Filters








1,780 Hits in 4.0 sec

Bag-of-Vector Embeddings of Dependency Graphs for Semantic Induction [article]

Diana Nicoleta Popa, James Henderson
2017 arXiv   pre-print
We demonstrate the usefulness of this representation by training bag-of-vector embeddings of dependency graphs and evaluating them on unsupervised semantic induction for the Semantic Textual Similarity  ...  In this paper we propose bag-of-vector embeddings of arbitrary linguistic graphs.  ...  In addition, several theoretical properties motivate the proposed algorithms for learning a model of embedding graphs in a bag-of-vectors and for inferring the bag-of-vector embedding of a graph given  ... 
arXiv:1710.00205v1 fatcat:pzdh3nsepnhjxo7qxclahm4ivu

Russian word sense induction by clustering averaged word embeddings [article]

Andrey Kutuzov
2018 arXiv   pre-print
It implied representing contexts of ambiguous words as averaged word embedding vectors, using off-the-shelf pre-trained distributional models.  ...  The paper reports our participation in the shared task on word sense induction and disambiguation for the Russian language (RUSSE-2018).  ...  Table1: Clustering performance (ARI) on the training sets, depending on the pre-trained word embedding model Table2: Clustering performance (ARI) depending on the parameters of word vector averaging Finally  ... 
arXiv:1805.02258v1 fatcat:jr4rqt34xzh25nx4pamu67uyz4

Entity Embeddings with Conceptual Subspaces as a Basis for Plausible Reasoning [article]

Shoaib Jameel, Steven Schockaert
2017 arXiv   pre-print
To address this issue, we propose a method which learns a vector-space embedding of entities from Wikipedia and constrains this embedding such that entities of the same semantic type are located in some  ...  While conceptual spaces enable elegant models of various cognitive phenomena, the lack of automated methods for constructing such representations have so far limited their application in artificial intelligence  ...  The idea of embedding knowledge graphs in a vector space was proposed in [3] .  ... 
arXiv:1602.05765v2 fatcat:4v2bnavl3jcz3inwpqi3rnmj4a

Semantic Relations and Deep Learning [article]

Vivi Nastase, Stan Szpakowicz
2021 arXiv   pre-print
The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www.morganclaypoolpublishers.com  ...  This is Chapter 5, made public by the kind permission of Morgan & Claypool.  ...  There are various methods of embedding a graph in a continuous vector space.  ... 
arXiv:2009.05426v4 fatcat:rmzoalfwcza4nex7pd4u6w7kbe

Making Sense of Word Embeddings

Maria Pelevina, Nikolay Arefiev, Chris Biemann, Alexander Panchenko
2016 Proceedings of the 1st Workshop on Representation Learning for NLP  
Huang et al. (2012) learn arXiv:1708.03390v1 [cs.CL] 10 Aug 2017 Calculate Word Similarity Graph Learning Word Vectors Word Sense Induction Text Corpus Word Vectors Word Similarity Graph Pooling of Word  ...  We present a simple yet effective approach for learning word sense embeddings.  ...  Acknowledgments We acknowledge the support of the Deutsche Forschungsgemeinschaft (DFG) foundation under the project "JOIN-T: Joining Ontologies and Semantics Induced from Text".  ... 
doi:10.18653/v1/w16-1620 dblp:conf/rep4nlp/PelevinaABP16 fatcat:w7pbdtqiqrfvteao3n6slsotri

Jointly Modeling Inter-Slot Relations by Random Walk on Knowledge Graphs for Unsupervised Spoken Language Understanding

Yun-Nung Chen, William Yang Wang, Alexander Rudnicky
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
In this paper, we exploit the typed syntactic dependency theory for unsupervised induction and filling of semantics slots in spoken dialogue systems.  ...  A key challenge of designing coherent semantic ontology for spoken language understanding is to consider inter-slot relations.  ...  Acknowledgments We thank Anatole Gershman for helpful discussions and anonymous reviewers for their useful comments. We are also grateful to MetLife's support.  ... 
doi:10.3115/v1/n15-1064 dblp:conf/naacl/ChenWR15 fatcat:7qxwmqgkj5c3dcwj7l33yqvhmy

Unsupervised Learning and Modeling of Knowledge and Intent for Spoken Dialogue Systems

Yun-Nung Chen
2015 Proceedings of the ACL-IJCNLP 2015 Student Research Workshop  
After replacing original bag-of-words contexts with dependency-based Figure 2 . 2 10: The framework for learning paragraph vectors.  ...  Dependency-Based Word Embedding Most neural embeddings use linear bag-of-words contexts, where a window size is defined to produce contexts of the target words [117, 118, 119] .  ... 
doi:10.3115/v1/p15-3001 dblp:conf/acl/Chen15 fatcat:kfxqwlfgpfgl7maz25j42nebme

Matrix Factorization with Knowledge Graph Propagation for Unsupervised Spoken Language Understanding

