Výsledky vyhledávání

Report

Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling

Autor: Wang, Longyue, Du, Zefeng, Liu, Donghuai, Cai, Deng, Yu, Dian, Jiang, Haiyun, Wang, Yan, Cui, Leyang, Shi, Shuming, Tu, Zhaopeng

Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing evaluation benchmarks primarily focus on the evaluation of inter-sente

Externí odkaz: http://arxiv.org/abs/2307.08074

Zobrazit plný text záznamu

Report

Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration

Autor: Lyu, Chenyang, Wu, Minghao, Wang, Longyue, Huang, Xinting, Liu, Bingshuai, Du, Zefeng, Shi, Shuming, Tu, Zhaopeng

Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text has not been fully studied. In this work, we propose Macaw-LLM, a novel

Externí odkaz: http://arxiv.org/abs/2306.09093

Zobrazit plný text záznamu

Report

A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models

Autor: Lyu, Chenyang, Du, Zefeng, Xu, Jitao, Duan, Yitao, Wu, Minghao, Lynn, Teresa, Aji, Alham Fikri, Wong, Derek F., Liu, Siyou, Wang, Longyue

Machine Translation (MT) has greatly advanced over the years due to the developments in deep neural networks. However, the emergence of Large Language Models (LLMs) like GPT-4 and ChatGPT is introducing a new phase in the MT domain. In this context,

Externí odkaz: http://arxiv.org/abs/2305.01181

Zobrazit plný text záznamu