Combining computational linguistics with sentence embedding to create a zero-shot NLIDB
ArrayAccessing relational databases using natural language is a challenging task, with existing methods often suffering from poor domain generalization and high computational costs. In this study, we propose a novel approach that eliminates the training phase
Yuriy Perezhohin +2 more
openalex +3 more sources
"We must work tirelessly to promote …": Mediating interpersonal commitment to material processes in English translation of Chinese political discourse. [PDF]
PLoS OneEvaluative items have been central in political translation studies. This paper extends previous research by focusing on "circumstances + material processes" expressions through data extracted from Chinese-English parallel corpus of Xi Jinping's ...
Li J, Chen S, Zhang Y.
europepmc +2 more sources
Promises and pitfalls of using LLMs to identify actor stances in political discourse. [PDF]
PLoS OneEmpirical research in the social sciences is often interested in understanding actor stances; the positions that social actors take regarding normative statements in societal discourse.
Walker V, Angst M.
europepmc +2 more sources
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, Few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning ...
Lei Wang +6 more
semanticscholar +1 more source
Better Zero-Shot Reasoning with Role-Play Prompting [PDF]
North American Chapter of the Association for Computational Linguistics, 2023 Modern large language models (LLMs) exhibit a remarkable capacity for role-playing, enabling them to embody not only human characters but also non-human entities.
Aobo Kong +6 more
semanticscholar +1 more source
Precise Zero-Shot Dense Retrieval without Relevance Labels [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 While dense retrieval has been shown to be effective and efficient across tasks and languages, it remains difficult to create effective fully zero-shot dense retrieval systems when no relevance labels are available.
Luyu Gao +3 more
semanticscholar +1 more source
Aligning Instruction Tasks Unlocks Large Language Models as Zero-Shot Relation Extractors [PDF]
Annual Meeting of the Association for Computational Linguistics, 2023 Recent work has shown that fine-tuning large language models (LLMs) on large-scale instruction-following datasets substantially improves their performance on a wide range of NLP tasks, especially in the zero-shot setting.
Kai Zhang +2 more
semanticscholar +1 more source
Fuzzy logic in linguistics: Its basic concepts and terminology [PDF]
Južnoslovenski Filolog, 2010 In this article the implementation of fuzzy logic in linguistics is concerned, with special reference to so-called ‘fuzzy linguistics’ and ‘cognitive linguistics’.
Radovanović Milorad
doaj +1 more source
Journal of World Languages, 2021 Widely studied in fields like education, psychology, and linguistics, readability can be defined as (a) reader’s understanding of a reading text, (b) features of a text, or (c) the matching of a text to its reader.
Liu Yan
doaj +1 more source
The Associative Dictionary of Media Events in the Early XXI Century: a New Lexicographic Concept
Вестник Кемеровского государственного университета, 2021 The article introduces a new concept of the Associative Dictionary of Media Events of the Early XXI Century. The project continues the traditions of common lexicography.
Ya. A. Dudareva +2 more
doaj +1 more source