Yun-Nung Chen, William Yang Wang, Anatole Gershman, Alexander Rudnicky
2015 Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)  
This paper introduces a novel matrix factorization (MF) approach to learn latent feature vectors for utterances and semantic elements without the need of corpus annotations.  ...  graph and a word-based lexical graph.  ...  Acknowledgments We thank anonymous reviewers for their useful comments and Prof. Manfred Stede for his mentoring. We are also grateful to MetLife's support.  ... 
doi:10.3115/v1/p15-1047 dblp:conf/acl/ChenWGR15 fatcat:nlb4lvynjvf5hegldu4togauce

Ontology-Aware Biomedical Relation Extraction [article]

Ahmad Aghaebrahimian, Maria Anisimova, Manuel Gil
2022 bioRxiv   pre-print
We demonstrate that entity type and ontology graph structure provide better representations than simple token-based representations for RE.  ...  The state-of-the-art systems often use resource-intensive hence slow algorithms and largely work for a particular type of relationship.  ...  The impact of the transductive and inductive approaches for preventing data leakage on ontology graph embeddings are also examined.  ... 
doi:10.1101/2022.03.22.485304 fatcat:p5z2rsfzsnh4pgtenhx47k4fwi

Sparse Structure Learning via Graph Neural Networks for Inductive Document Classification [article]

Yinhua Piao, Sangseon Lee, Dohoon Lee, Sun Kim
2022 arXiv   pre-print
For inductive learning, the refined document graph is further fed into a general readout function for graph-level classification and optimization in an end-to-end manner.  ...  dependency.  ...  ., bag-of-words, term frequency-inverse document frequency.  ... 
arXiv:2112.06386v2 fatcat:v5bztrfi3fe4rbauefulbck4v4

A framework for enriching lexical semantic resources with distributional semantics

CHRIS BIEMANN, STEFANO FARALLI, ALEXANDER PANCHENKO, SIMONE PAOLO PONZETTO
2018 Natural Language Engineering  
We then automatically disambiguate such representations to obtain a full-fledged proto-conceptualization, i.e. a typed graph of induced word senses.  ...  hypernym graphs and learning taxonomies from scratch.  ...  (i.e., WordNet and BabelNet) (see Section 6.3) in the Linked Open Data Cloud; iii) the types of the unmapped PCZ senses produced in the third experiment (see Section 6.4).  ... 
doi:10.1017/s135132491700047x fatcat:z6acyjpzpvduzjvzmrrsddity4

Distributed Representations for Unsupervised Semantic Role Labeling

Kristian Woodsend, Mirella Lapata
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
We present a new approach for unsupervised semantic role labeling that leverages distributed representations.  ...  The induced representations are clustered into roles using a linear programming formulation of hierarchical clustering, where we can model task-specific knowledge.  ...  Acknowledgements We would like to thank Miguel Forte and members of the ILCC at the School of Informatics for their valuable feedback.  ... 
doi:10.18653/v1/d15-1295 dblp:conf/emnlp/WoodsendL15 fatcat:fjx4tbyqkzhpbhlyzoczbzhbly

Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction [article]

Dmitry Ustalov and Alexander Panchenko and Chris Biemann and Simone Paolo Ponzetto
2019 arXiv   pre-print
unsupervised semantic frame induction from dependency triples, and unsupervised semantic class induction from a distributional thesaurus.  ...  We present a detailed theoretical and computational analysis of the Watset meta-algorithm for fuzzy graph clustering, which has been found to be widely applicable in a variety of domains.  ...  Foundation for Basic Research (RFBR) under the project no. 16-37-00354 мол_а.  ... 
arXiv:1808.06696v3 fatcat:jdd5cnkhffhaxlti72oskgleye

Watset: Local-Global Graph Clustering with Applications in Sense and Frame Induction

Dmitry Ustalov, Alexander Panchenko, Chris Biemann, Simone Paolo Ponzetto
2019 Computational Linguistics  
unsupervised semantic frame induction from dependency triples, and unsupervised semantic class induction from a distributional thesaurus.  ...  We present a detailed theoretical and computational analysis of the Watset meta-algorithm for fuzzy graph clustering, which has been found to be widely applicable in a variety of domains.  ...  We thank Bonaventura Coppolla for discussions and preliminary work on graph-based frame induction and Andrei Kutuzov, who conducted experiments with the HOSG-based baseline related to the frame induction  ... 
doi:10.1162/coli_a_00354 fatcat:b5dr23gh6var3fnzjdgztzdjni

MEmbER

Shoaib Jameel, Zied Bouraoui, Steven Schockaert
2017 Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval - SIGIR '17  
We propose a new class of methods for learning vector space embeddings of entities.  ...  that are derived from a bagof-words representation of the entities. e resulting vector spaces provide us with a natural vehicle for identifying entities that have a given property (or ranking them according  ...  Vector space embeddings Our approach is related to two popular types of vector space representations: word embeddings and knowledge graph embeddings.  ... 
doi:10.1145/3077136.3080803 dblp:conf/sigir/JameelBS17 fatcat:ixid6gnp3jahtfw7hdks7cdyaq
« Previous Showing results 1 — 15 out of 1,780 results