no code implementations • LREC 2022 • Peng Liu, Cristina Marco, Jon Atle Gulla
This method benefits from the English Sentiwordnet and a thesaurus in one of the target languages.
1 code implementation • 4 Apr 2024 • Lemei Zhang, Peng Liu, Yashar Deldjoo, Yong Zheng, Jon Atle Gulla
The emergence of Large Language Models (LLMs) has achieved tremendous success in the field of Natural Language Processing owing to diverse training paradigms that empower LLMs to effectively capture intricate linguistic patterns and semantic representations.
no code implementations • 3 Dec 2023 • Peng Liu, Lemei Zhang, Terje Nissen Farup, Even W. Lauvrak, Jon Espen Ingvaldsen, Simen Eide, Jon Atle Gulla, Zhirong Yang
To bridge these gaps, we introduce NLEBench, a comprehensive benchmark tailored for evaluating natural language generation capabilities in Norwegian, a low-resource language.
2 code implementations • 7 Feb 2023 • Peng Liu, Lemei Zhang, Jon Atle Gulla
The emergence of Pre-trained Language Models (PLMs) has achieved tremendous success in the field of Natural Language Processing (NLP) by learning universal representations on large corpora in a self-supervised manner.
no code implementations • 23 Dec 2022 • Lemei Zhang, Peng Liu, Jon Atle Gulla
Recent advances in graph-based learning approaches have demonstrated their effectiveness in modelling users' preferences and items' characteristics for Recommender Systems (RSS).
no code implementations • 9 Nov 2022 • Yujie Xing, Jon Atle Gulla
In this paper, we focus on an essential component of multi-turn generation-based conversational agents: context attention distribution, i. e. how systems distribute their attention on dialogue's context.
no code implementations • Findings (NAACL) 2022 • Yujie Xing, Jinglun Cai, Nils Barlaug, Peng Liu, Jon Atle Gulla
Furthermore, we propose Domain-specific Frequency (DF), a novel word-level importance weight that measures the relative importance of a word for a specific corpus compared to other corpora.
no code implementations • 21 Oct 2020 • Nils Barlaug, Jon Atle Gulla
In this survey, we present how neural networks have been used for entity matching.
no code implementations • COLING 2016 • Patrik F. Bakken, Terje A. Bratlie, Cristina Marco, Jon Atle Gulla
This paper presents classification results for the analysis of sentiment in political news articles.