Sense representations for Portuguese: experiments with sense embeddings and deep neural language models
Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the traditional approaches for generating word embeddings have a strict d...
Saved in:
| Published in: | Language resources and evaluation Vol. 55; no. 4; pp. 901 - 924 |
|---|---|
| Main Authors: | , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Dordrecht
Springer Netherlands
01-12-2021
Springer Nature B.V |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the traditional approaches for generating word embeddings have a strict drawback: they produce a single vector representation for a given word ignoring the fact that ambiguous words can assume different meanings. In this paper, we explore unsupervised sense representations which, different from traditional word embeddings, are able to induce different senses of a word by analyzing its contextual semantics in a text. The unsupervised sense representations investigated in this paper are: sense embeddings and deep neural language models. We present the first experiments carried out for generating sense embeddings for Portuguese. Our experiments show that the sense embedding model (Sense2vec) outperformed traditional word embeddings in syntactic and semantic analogies task, proving that the language resource generated here can improve the performance of NLP tasks in Portuguese. We also evaluated the performance of pre-trained deep neural language models (ELMo and BERT) in two transfer learning approaches: feature based and fine-tuning, in the semantic textual similarity task. Our experiments indicate that the fine tuned Multilingual and Portuguese BERT language models were able to achieve better accuracy than the ELMo model and baselines. |
|---|---|
| AbstractList | Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural language processing tasks. Although very useful in many applications, the traditional approaches for generating word embeddings have a strict drawback: they produce a single vector representation for a given word ignoring the fact that ambiguous words can assume different meanings. In this paper, we explore unsupervised sense representations which, different from traditional word embeddings, are able to induce different senses of a word by analyzing its contextual semantics in a text. The unsupervised sense representations investigated in this paper are: sense embeddings and deep neural language models. We present the first experiments carried out for generating sense embeddings for Portuguese. Our experiments show that the sense embedding model (Sense2vec) outperformed traditional word embeddings in syntactic and semantic analogies task, proving that the language resource generated here can improve the performance of NLP tasks in Portuguese. We also evaluated the performance of pre-trained deep neural language models (ELMo and BERT) in two transfer learning approaches: feature based and fine-tuning, in the semantic textual similarity task. Our experiments indicate that the fine tuned Multilingual and Portuguese BERT language models were able to achieve better accuracy than the ELMo model and baselines. |
| Author | Rodrigues da Silva, Jéssica Caseli, Helena de M. |
