Zobrazeno 1 - 10
of 200
pro vyhledávání: '"Demberg, Vera"'
Large Language Models (LLMs) can generate text by transferring style attributes like formality resulting in formal or informal text. However, instructing LLMs to generate text that when spoken, is more intelligible in an acoustically difficult enviro
Externí odkaz:
http://arxiv.org/abs/2408.04029
Despite attempts to make Large Language Models multi-lingual, many of the world's languages are still severely under-resourced. This widens the performance gap between NLP and AI applications aimed at well-financed, and those aimed at less-resourced
Externí odkaz:
http://arxiv.org/abs/2406.18776
Autor:
Pu, Dongqi, Demberg, Vera
For long document summarization, discourse structure is important to discern the key content of the text and the differences in importance level between sentences. Unfortunately, the integration of rhetorical structure theory (RST) into parameter-eff
Externí odkaz:
http://arxiv.org/abs/2405.00657
Nigerian Pidgin is an English-derived contact language and is traditionally an oral language, spoken by approximately 100 million people. No orthographic standard has yet been adopted, and thus the few available Pidgin datasets that exist are charact
Externí odkaz:
http://arxiv.org/abs/2404.18264
Scientific news reports serve as a bridge, adeptly translating complex research articles into reports that resonate with the broader public. The automated generation of such narratives enhances the accessibility of scholarly insights. In this paper,
Externí odkaz:
http://arxiv.org/abs/2403.17768
Pre-trained large language models, such as ChatGPT, archive outstanding performance in various reasoning tasks without supervised training and were found to have outperformed crowdsourcing workers. Nonetheless, ChatGPT's performance in the task of im
Externí odkaz:
http://arxiv.org/abs/2402.04918
A wide body of evidence shows that human language processing difficulty is predicted by the information-theoretic measure surprisal, a word's negative log probability in context. However, it is still unclear how to best estimate these probabilities n
Externí odkaz:
http://arxiv.org/abs/2311.09325
Recently, large pre-trained language models (LLMs) have demonstrated superior language understanding abilities, including zero-shot causal reasoning. However, it is unclear to what extent their capabilities are similar to human ones. We here study th
Externí odkaz:
http://arxiv.org/abs/2311.07311
Hallucinations in text generation occur when the system produces text that is not grounded in the input. In this work, we tackle the problem of hallucinations in neural chart summarization. Our analysis shows that the target side of chart summarizati
Externí odkaz:
http://arxiv.org/abs/2308.00399
Autor:
Chang, Ernie, Rashid, Muhammad Hassan, Lin, Pin-Jie, Zhao, Changsheng, Demberg, Vera, Shi, Yangyang, Chandra, Vikas
Knowing exactly how many data points need to be labeled to achieve a certain model performance is a hugely beneficial step towards reducing the overall budgets for annotation. It pertains to both active learning and traditional data annotation, and i
Externí odkaz:
http://arxiv.org/abs/2307.00374