-hop Science Question Answering. Our framework is capable of performing…
ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding
Lingyun Feng, Jianwei Yu, Deng Cai +3
Language understanding in speech-based systems have attracted much attention in recent years with the growing demand for voice interface applications. However, the robustness of na…