| Author_xml | – sequence: 1 givenname: Jéssica orcidid: 0000-0001-6275-6039 surname: Rodrigues da Silva fullname: Rodrigues da Silva, Jéssica email: jsc.rodrigues@gmail.com organization: Federal University of São Carlos (UFSCar) – sequence: 2 givenname: Helena de M. orcidid: 0000-0003-3996-8599 surname: Caseli fullname: Caseli, Helena de M. organization: Federal University of São Carlos (UFSCar) |
| BookMark | eNp9kMtKxDAUhoOM4MzoC7gKuK7m0iatOxm8wYCCCu5Cmp7WDp2kJi3q25uZiu5cnQvffy7_As2ss4DQKSXnlBB5ESjJZJEQRhJSZCxL6AGa00ymsUXz2W9OXo_QIoQNISlLZT5HzRPYANhD7yGAHfTQOhtw7Tx-dH4YmzG2LzF89uDbbQQC_miHNxz2MtiWUFWtbQLWtsIVQI8tjF53uNO2GXUDeOsq6MIxOqx1F-DkJy7Ry8318-ouWT_c3q-u1onhtBgSVumCVqVgHIQ0kDJTFrTIhRCyBkklrzkxZZlzE2vOcpIzoXUmODO6TjPgS3Q2ze29e4-3D2rjRm_jSsWyHS5ZKiLFJsp4F4KHWvXxO-2_FCVqZ6iaDFXRMbU3VNEo4pMoRNg24P9G_6P6Bs3xfEk |
| CitedBy_id | crossref_primary_10_1007_s11227_023_05647_9 |
| Cites_doi | 10.18653/v1/K16-1006 10.21437/Interspeech.2014-564 10.1109/IJCNN.2013.6707118 10.1609/aaai.v29i1.9496 10.3115/v1/P15-1072 10.1162/tacl_a_00051 10.3115/v1/P15-1173 10.1609/aaai.v25i1.7917 10.1007/978-3-319-41552-9_27 10.3115/v1/D14-1162 10.1145/361219.361220 10.1145/371920.372094 10.1109/CVPR.2015.7298994 10.18653/v1/N18-1202 10.18653/v1/W16-1620 10.3115/v1/N15-1142 10.3115/v1/P15-1010 10.1109/ICCV.2015.11 10.3115/v1/D14-1110 10.21437/Interspeech.2013-596 10.18653/v1/W19-4302 10.18653/v1/D19-1410 10.1613/jair.1.11259 10.3115/v1/D14-1113 |
| ContentType | Journal Article |
| Copyright | The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2021 The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2021. |
| Copyright_xml | – notice: The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2021 – notice: The Author(s), under exclusive licence to Springer Nature B.V. part of Springer Nature 2021. |
| DBID | AAYXX CITATION 3V. 7SC 7T9 7XB 8AL 8FD 8FE 8FG 8FK 8G5 ABUWG AFKRA AIMQZ ALSLI ARAPS AVQMV AZQEC BENPR BGLVJ CCPQU CPGLG CRLPW DWQXO GB0 GNUQQ GUQSH HCIFZ JQ2 K50 K7- L7M LIQON L~C L~D M0N M1D M2O MBDVC P5Z P62 PQEST PQQKQ PQUKI PRINS Q9U |
| DOI | 10.1007/s10579-020-09525-1 |
| DatabaseName | CrossRef ProQuest Central (Corporate) Computer and Information Systems Abstracts Linguistics and Language Behavior Abstracts (LLBA) ProQuest Central (purchase pre-March 2016) Computing Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) Research Library (Alumni Edition) ProQuest Central (Alumni) ProQuest Central UK/Ireland ProQuest One Literature Social Science Premium Collection (Proquest) (PQ_SDU_P3) Advanced Technologies & Aerospace Collection Arts Premium Collection ProQuest Central Essentials ProQuest Databases Technology Collection ProQuest One Community College Linguistics Collection Linguistics Database ProQuest Central DELNET Social Sciences & Humanities Collection ProQuest Central Student Research Library Prep SciTech Premium Collection (Proquest) (PQ_SDU_P3) ProQuest Computer Science Collection Art, Design and Architecture Collection Computer Science Database Advanced Technologies Database with Aerospace One Literature (ProQuest) Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Computing Database Arts & Humanities Database ProQuest research library Research Library (Corporate) Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic |
| DatabaseTitle | CrossRef ProQuest DELNET Social Sciences and Humanities Collection Research Library Prep Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College Research Library (Alumni Edition) ProQuest Central China ProQuest Central Linguistics Collection Arts Premium Collection ProQuest Central Korea ProQuest Research Library ProQuest Art, Design and Architecture Collection Advanced Technologies Database with Aerospace Advanced Technologies & Aerospace Collection Social Science Premium Collection ProQuest Computing ProQuest One Literature - U.S. Customers Only ProQuest Central Basic ProQuest One Literature ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition Linguistics and Language Behavior Abstracts (LLBA) ProQuest Technology Collection ProQuest SciTech Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition Linguistics Database Arts & Humanities Full Text ProQuest One Academic ProQuest Central (Alumni) |
| DatabaseTitleList | ProQuest DELNET Social Sciences and Humanities Collection |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Library & Information Science Computer Science |
| EISSN | 1574-0218 |
| EndPage | 924 |
| ExternalDocumentID | 10_1007_s10579_020_09525_1 |
| GroupedDBID | -51 -5C -5G -BR -DZ -EM -Y2 -~C .4H .4S .86 .DC 06D 07C 0R~ 0VY 199 2.D 203 29L 2J2 2JN 2JY 2KG 2LR 2P1 2VQ 2~H 30V 3EH 3V. 4.4 406 408 409 40E 5GY 5VS 67Z 6NX 78A 8FE 8FG 8G5 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AABYN AAFGU AAGAY AAGJQ AAHNG AAIAL AAJKR AANTL AANZL AAPBV AARHV AARTL AATNV AATVU AAUYE AAWCG AAXYU AAYFA AAYIU AAYOK AAYQN AAYTO ABBBX ABBHK ABBXA ABDZT ABECU ABECW ABFGW ABFTV ABHLI ABHQN ABJNI ABJOX ABKAS ABKCH ABKTR ABLJU ABMNI ABMQK ABNWP ABPTK ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACBMV ACBRV ACBXY ACBYP ACGFO ACGFS ACHSB ACHXU ACIGE ACIPQ ACKNC ACMDZ ACMLO ACNXV ACOKC ACOMO ACREN ACTTH ACVWB ACVYN ACWMK ADHIR ADINQ ADKNI ADKPE ADMDM ADOXG ADPTO ADRFC ADSWE ADTPH ADULT ADURQ ADYFF ADYOE ADZKW AEBTG AEEQQ AEFTE AEGAL AEGNC AEJHL AEJRE AEKMD AENEX AEOHA AEPYU AESKC AESTI AETLH AEUPB AEVLU AEVTX AEXYK AFEXP AFFNX AFGCZ AFKRA AFLOW AFNRJ AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGBP AGHSJ AGJBK AGMZJ AGQMX AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIIXL AILAN AIMQZ AIMYW AITGF AJBLW AJDOV AJRNO AJZVZ AKQUC ALMA_UNASSIGNED_HOLDINGS ALSLI ALWAN AMKLP AMTXH AMXSW AMYLF AOCGG ARAPS ARCSS ARMRJ AVQMV AXYYD AYQZM AZFZN AZQEC AZRUE B-. BA0 BDATZ BENPR BGLVJ BGNMA BHNFS BPHCQ CAG CCPQU COF CPGLG CRLPW CS3 CSCUP DDRTE DL5 DNIVK DPUIP DWQXO EBLON EBS EDO EHI EIOEI EJD ESBYG FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRRFC FSGXE FWDCC GB0 GGCAI GGRSB GJIRD GNUQQ GNWQR GPZZG GQ6 GQ7 GQ8 GUQSH GXS HCIFZ HF~ HG5 HG6 HLICF HMHOC HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IHE IJ- IKXTQ ITM IWAJR IXC IZIGR IZQ I~X I~Z J-C J0Z JAAYA JAB JBMMH JBSCW JCJTX JENOY JHFFW JKQEH JLEZI JLXEF JPL JSODD JST JZLTJ K50 K6V K7- KDC KOV LIQON LLZTM M0N M1D M2O M4Y MA- MQGED N2Q NB0 NDZJH NF0 NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM P-O P19 P62 P9Q PF- PQQKQ PROAC PT4 Q2X QF4 QN3 QN7 QOS R89 R9I RHV RIG ROL RPX RSV S16 S1Z S26 S27 S28 S3B SA0 SAP SCLPG SDA SDH SDM SHS SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TN5 TSG TSK TSV TUC TUS U2A UG4 UNUBA UOJIU UTJUX UZXMN VC2 VFIZW VQA W23 W48 WK8 YLTOR Z45 Z7X Z83 Z88 Z8R Z8W Z92 ZMTXR ZWUKE ~EX AACDK AAEOY AAHCP AAJBT AASML AAYXX AAYZH ABAKF ABXSQ ACAOD ACDTI ACZOJ ADACV AEFQL AEMSY AFBBN AGQEE AGRTI AGZLP AHEXP AIGIU CITATION H13 IPSME 7SC 7T9 7XB 8AL 8FD 8FK JQ2 L7M L~C L~D MBDVC PQEST PQUKI PRINS Q9U |
| ID | FETCH-LOGICAL-c319t-2da91db623e67ce42cb91986667fe7173f30cbb83c7fe3280826aa5632caf45e3 |
| IEDL.DBID | AEJHL |
| ISSN | 1574-020X |
