Filters








8,236 Hits in 2.6 sec

Exploring multilingual semantic role labeling

Baoli Li, Martin Emms, Saturnino Luz, Carl Vogel
2009 Proceedings of the Thirteenth Conference on Computational Natural Language Learning Shared Task - CoNLL '09   unpublished
This paper describes the multilingual semantic role labeling system of Computational Linguistics Group, Trinity College Dublin, for the CoNLL-2009 SRLonly closed shared task.  ...  The system obtained labeled F1 69.26 averaging over seven languages (Catalan, Chinese, Czech, English, German, Japanese, and Spanish), which ranks the system fourth among the seven systems participating  ...  Word semantic dependencies derived by semantic role labeling are assumed to facilitate automated interpretation of natural language texts.  ... 
doi:10.3115/1596409.1596422 fatcat:xzc4fz44bfdbrltsllgxsqedwa

Syntax-aware Multilingual Semantic Role Labeling [article]

Shexia He, Zuchao Li, Hai Zhao
2019 arXiv   pre-print
Recently, semantic role labeling (SRL) has earned a series of success with even higher performance improvements, which can be mainly attributed to syntactic integration and enhanced word representation  ...  Besides, we pose a discussion on the syntactic role among different languages and verify the effectiveness of deep enhanced representation for multilingual SRL.  ...  Introduction Semantic role labeling (SRL) aims to derive the meaning representation such as an instantiated predicate-argument structure for a sentence.  ... 
arXiv:1909.00310v3 fatcat:vp7sbvg5qrcr5ifpayrkw64wbm

MASALA: Modelling and Analysing the Semantics of Adpositions in Linguistic Annotation of Hindi [article]

Aryaman Arora, Nitin Venkateswaran, Nathan Schneider
2022 arXiv   pre-print
We look towards upstream applications in semantic role labelling and extension to related languages such as Gujarati.  ...  We used the multilingual SNACS annotation scheme, which has been applied to a variety of typologically diverse languages.  ...  Acknowledgements We thank members of the CARMLS group (particularly Maitrey Mehta, Jena Hwang, and Vivek Srikumar) for stimulating discussions on case and adposition semantics, students in NERT, and the  ... 
arXiv:2205.03955v1 fatcat:dvvyftkperaqnhur34yvgdn5ea

Syntax-aware Multilingual Semantic Role Labeling

Shexia He, Zuchao Li, Hai Zhao
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Recently, semantic role labeling (SRL) has earned a series of success with even higher performance improvements, which can be mainly attributed to syntactic integration and enhanced word representation  ...  Besides, we pose a discussion on the syntactic role among different languages and verify the effectiveness of deep enhanced representation for multilingual SRL.  ...  Introduction Semantic role labeling (SRL) aims to derive the meaning representation such as an instantiated predicate-argument structure for a sentence.  ... 
doi:10.18653/v1/d19-1538 dblp:conf/emnlp/HeLZ19 fatcat:eyhqjiks6jeudf3ttojdevnz6i

A Bayesian Model of Multilingual Unsupervised Semantic Role Induction [article]

Nikhil Garg, James Henderson
2016 arXiv   pre-print
We propose a Bayesian model of unsupervised semantic role induction in multiple languages, and use it to explore the usefulness of parallel corpora for this task.  ...  find that the biggest impact of adding a parallel corpus to training is actually the increase in mono-lingual data, with the alignments to another language resulting in small improvements, even with labeled  ...  Labeled Data in Monolingual Model We explored the improvement in the monolingual model in a semi-supervised setting.  ... 
arXiv:1603.01514v1 fatcat:yaaf6c7tffhyvg4zq4mbpdvcii

Polyglot Semantic Role Labeling [article]

Phoebe Mulcaire, Swabha Swayamdipta, Noah Smith
2018 arXiv   pre-print
We experiment with a new approach where we combine resources from a pair of languages in the CoNLL 2009 shared task to build a polyglot semantic role labeler.  ...  Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages.  ...  Inspired by this, we apply the idea of training one model on multiple languages-which we call polyglot trainingto PropBank-style semantic role labeling (SRL).  ... 
arXiv:1805.11598v1 fatcat:6umi2cq7i5f6nma4ttxqinows4

Polyglot Semantic Role Labeling

Phoebe Mulcaire, Swabha Swayamdipta, Noah A. Smith
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)  
., 2009) to build a polyglot semantic role labeler.  ...  Previous approaches to multilingual semantic dependency parsing treat languages independently, without exploiting the similarities between semantic structures across languages.  ...  Inspired by this, we apply the idea of training one model on multiple languages-which we call polyglot trainingto PropBank-style semantic role labeling (SRL).  ... 
doi:10.18653/v1/p18-2106 dblp:conf/acl/MulcaireSS18 fatcat:rbdnpaowu5fpfk4l2fzzje353a

BERTje: A Dutch BERT Model [article]

Wietse de Vries, Andreas van Cranenburgh, Arianna Bisazza, Tommaso Caselli, Gertjan van Noord, Malvina Nissim
2019 arXiv   pre-print
BERTje consistently outperforms the equally-sized multilingual BERT model on downstream NLP tasks (part-of-speech tagging, named-entity recognition, semantic role labeling, and sentiment analysis).  ...  Compared to the multilingual BERT model, which includes Dutch but is only based on Wikipedia text, BERTje is based on a large and diverse dataset of 2.4 billion tokens.  ...  Named-Entity Recognition Semantic Roles and Spatio-Temporal Relations The results in Table 3 show that BERTje outperforms multilingual BERT for the semantic role labeling (SRL) and spatio-temporal  ... 
arXiv:1912.09582v1 fatcat:k6w2duacjrecbkvpehqwolgyda

