1 code implementation • 24 Apr 2023 • Yucheng Li
Large language models (LLMs) have received significant attention by achieving remarkable performance across various tasks.
1 code implementation • 9 Oct 2023 • Yucheng Li, Bo Dong, Chenghua Lin, Frank Guerin
This paper proposes a method called Selective Context that enhances the inference efficiency of LLMs by identifying and pruning redundancy in the input context to make the input more compact.
1 code implementation • 10 Jun 2022 • Yucheng Li, Chenghua Lin, Frank Geurin
Metaphor generation is a challenging task which can impact many downstream tasks such as improving user satisfaction with dialogue systems and story generation.
1 code implementation • COLING 2022 • Yucheng Li, Chenghua Lin, Frank Guerin
The metaphor identification module is able to perform a self-training procedure, which discovers novel metaphors from a large-scale unlabeled corpus for NM generation.
1 code implementation • 19 Sep 2023 • Yucheng Li
Data contamination in model evaluation is getting increasingly prevalent as the massive training corpora of large language models often unintentionally include benchmark samples.
1 code implementation • 26 Oct 2023 • Yucheng Li, Frank Guerin, Chenghua Lin
We also introduce an open-source pipeline that enables the community to perform contamination analysis on customised data and models.
1 code implementation • 9 Feb 2023 • Yucheng Li, Shun Wang, Chenghua Lin, Frank Guerin, Loïc Barrault
In this paper, we propose FrameBERT, a RoBERTa-based model that can explicitly learn and incorporate FrameNet Embeddings for concept-level metaphor detection.
1 code implementation • 1 Feb 2024 • Yucheng Li, Yunhao Guo, Frank Guerin, Chenghua Lin
We measure: 1) the compression performance on the testing period as a measure of generalization on unseen data; and 2) the performance gap between the training and testing period as a measure of robustness.
1 code implementation • 19 Dec 2023 • Yucheng Li, Frank Guerin, Chenghua Lin
LatestEval avoids data contamination by only using texts published within a recent time window, ensuring no overlap with the training corpora of pre-trained language models.
1 code implementation • 11 Feb 2023 • Shun Wang, Yucheng Li, Chenghua Lin, Loïc Barrault, Frank Guerin
We propose a novel RoBERTa-based model, RoPPT, which introduces a target-oriented parse tree structure in metaphor detection.
1 code implementation • 30 Jan 2023 • Yucheng Li, Frank Guerin, Chenghua Lin
Metaphors are proven to have stronger emotional impact than literal expressions.
1 code implementation • 12 Apr 2016 • Wenying Ma, Liangliang Cao, Lei Yu, Guoping Long, Yucheng Li
We also applied GPU-FV for realtime video monitoring tasks and found that GPU-FV outperforms a number of previous works.
no code implementations • Findings of the Association for Computational Linguistics 2020 • Xinwei Long, Shuzi Niu, Yucheng Li
Named Entity Recognition (NER) is deeply explored and widely used in various tasks.
no code implementations • 30 May 2022 • Jin Chen, Defu Lian, Yucheng Li, Baoyun Wang, Kai Zheng, Enhong Chen
Recommender retrievers aim to rapidly retrieve a fraction of items from the entire item corpus when a user query requests, with the representative two-tower model trained with the log softmax loss.
1 code implementation • 26 May 2023 • Yucheng Li, Shun Wang, Chenghua Lin, Guerin Frank
One noticeable trend in metaphor detection is the embrace of linguistic theories such as the metaphor identification procedure (MIP) for model architecture design.
no code implementations • 29 Jan 2024 • Yucheng Li, Frank Guerin, Chenghua Lin
In this paper, we test various NLP models on the VUA metaphor dataset and quantify to what extent metaphors affect models' performance on various downstream tasks.