| IngestDate | Mon Nov 04 10:51:57 EST 2024 Fri Nov 22 00:28:03 EST 2024 Sat Dec 16 12:09:23 EST 2023 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | Deep neural language models Sense embeddings Portuguese Word sense disambiguation Word embeddings |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c319t-2da91db623e67ce42cb91986667fe7173f30cbb83c7fe3280826aa5632caf45e3 |
| ORCID | 0000-0001-6275-6039 0000-0003-3996-8599 |
| PQID | 2580827246 |
| PQPubID | 28740 |
| PageCount | 24 |
| ParticipantIDs | proquest_journals_2580827246 crossref_primary_10_1007_s10579_020_09525_1 springer_journals_10_1007_s10579_020_09525_1 |
| PublicationCentury | 2000 |
| PublicationDate | 2021-12-01 |
| PublicationDateYYYYMMDD | 2021-12-01 |
| PublicationDate_xml | – month: 12 year: 2021 text: 2021-12-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Dordrecht |
| PublicationPlace_xml | – name: Dordrecht – name: Dordrect |
| PublicationTitle | Language resources and evaluation |
| PublicationTitleAbbrev | Lang Resources & Evaluation |
| PublicationYear | 2021 |
| Publisher | Springer Netherlands Springer Nature B.V |
| Publisher_xml | – name: Springer Netherlands – name: Springer Nature B.V |
| References | Finkelstein, L., Gabrilovich, E., Matias, Y., Rivlin, E., Solan, Z., Wolfman, G., & Ruppin, E. (2001). Placing search in context: The concept revisited. In: Proceedings of the 10th international conference on World Wide Web, pp 406–414. Cardoso, P. C., Maziero, E. G., Jorge, M. L., Seno, E. M., Di Felippo, A., Rino, L. H., et al. (2011). Cstnews-A discourse-annotated corpus for single and multi-document summarization of news texts in Brazilian Portuguese. In Proceedings of the 3rd RST Brazilian meeting (pp. 88–105). Mesnil, G., He, X., Deng, L., & Bengio, Y. (2013). Investigation of recurrent-neural-network architectures and learning methods for spoken language understanding. In Interspeech (pp. 3771–3775). Rodrigues, J., Branco, A., Neale, S., & Silva, J. (2016). Lx-dsemvectors: Distributional semantics models for Portuguese. In International conference on computational processing of the Portuguese language, Springer (pp. 259–270). Branco, A., Mendes, A., Pereira, S., Henriques, P., Pellegrini, T., Meinedo, H., et al. (2012). The Portuguese language in the digital age. White Paper Series, Berlin, http://metanet4u.eu/wbooks/portuguese.pdf. Wagner Filho, J. A., Wilkens, R., Idiart, M., & Villavicencio, A. (2018). The BrWaC corpus: A new open resource for Brazilian Portuguese. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). Liu, W., Mei, T., Zhang, Y., Che, C., & Luo, J. (2015). Multi-task deep visual-semantic embedding for video thumbnail selection. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3707–3715). Camacho-ColladosJPilehvarMTFrom word to sense embeddings: A survey on vector representations of meaningJournal of Artificial Intelligence Research20186374378810.1613/jair.1.11259 Peters, M., Ruder, S., & Smith, N. A. (2019). To tune or not to tune? adapting pretrained representations to diverse tasks. arXiv preprint arXiv:190305987. Iacobacci, I., Pilehvar, MT., & Navigli, R. (2015). Sensembed: Learning sense embeddings for word and relational similarity. In: 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), pp 95–105. Camacho-Collados, J., Pilehvar, M. T., & Navigli, R. (2015). A unified multilingual semantic representation of concepts. In Proceedings of the 53rd annual meeting of the association for computational linguistics and the 7th international joint conference on natural language processing (Vol. 1: Long Papers, pp. 741–751). Chen, X., Liu, Z., & Sun, M. (2014). A unified model for word sense representation and disambiguation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1025–1035). Chelba, C., Mikolov, T., Schuster, M., Ge, Q., Brants, T., Koehn, P., & Robinson, T. (2013). One billion word benchmark for measuring progress in statistical language modeling. arXiv preprint arXiv:13123005. