Results 1 to 10 of about 1,460 (118)

The Multidimensional Nature of Semantic Transparency in a Cross-Linguistic Perspective: Evidence From Human Intuitions, Computational Estimates, and Processing Data for Chinese Compounds. [PDF]

Cogn Sci
Abstract Semantic transparency is a key construct for understanding how complex words are represented and processed, yet it has been conceptualized and operationalized in diverse ways across studies. In this study, we validate whether semantic transparency exhibits multidimensional properties across different measures in Mandarin Chinese.
Chen J, Chersoni E, Marelli M, Huang CR.
europepmc   +2 more sources

HyperText: Endowing FastText with Hyperbolic Geometry [PDF]

Findings of the Association for Computational Linguistics: EMNLP 2020, 2020
Natural language data exhibit tree-like hierarchical structures such as the hypernym-hyponym relations in WordNet. FastText, as the state-of-the-art text classifier based on shallow neural network in Euclidean space, may not model such hierarchies precisely with limited representation capacity.
Zhu, Yudong, Zhou, Di, Xiao, Jinghui, Jiang, Xin, Chen, Xiao, Liu, Qun   +5 more
openaire   +2 more sources

Probabilistic FastText for Multi-Sense Word Embeddings [PDF]

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018
We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams.
Athiwaratkun, Ben, Wilson, Andrew Gordon, Anandkumar, Anima   +2 more
openaire   +3 more sources

FastText-Based Intent Detection for Inflected Languages [PDF]

Information, 2019
Intent detection is one of the main tasks of a dialogue system. In this paper, we present our intent detection system that is based on fastText word embeddings and a neural network classifier. We find an improvement in fastText sentence vectorization, which, in some cases, shows a significant increase in intent detection accuracy.
Kaspars Balodis, Daiga Deksne
openaire   +2 more sources

Requirements Classification Using FastText and BETO in Spanish Documents

, 2023
Requirements classification using fastText and BETO in Spanish documents. Published version of code and datasets used. Cited as: Limaylla-Lunarejo, M. I., Condori-Fernandez, N., & Luaces, M. R. (2023, April). Requirements Classification Using FastText and BETO in Spanish Documents.
Lunarejo, María Isabel Limaylla, Condori-Fernandez, Nelly, Luaces, Miguel R.   +2 more
openaire   +2 more sources

Hierarchical Classification Algorithm Based on FastText

DEStech Transactions on Environment, Energy and Earth Sciences, 2019
At present, methods for automatic assigning labels for literature using the Chinese Library Classification system are mostly based on machine learning methods, and many use the build knowledge base to improve classification effect. These methods are applicable to small-scale dataset, and as the categorical numbers increase, the classification effect ...
Yaxin RAN, Hongqi HAN, Yunliang ZHANG, Xiaorui ZHAI, Mengjuan WENG   +4 more
openaire   +2 more sources

Utilizing FastText for Venue Recommendation

, 2020
Venue recommendation systems model the past interactions (i.e., check-ins) of the users and recommend venues. Traditional recommendation systems employ collaborative filtering, content-based filtering or matrix factorization. Recently, vector space embedding and deep learning algorithms are also used for recommendation. In this work, I propose a method
openaire   +2 more sources

Exploring Swedish & English fastText Embeddings

, 2022
In this paper, we show that embeddings from relatively smaller corpora sometimes outperform thosefrom larger corpora and we introduce a new Swedish analogy test set and make it publicly available.To achieve good performance in Natural Language Processing (NLP) downstream tasks, several factorsplay important roles: dataset size, the right hyper ...
Adewumi, Oluwatosin, Liwicki, Foteini, Liwicki, Marcus   +2 more
openaire   +1 more source

MicrobeDiscover: A Knowledge Graph–Enabled AI Framework for Identifying Microbes for Inorganic Nanomaterial Biosynthesis

Advanced Science, EarlyView.
Microbial synthesis of nanomaterials (NMs) is eco‐friendly, but the screening of microorganisms is limited by inefficient traditional methods (currently only involving∽400 microorganisms/90 NMs). We propose AI framework MicrobeDiscover, integrating a knowledge graph of microbe‐NM interactions.
Ludi Wang, Hexing Han, Yufeng Liu, Zhiyuan Ning, Yujie Ma, Haidan Wang, Jinling Xu, Qiansheng Huang, Wenjuan Cui, Yuanchun Zhou, Yang Gao, Bin Wang, Yi Du   +12 more
wiley   +1 more source

Consumer Acceptance of Conversational Bots: Systematic Literature Review and Meta‐Analysis

Journal of Consumer Behaviour, EarlyView.
ABSTRACT As consumers increasingly rely on conversational bots for daily tasks, evidence surrounding motivations for acceptance remains scattered. A systematic literature review (SLR) was conducted on 64 journal articles published between 2008 and 2024, of which 48 provided sufficient quantitative data for inclusion in a meta‐analysis.
Omar H. Fares, Seung Hwan (Mark) Lee
wiley   +1 more source