A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Filters
Multilingual Word Sense Disambiguation with Unified Sense Representation
[article]
2022
arXiv
pre-print
Preserved Fulltext
With the unified sense representations, annotations from multiple languages can be jointly trained to benefit the MWSD tasks. ...
languages, we propose building knowledge and supervised-based Multilingual Word Sense Disambiguation (MWSD) systems. ...
Conclusion and Future Work In this paper, to build feasible knowledge and supervised based systems for multilingual word sense disambiguation, we propose to construct unified sense representation by utilizing ...
arXiv:2210.07447v1
fatcat:lagdztw7mbdirdf4zkl4t4lxpi
EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text
2017
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
In this paper we present EUROSENSE, a multilingual sense-annotated resource based on the joint disambiguation of the Europarl parallel corpus, with almost 123 million sense annotations for over 155 thousand ...
We evaluate the quality of our sense annotations intrinsically and extrinsically, showing their effectiveness as training data for Word Sense Disambiguation. ...
languages within a unified sense inventory. ...
doi:10.18653/v1/p17-2094
dblp:conf/acl/BoviCRN17
fatcat:5lxbfiik35em3fybqhnwzmfhju
Semi Supervised Preposition-Sense Disambiguation using Multilingual Data
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We show that signals from unannotated multilingual data can be used to improve supervised preposition-sense disambiguation. ...
The multilingual signals consistently improve results on two preposition-sense datasets. ...
Using the representation for sense classification Once the encoder is trained over the multilingual data, we incorporate it in the supervised sense-disambiguation model by concatenating the representation ...
arXiv:1611.08813v1
fatcat:wkjpkoyfbvfrtjhlkitn33xwge
A Unified Multilingual Semantic Representation of Concepts
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)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2015; you can also visit the original URL.
The file type is application/pdf.
We put forward a novel multilingual concept representation, called MUFFIN, which not only enables accurate representation of word senses in different languages, but also provides multiple advantages over ...
However, most existing semantic representation techniques cannot be used effectively for the representation of individual word senses. ...
Conclusions This paper presented MUFFIN, a new multilingual, unified and flexible representation of individual word senses. ...
doi:10.3115/v1/p15-1072
dblp:conf/acl/Camacho-Collados15
fatcat:2bt4vgwifzct7kys4zhhwj3sve
Nasari : Integrating explicit knowledge and corpus statistics for a multilingual representation of concepts and entities
2016
Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Then, we describe some applications of the vectors with their respective frameworks and experiments in Sections 6 (Semantic Similarity), 7 (Sense Clustering), 8 (Domain Labeling), and 9 (Word Sense Disambiguation ...
In this paper we put forward a novel multilingual vector representation, called Nasari, which not only enables accurate representation of word senses in different languages, but it also provides two main ...
Word Sense Disambiguation Word Sense Disambiguation is a task that can benefit significantly from the representation of word senses, mainly due to its sense-level application. ...
doi:10.1016/j.artint.2016.07.005
fatcat:qemh2zkstbbjlklzoeww2thzea
Analogy Between Concepts (Extended Abstract)
2020
Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper, we more particularly consider "relational proportions" of the form "object A has the same relationship with attribute a as object B with attribute b". ...
This showed, for the first time, the effectiveness of latent word representations in Word Sense Disambiguation. ...
tasks of Word Sense Disambiguation. ...
doi:10.24963/ijcai.2020/687
dblp:conf/ijcai/Pasini20
fatcat:thwkuli3wfehljpqpuuvd66jky
Semantic Representations of Word Senses and Concepts
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Indeed, the representation of individual word senses and concepts has recently gained in popularity with several experimental results showing that a considerable performance improvement can be achieved ...
Representations of word senses have the potential to overcome this inherent limitation. ...
A unified model for
word sense representation and disambiguation. In
Proceedings of EMNLP, pages 1025-1035, Doha,
Qatar.
[Chen et al.2015] Tao Chen, Ruifeng Xu, Yulan He, and
Xuan Wang. 2015. ...
arXiv:1608.00841v1
fatcat:sypz6ydpxzd7hime2dt3zftzx4
SenseDefs: a multilingual corpus of semantically annotated textual definitions
2018
Language Resources and Evaluation
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
a wide-coverage unified sense inventory. ...
information of equivalent definitions across different languages to provide context for disambiguation; then we refine the disambiguation output with a distributional approach based on semantic similarity ...