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, Ł., & Polosukhin, I. (2017). Attention is all you need. In Advances in neural information processing systems (pp. 5998–6008). Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., et al. (2019a). Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:190711692. Pina, L. N., & Johansson, R. (2014). A simple and efficient method to generate word sense representations. arXiv preprint arXiv:14126045. Bordes, A., Weston, J., Collobert, R., & Bengio, Y. (2011). Learning structured embeddings of knowledge bases. In Twenty-fifth AAAI conference on artificial intelligence. Reimers, N., & Gurevych, I. (2019). Sentence-bert: Sentence embeddings using siamese bert-networks. arXiv preprint arXiv:190810084. Rodrigues, J., & Branco, A. (2018). Finely tuned, 2 billion token based word embeddings for portuguese. In Proceedings of the eleventh international conference on language resources and evaluation (LREC 2018). BojanowskiPGraveEJoulinAMikolovTEnriching word vectors with subword informationTransactions of the Association for Computational Linguistics2017513514610.1162/tacl_a_00051 Takala, P. (2016). Word embeddings for morphologically rich languages. In ESANN. Peters, M. E., Neumann, M., Iyyer, M., Gardner, M., Clark, C., Lee, K., & Zettlemoyer, L. (2018). Deep contextualized word representations. arXiv preprint arXiv:180205365. LiWMcCallumASemi-supervised sequence modeling with syntactic topic modelsAAAI20055813818 Rothe, S., & Schütze, H. (2015). Autoextend: Extending word embeddings to embeddings for synsets and lexemes. arXiv preprint arXiv:150701127. SaltonGWongAYangCSA vector space model for automatic indexingCommunications of the ACM1975181161362010.1145/361219.361220 BruckschenMMunizFSouzaJFuchsJInfanteKMunizMGonçalvesPVieiraRAluısioSAnotaçao lingüıstica em xml do corpus pln-br2008ICMC-USPSérie de relatórios do NILC Pelevina, M., Arefyev, N., Biemann, C., & Panchenko, A. (2017). Making sense of word embeddings. arXiv preprint arXiv:170803390. Radford, A., Narasimhan, K., Salimans, T., & Sutskever, I. (2018). Improving language understanding by generative pre-training. https://www.s3-us-west-2amazonawscom/openai-assets/researchcovers/languageunsupervised/languageunderstandingpaperpdf. Huang, EH., Socher, R., Manning, CD., & Ng, AY. (2012). Improving word representations via global context and multiple word prototypes. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers-Volume 1, Association for Computational Linguistics, pp 873–882. Reisinger, J., & Mooney, R. J. (2010). Multi-prototype vector-space models of word meaning. In Human language technologies: The 2010 annual conference of the North American chapter of the association for computational linguistics, Association for Computational Linguistics (pp. 109–117). Devlin, J., Chang, MW., Lee, K., & Toutanova, K. (2018). Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:181004805. McCann, B., Bradbury, J., Xiong, C., & Socher, R. (2017). Learned in translation: Contextualized word vectors. In Advances in neural information processing systems (pp. 6294–6305). Mikolov, T., Le, Q. V., & Sutskever, I. (2013b). Exploiting similarities among languages for machine translation. arXiv preprint arXiv:13094168. Mikolov, T., Chen, K., Corrado, G., & Dean, J. (2013a). Efficient estimation of word representations in vector space. arXiv preprint arXiv:13013781. Melamud, O., Goldberger, J., & Dagan, I. (2016). context2vec: Learning generic context embedding with bidirectional LSTM. In Proceedings of The 20th SIGNLL conference on computational natural language learning (pp. 51–61). Fonseca, ER., & Rosa, JLG. (2013). A two-step convolutional neural network approach for semantic role labeling. In: The 2013 International Joint Conference on Neural Networks (IJCNN), IEEE, pp 1–7. Lample, G., & Conneau, A. (2019). Cross-lingual language model pretraining. arXiv preprint arXiv:190107291. Aluísio, R. M., Pinheiro, G. M., Finger, M., Graças, M., Nunes, V., & Tagnin, S. E. (2003). The Lacio-Web project: Overview and issues in Brazilian Portuguese corpora creation. In Proceedings of corpus linguistics, Citeseer. Ling, W., Dyer, C., Black, A. W., & Trancoso, I. (2015). Two/too simple adaptations of word2vec for syntax problems. In Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: human language technologies (pp. 1299–1304). Trask, A., Michalak, P., & Liu, J. (2015). sense2vec-a fast and accurate method for word sense disambiguation in neural word embeddings. arXiv preprint arXiv:151106388. Zhu, Y., Kiros, R., Zemel, R., Salakhutdinov, R., Urtasun, R., Torralba, A., & Fidler, S. (2015). Aligning books and movies: Towards story-like visual explanations by watching movies and reading books. In Proceedings of the IEEE international conference on computer vision (pp. 19–27). SchützeHAutomatic word sense discriminationComputational Linguistics199824197123 Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A. Y., & Potts, C. (2013). Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 conference on empirical methods in natural language processing (pp. 1631–1642). Nóbrega, F. A. A. (2013). Desambiguação lexical de sentidos para o português por meio de uma abordagem multilíngue mono e multidocumento. PhD thesis, Universidade de São Paulo. Pennington, J., Socher, R., & Manning, C. D. (2014). Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP) (pp. 1532–1543). Firth, J., & (1957). A synopsis of linguistic theory 1930–1955. In: Studies in Linguistic Analysis, Philological Society, Oxford, reprinted in Palmer, F., (Eds.). (1968). Selected Papers of J. Longman, Harlow: R. Firth. Wu, Z., & Giles, C L. (2015). Sense-aware semantic analysis: A multi-prototype word representation model using wikipedia. In Twenty-ninth AAAI conference on artificial intelligence. Hartmann, N., Fonseca, E., Shulby, C., Treviso, M., Rodrigues, J., & Aluisio, S. (2017). Portuguese word embeddings: Evaluating on word analogies and natural language tasks. arXiv preprint arXiv:170806025. Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., et al. (2019b). Roberta: A robustly optimized bert pretraining approach. arxiv 2019. arXiv preprint arXiv:190711692. HarrisZSDistributional structure. Word1954102–3146162 Neelakantan, A., Shankar, J., Passos, A., & McCallum, A. (2015). Efficient non-parametric estimation of multiple embeddings per word in vector space. arXiv preprint arXiv:150406654. P Bojanowski (9525_CR2) 2017; 5 9525_CR49 9525_CR46 9525_CR45 9525_CR48 9525_CR47 9525_CR42 9525_CR41 9525_CR40 9525_CR17 M Bruckschen (9525_CR5) 2008 9525_CR16 9525_CR19 9525_CR18 9525_CR13 9525_CR12 H Schütze (9525_CR44) 1998; 24 9525_CR14 ZS Harris (9525_CR15) 1954; 10 9525_CR11 9525_CR10 9525_CR51 9525_CR50 G Salton (9525_CR43) 1975; 18 9525_CR28 9525_CR27 9525_CR29 9525_CR24 9525_CR23 9525_CR26 9525_CR25 9525_CR22 9525_CR21 9525_CR39 W Li (9525_CR20) 2005; 5 9525_CR38 9525_CR35 9525_CR34 9525_CR37 9525_CR36 9525_CR31 9525_CR30 9525_CR3 9525_CR33 9525_CR4 9525_CR32 9525_CR1 J Camacho-Collados (9525_CR6) 2018; 63 9525_CR9 9525_CR7 9525_CR8 |
| References_xml | – ident: 9525_CR47 – ident: 9525_CR26 doi: 10.18653/v1/K16-1006 – ident: 9525_CR9 doi: 10.21437/Interspeech.2014-564 – ident: 9525_CR24 – ident: 9525_CR14 doi: 10.1109/IJCNN.2013.6707118 – ident: 9525_CR28 – ident: 9525_CR8 – ident: 9525_CR50 doi: 10.1609/aaai.v29i1.9496 – ident: 9525_CR4 – ident: 9525_CR7 doi: 10.3115/v1/P15-1072 – ident: 9525_CR11 – volume: 5 start-page: 135 year: 2017 ident: 9525_CR2 publication-title: Transactions of the Association for Computational Linguistics doi: 10.1162/tacl_a_00051 contributor: fullname: P Bojanowski – ident: 9525_CR42 doi: 10.3115/v1/P15-1173 – ident: 9525_CR3 doi: 10.1609/aaai.v25i1.7917 – ident: 9525_CR23 – ident: 9525_CR41 doi: 10.1007/978-3-319-41552-9_27 – ident: 9525_CR19 – ident: 9525_CR48 – ident: 9525_CR33 doi: 10.3115/v1/D14-1162 – ident: 9525_CR40 – volume: 18 start-page: 613 issue: 11 year: 1975 ident: 9525_CR43 publication-title: Communications of the ACM doi: 10.1145/361219.361220 contributor: fullname: G Salton – ident: 9525_CR12 doi: 10.1145/371920.372094 – volume: 5 start-page: 813 year: 2005 ident: 9525_CR20 publication-title: AAAI contributor: fullname: W Li – ident: 9525_CR37 – ident: 9525_CR16 – ident: 9525_CR22 doi: 10.1109/CVPR.2015.7298994 – ident: 9525_CR49 – ident: 9525_CR35 doi: 10.18653/v1/N18-1202 – volume-title: Anotaçao lingüıstica em xml do corpus pln-br year: 2008 ident: 9525_CR5 contributor: fullname: M Bruckschen – ident: 9525_CR45 – ident: 9525_CR32 doi: 10.18653/v1/W16-1620 – volume: 24 start-page: 97 issue: 1 year: 1998 ident: 9525_CR44 publication-title: Computational Linguistics contributor: fullname: H Schütze – ident: 9525_CR13 – ident: 9525_CR21 doi: 10.3115/v1/N15-1142 – ident: 9525_CR18 doi: 10.3115/v1/P15-1010 – ident: 9525_CR36 – ident: 9525_CR29 – ident: 9525_CR17 – ident: 9525_CR51 doi: 10.1109/ICCV.2015.11 – ident: 9525_CR10 doi: 10.3115/v1/D14-1110 – ident: 9525_CR25 – ident: 9525_CR46 – volume: 10 start-page: 146 issue: 2–3 year: 1954 ident: 9525_CR15 publication-title: Distributional structure. Word contributor: fullname: ZS Harris – ident: 9525_CR27 doi: 10.21437/Interspeech.2013-596 – ident: 9525_CR34 doi: 10.18653/v1/W19-4302 – ident: 9525_CR1 – ident: 9525_CR38 doi: 10.18653/v1/D19-1410 – ident: 9525_CR39 – volume: 63 start-page: 743 year: 2018 ident: 9525_CR6 publication-title: Journal of Artificial Intelligence Research doi: 10.1613/jair.1.11259 contributor: fullname: J Camacho-Collados – ident: 9525_CR30 doi: 10.3115/v1/D14-1113 – ident: 9525_CR31 |
| SSID | ssj0042478 |
| Score | 2.3170433 |
| Snippet | Sense representations have gone beyond word representations like Word2Vec, GloVe and FastText and achieved innovative performance on a wide range of natural... |