Challenges for the multilingual Web of Data

Jorge Gracia, Elena Montiel-Ponsoda, Philipp Cimiano, Asunción Gómez-Pérez, Paul Buitelaar, John McCrae
2012 Journal of Web Semantics  
In this article we present this vision of a multilingual Web of Data.  ...  and vocabularies in different languages, ii) mappings between data with labels in different languages, and iii) services to dynamically access and traverse Linked Data across different languages.  ...  Some first steps to be explored towards the realization of this goal are the use of cross-lingual semantic measures and the exploitation of multilingual background knowledge sources.  ... 
doi:10.1016/j.websem.2011.09.001 fatcat:haagemrzjbfrze53iu5xj4xkpq

CLAR: A Cross-Lingual Argument Regularizer for Semantic Role Labeling [article]

Ishan Jindal, Yunyao Li, Siddhartha Brahma, Huaiyu Zhu
2020 arXiv   pre-print
Semantic role labeling (SRL) identifies predicate-argument structure(s) in a given sentence.  ...  Meanwhile, despite the dissimilarity in argument annotations between languages, certain argument labels do share common semantic meaning across languages (e.g. adjuncts have more or less similar semantic  ...  Semantic Role Labeler Our role labeler consists of Multi-Layer Perceptron (MLP) layers with highway connections (Srivastava et al., 2015) .  ... 
arXiv:2011.04732v1 fatcat:hrop2bxfhjephm5ojb6zfudphq

Cross-lingual Semantic Role Labeling with Model Transfer [article]

Hao Fei and Meishan Zhang and Fei Li and Donghong Ji
2020 arXiv   pre-print
Prior studies show that cross-lingual semantic role labeling (SRL) can be achieved by model transfer under the help of universal features.  ...  We study both the bilingual transfer and multi-source transfer, under gold or machine-generated syntactic inputs, pre-trained high-order abstract features, and contextualized multilingual word representations  ...  Semantic Role Labeling A line of research efforts has been made for semantic role labeling.  ... 
arXiv:2008.10284v1 fatcat:v3zwcyw22faz3ifofq5mrh2gpu

Polyglot Contextual Representations Improve Crosslingual Transfer [article]

Phoebe Mulcaire, Jungo Kasai, Noah A. Smith
2019 arXiv   pre-print
We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons  ...  Our method combines the advantages of contextual word representations with those of multilingual representation learning.  ...  We explore crosslingual transfer between highly dissimilar languages (English→Chinese and English→Arabic) for three core tasks: Universal Dependency (UD) parsing, semantic role labeling (SRL), and named  ... 
arXiv:1902.09697v2 fatcat:pbn2muy3qbecjhkb3w7hj5ysea

Collaborative Development of Multilingual Thesauri with VocBench (System Description and Demonstrator) [chapter]

Armando Stellato, Sachit Rajbhandari, Andrea Turbati, Manuel Fiorelli, Caterina Caracciolo, Tiziano Lorenzetti, Johannes Keizer, Maria Teresa Pazienza
2015 Lecture Notes in Computer Science  
Dedicated user roles provide a clean separation of competences, addressing different specificities ranging from management aspects to vertical competences on content editing, such as conceptualization  ...  Concepts in the tree may be shown through their labels in all of the selected languages for visualization. An option toggles between a view of preferred labels only, and all labels.  ...  Role-Based Access Control.  ... 
doi:10.1007/978-3-319-25639-9_29 fatcat:gwo7fdpvevevzmmltbnzazri6i

Polyglot Contextual Representations Improve Crosslingual Transfer

Phoebe Mulcaire, Jungo Kasai, Noah A. Smith
2019 Proceedings of the 2019 Conference of the North  
We produce language models from dissimilar language pairs (English/Arabic and English/Chinese) and use them in dependency parsing, semantic role labeling, and named entity recognition, with comparisons  ...  Our method combines the advantages of contextual word representations with those of multilingual representation learning.  ...  A.3 Semantic Role Labeling For SRL, we again follow the hyperparameters given in AllenNLP (Table 5 ).  ... 
doi:10.18653/v1/n19-1392 dblp:conf/naacl/MulcaireKS19 fatcat:hb3yqssp7rgcxjnbnxpubbdlsy

X-SRL: A Parallel Cross-Lingual Semantic Role Labeling Dataset [article]

Angel Daza, Anette Frank
2020 arXiv   pre-print
In this work, we propose a method to automatically construct an SRL corpus that is parallel in four languages: English, French, German, Spanish, with unified predicate and role annotations that are fully  ...  In fact, existing multilingual SRL datasets contain disparate annotation styles or come from different domains, hampering generalization in multilingual learning.  ...  Introduction Semantic Role Labeling (SRL) is the task of extracting semantic predicate-argument structures from sentences.  ... 
arXiv:2010.01998v1 fatcat:qcxrjwnwbrhyvkihvwnjxgobly
« Previous Showing results 1 — 15 out of 8,236 results