We provide an exhaustive background of all the resources used in this work (Sect. 2), as well as an extended step-wise description of our disambiguation pipeline (Sect. 3 ...
doi:10.1007/s10579-018-9421-3
fatcat:lfsmbwy4cjeedmvrkcd2g5d4k4
UNIBA: Combining Distributional Semantic Models and Sense Distribution for Multilingual All-Words Sense Disambiguation and Entity Linking
2015
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
This paper describes the participation of the UNIBA team in the Task 13 of SemEval-2015 about Multilingual All-Words Sense Disambiguation and Entity Linking. ...
We propose an algorithm able to disambiguate both word senses and named entities by combining the simple Lesk approach with information coming from both a distributional semantic model and usage frequency ...
This paper proposes a unified strategy for word sense and named entity disambiguation which leverages BabelNet, a multilingual resource that encompasses both encyclopedic and lexicographic knowledge ( ...
doi:10.18653/v1/s15-2061
dblp:conf/semeval/BasileCS15
fatcat:nxwlhk4tabgr3i3ryvnn3vhxga
A Large-Scale Multilingual Disambiguation of Glosses
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper we present a large-scale high-quality corpus of disambiguated glosses in multiple languages, comprising sense annotations of both concepts and named entities from a unified sense inventory ...
information of equivalent definitions across different languages to provide context for disambiguation, and then we combine it with a semantic similarity-based refinement. ...
Instead, in this paper we propose an automatic disambiguation approach which leverages multilinguality and cross-resource information along with a state-of-the-art multilingual Word Sense Disambiguation ...
arXiv:1608.06718v1
fatcat:m2va7zpvebhcbau75cza4o23gy
BabelNet and Friends: A manifesto for multilingual semantic processing
2013
Intelligenza Artificiale
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
In this paper I present a manifesto for the multilingual semantic processing of text. ...
In the last part of the paper I outline a likely future for multilingual semantic processing focusing on the current directions and successes and highlighting on the major obstacles that make this task ...
, since the disambiguation is to be performed with multilingual sense tags. ...
doi:10.3233/ia-130057
fatcat:hs4h4rledrdilnoz2yaslxvprq
Knowledge Base Unification via Sense Embeddings and Disambiguation
2015
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2018; you can also visit the original URL.
The file type is application/pdf.
KB-UNIFY consists of three main steps: (1) disambiguation of relation argument pairs via a sensebased vector representation and a large unified sense inventory; (2) ranking of semantic relations according ...
We present KB-UNIFY, a novel approach for integrating the output of different Open Information Extraction systems into a single unified and fully disambiguated knowledge repository. ...
BABELFY 2 is a joint state-of-the-art approach to multilingual Entity Linking and Word Sense Disambiguation. ...
doi:10.18653/v1/d15-1084
dblp:conf/emnlp/BoviAN15
fatcat:algllldpjfcvllbkgjhypz3kvi
A Survey on Lexical Ambiguity Detection and Word Sense Disambiguation
[article]
2024
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2024; you can also visit the original URL.
The file type is application/pdf.
The paper introduces cutting-edge methodologies like word sense extension (WSE) and neuromyotonic approaches, enhancing disambiguation accuracy by predicting new word senses. ...
Focusing extensively on Word Sense Disambiguation (WSD), it outlines diverse approaches ranging from deep learning techniques to leveraging lexical resources and knowledge graphs like WordNet. ...
on unified sense representations and knowledge transfer between languages. ...
arXiv:2403.16129v1
fatcat:2kb73etdhzaqtcwtk5qb5tlc5q
A Short Survey on Sense-Annotated Corpora
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Large sense-annotated datasets are increasingly necessary for training deep supervised systems in Word Sense Disambiguation. ...
Furthermore, we provide the reader with general statistics of each dataset and an analysis of their specific features. ...
Acknowledgments The authors would like to thank Claudio Delli Bovi and Alessandro Raganato for interesting discussions and their input with some of the datasets. ...
arXiv:1802.04744v4
fatcat:q47h6c2ehvetjofeoxa67omhgy
From Word To Sense Embeddings: A Survey on Vector Representations of Meaning
2018
The Journal of Artificial Intelligence Research
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
We start from the theoretical background behind word vector space models and highlight one of their major limitations: the meaning conflation deficiency, which arises from representing a word with all ...
Then, we explain how this deficiency can be addressed through a transition from the word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous ...
Word Sense Disambiguation Word Sense Disambiguation (WSD) is a task which is closely related to the meaning conflation deficiency. ...
doi:10.1613/jair.1.11259
fatcat:e6bjteqkdjdjjf3x7g56vcbjha
« Previous
Showing results 1 — 15 out of 1,584 results