| SourceID | proquest crossref springer |
| SourceType | Aggregation Database Publisher |
| StartPage | 901 |
| SubjectTerms | Computational Linguistics Computer Science Experiments Language Language and Literature Language modeling Linguistics Natural language processing Original Paper Performance enhancement Performance evaluation Portuguese language Representations Semantic analysis Semantics Social Sciences Syntax Words (language) |
| Title | Sense representations for Portuguese: experiments with sense embeddings and deep neural language models |
| URI | https://link.springer.com/article/10.1007/s10579-020-09525-1 https://www.proquest.com/docview/2580827246 |
| Volume | 55 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR27TsMw0IJ2YaFQQBRa5AGxQFDjR2yzVbRVhRBLQWqnKA-nAyJUpP1_zq5NAMEAS6LIF-vku7Pv4btD6FwxoRIudSBzkCamwjRINaVBIZRICTwjbZvYTsXDTA5HpkwO_XBdlM_XPiJpN-pPuW5cqMBYO6AVEB6AydOEs4cDczcHo7vJvd-AGWF2Aw65YAZ-5nJlfp7l63lUK5nf4qL2uBm3_oXoHtp12iUebNhhH23pso1avnMDdoLcRj2XroAvsMtHMvTx4wdoMQXrVmNb8dJnJ5UVBkhsrp6uF4C9vsF1e4AKG4curuxv-iXVuY1p4aTMca71Epu6mYCZd49i24GnOkRP49Hj7SRwLRmCDGR1FZA8UWGegs6kI5FpRrJUhUqCDSQKbQL6Be1naSppBt-USFAwoiThESVZUjCu6RFqlK-lPkY4jzIwLgvFEsUYlZEES6ivJJeh9W2JDrr0hImXm8obcV1j2axxDGsc2zWOww7qetrFTgqrmHCDgCAs6qArT6x6-PfZTv4Gfop2iLnqYm-5dFFj9bbWPbRd5eszx5vmPZvPh---8t7x |
| link.rule.ids | 315,782,786,27933,27934,41073,42142,48344,48347,49649,49652,52153 |
| linkProvider | Springer Nature |
| linkToHtml | http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR1NT8Iw9EXhoBdR1IiC9mC86BLXdWvrjSgIEbmACbdlWztOTuLg__ta1qBGD3pZsvS1eel7r32v7wvgUjIuk1BoTyiUJib91Et1EHg5lzyl-I20bWI74eOZeOiZMjnM5cLYaHfnkrQn9adkt5BLz5g7qBbQ0EObp85kxJCX693h9LHvTmBGmT2B_ZAzAz-rkmV-XuXrhbTRMr85Ru1902_8D9N92Kv0S9JdM8QBbOmiCQ3Xu4FUotyETpWwQK5IlZFkKOTGD2E-QftWE1vz0uUnFSVBSGKCT1dzRF_fkU2DgJKYJ11S2mn6NdXKerVIUiiitF4QUzkTMXMPpMT24CmP4KXfm94PvKopg5ehtC49qhLpqxS1Jh3xTDOapdKXAq0gnmvj0s-D2yxNRZDhf0AFqhhRkoRRQLMkZ6EOjqFWvBX6BIiKMjQvc8kSyVggIoG20K0UofDt6xZvwbWjTLxY196IN1WWzR7HuMex3ePYb0HbES-u5LCMaWgQ4JRFLbhxxNoM_77a6d_AL2BnMH0exaPh-OkMdqkJfLExL22oLd9XugPbpVqdV4z6ASbF4S8 |
| linkToPdf | http://sdu.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3NS8MwFH_oBuLF6VScnzmIFy1b07RJvA3dmDpEmIK30jbpTtZht__fl6yxKnoQL4WS15Dm5SXvl_cFcCoZl0kotCcUShOTfuqlOgi8nEueUnxG2haxnfD7Z3E9MGlyPqL4rbe7M0kuYxpMlqZi3p2pvPsp8C3k0jPQB1UEGnqIf5oMkQyu9GZ_cDsau92YUWZ3Yz_kzNA_V4EzP_fy9XCqNc5vRlJ79gxb_x_1JmxUeifpLxfKFqzoog0tV9OBVCLehqMqkIGckSpSyXDOtW_DdIK4VxObC9PFLRUlQUpinFIXU_wVfUnqwgElMVe9pLSf6ZdUK2vtIkmhiNJ6RkxGTRyZuzgltjZPuQNPw8Hj1cirijV4GUrx3KMqkb5KUZvSEc80o1kqfSkQHfFcG1N_HvSyNBVBhu8BFah6REkSRgHNkpyFOtiFRvFa6D0gKsoQduaSJZKxQEQCMVJPilD49taLd-DccSmeLXNyxHX2ZTPHMc5xbOc49jtw6BgZV_JZxjQ0A-CURR24cIyrm3_vbf9v5Cew9nA9jMc393cHsE6NP4x1hTmExvxtoY9gtVSL42rNvgNmGuny |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Sense+representations+for+Portuguese%3A+experiments+with+sense+embeddings+and+deep+neural+language+models&rft.jtitle=Language+resources+and+evaluation&rft.au=Rodrigues+da+Silva%2C+J%C3%A9ssica&rft.au=Caseli%2C+Helena+de+M.&rft.date=2021-12-01&rft.pub=Springer+Netherlands&rft.issn=1574-020X&rft.eissn=1574-0218&rft.volume=55&rft.issue=4&rft.spage=901&rft.epage=924&rft_id=info:doi/10.1007%2Fs10579-020-09525-1&rft.externalDocID=10_1007_s10579_020_09525_1 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1574-020X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1574-020X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1574-020X&client=summon |