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.
Filters
A review on Relation Extraction with an eye on Portuguese
2013
Journal of the Brazilian Computer Society
Preserved Fulltext
We present a review of the state-of-the-art for Relation Extraction in free texts, addressing the progress and difficulties of the area, and situating Portuguese in that frame. ...
We also give special attention to the literature for Portuguese tools, which need further progress. ...
We thank the Brazilian funding agency FAPERGS/CAPES for the scholarship granted. ...
doi:10.1007/s13173-013-0116-8
fatcat:rxrt7yieija3hndl7qzhazdtqq
Recognizing Textual Entailment: Challenges in the Portuguese Language
2018
Information
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.
In addition, we conclude that semantic-based approaches are promising in this task, and that combining data from European and Brazilian Portuguese is less straightforward than it may initially seem. ...
) and paraphrases from text written in the Portuguese language, by employing supervised machine learning techniques. ...
Henrique Lopes Cardoso has supervised the work, namely for defining the methods proposed, designing the experimental settings and analyzing results. ...
doi:10.3390/info9040076
fatcat:e7n6olpwvjbbjpo3wjss5wkoxy
Crossing the Conversational Chasm: A Primer on Natural Language Processing for Multilingual Task-Oriented Dialogue Systems
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 pre-print arXiv:2104.08570v1 fatcat:nbqgccmjcbcalcceijr5zervtm
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent to complete a concrete task. ...
On the other hand, their effectiveness beyond these boundaries is doubtful or hard to assess due to the lack of linguistically diverse benchmarks (especially for natural language generation and end-to-end ...
Acknowledgments Evgeniia Razumovskaia is supported by a scholarship from Huawei. ...
arXiv:2104.08570v2
fatcat:bi5xizz4wzct5fpiuk3ikotjta
A Design Proposal of an Online Corpus-Driven Dictionary of Portuguese for University Students
2019
Journal of Portuguese Linguistics
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.
benchmark. ...
Furthermore, the undertaking of this PhD project in Portugal by a Brazilian researcher, under the supervision of Portuguese linguists, reveals the underlying motto of my research: to strengthen the academic ...
doi:10.5334/jpl.209
fatcat:ofqxdeezmnav3mzbujrgmzt3j4
Social Media Text Processing and Semantic Analysis for Smart Cities
[article]
2017
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.
We then use a combination of bag-of-embeddings and traditional bag-of-words to train travel-related classifiers in both Portuguese and English to filter travel-related content from non-related. ...
in a period of 3 months. ...
Acknowledgements First of all, my deep gratitude to my friends for being on my side when I was a bit down. ...
arXiv:1709.03406v1
fatcat:styrizf3k5caxoh33xqaonkpye
Robust Complaint Processing in Portuguese
2021
Information
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 2022; you can also visit the original URL.
The file type is application/pdf.
This paper exposes a set of challenges encountered when dealing with a real-world complex NLP problem, based on user-generated complaint data in Portuguese. ...
However, most achievements are evaluated on benchmarked curated corpora, with little attention devoted to user-generated content and less-resourced languages. ...
An additional set of 28,838 unannotated sentences was included in the corpus, with the aim of enabling the usage of semi-supervised approaches. ...
doi:10.3390/info12120525
fatcat:q4qf5lotvfecfek5k6woar7q5i
A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era
2016
Zenodo
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.
This research was supported in part by a Discovery and Innovation Research Seed award from the Office of the Vice Provost for Research at Cornell. ...
the language used in Portuguese newspapers than that used in Brazilian newspapers. ...
They performed semantic role labeling on sentences to extract features based on ngrams and trained a classifier to classify a sentence as future referenced or not. ...
doi:10.5281/zenodo.1242850
fatcat:nfkqg7jhjffdvgezdjzc6xxppa
Without lexicons, multiword expression identification will never fly: A position statement
2019
Proceedings of the Joint Workshop on Multiword Expressions and WordNet (MWE-WN 2019)
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.
Because most multiword expressions (MWEs), especially verbal ones, are semantically non-compositional, their automatic identification in running text is a prerequisite for semantically-oriented downstream ...
We define requirements for such a minimal NLP-oriented lexicon, and we propose a roadmap for the MWE community driven by these requirements. ...
a seen MWE and maintain a direct dependency relation, whatever the label and direction of this dependency. ...
doi:10.18653/v1/w19-5110
dblp:conf/mwe/SavaryCR19
fatcat:d5rovrbxhnapno7ncnon45noay
Multi-word Entity Classification in a Highly Multilingual Environment
2017
Proceedings of the 13th Workshop on Multiword Expressions (MWE 2017)
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.
The program also included a panel discussion on the future directions of the MWE community and the SIGLEX Section. ...
and integrate richer arc labels and nonflat structures to predict internal MWE structure. ...
Juan de la Cierva formación grant (FJCI-2014-22853), and by a postdoctoral fellowship granted by the Galician Government (POS-A/2013/191). ...
doi:10.18653/v1/w17-1702
dblp:conf/mwe/ChesneyJSP17
fatcat:bv7aavgth5eurmzuphuowtuuhq
Program Committee
2006
2006 Sixth IEEE International Workshop on Source Code Analysis and Manipulation
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.
The program combined the main conference with a special day on wordnets and word-embeddings and finished with a half day workshop on technology enhanced learning (TEL). ...
of Hamburg) and Using a Grammar Implementation to Teach Writing Skills by Dan Flickinger (Stanford). ...
Acknowledgments We wish to thank Georgia Sanna for the first joint analysis about the possibility of creating a wordnet for the Sardinian language. ...
doi:10.1109/scam.2006.23
dblp:conf/scam/X06c
fatcat:2dhsf7loj5hlffu2jxpmlo2qcq
FarsTail: A Persian Natural Language Inference Dataset
[article]
2021
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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
A carefully designed multi-step process is adopted to ensure the quality of the dataset. ...
The samples are generated from 3,539 multiple-choice questions with the least amount of annotator interventions in a way similar to the SciTail dataset. ...
including a collection of 10,000 pairs, half in Brazilian Portuguese and half in European Portuguese. • XNLI [9] : This dataset was developed for evaluating the cross-lingual understanding capabilities ...
arXiv:2009.08820v2
fatcat:bpel5fhq3jhmfph2aldk5l2ocu
Entity Retrieval and Text Mining for Online Reputation Monitoring
[article]
2018
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.
As such, we propose the inclusion of entity retrieval capabilities as a first step towards the extension of current ORM capabilities. ...
This is a challenging problem which traditional entity search systems cannot cope with. ...
As expected, this reduces the generality of the model, as it is biased towards a specific domain. Supervised learning approaches require training data. ...
arXiv:1801.07743v1
fatcat:f56lljaavnd6zm4vnngs2m3tga
Recent Advances
2018
Journal of Optimization Theory and Applications
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 used a supervised learning algorithm implemented by the CRF++ Package 6 . ...
If a certain amount of linguistic similarity is found in a text passage with a lexicalized label, this text segment can then be semantically annotated with the concepts the label is associated with. ...
Towards a System for Dynamic Language Resources in LOD Combined analysis of news and Twitter messages Mian Du Jussi Kangasharju Ossi Karkulahti Lidia Pivovarova Roman Yangarber University of Helsinki, ...
doi:10.1007/s10957-018-1316-3
fatcat:6mmzisl7jbhsvi5dhblc3jqimq
Over a Decade of Social Opinion Mining
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2021 accepted arXiv:2012.03091v2 fatcat:imq4v7fu4bgmrc2scflbkmn3de
Such multi-source information fusion plays a fundamental role in mining of people's social opinions from social media platforms. ...
A thorough systematic review was carried out on Social Opinion Mining research which totals 485 studies and spans a period of twelve years between 2007 and 2018. ...
The first column in-
dicates the algorithm, the second lists the type of learning algorithm, in terms
of Supervised (Sup), Unsupervised (Unsup) and Semi-supervised (Semi-sup),
which result corresponds ...
arXiv:2012.03091v1
fatcat:bm5nydbdvbalzi33l3w2ivkdja
AUSTRAL: v.2, n.3 (2013)
2013
Austral
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.
All of the contributions will be subjected to a scientific review. ...
The journal publishes original articles and book reviews in English, Portuguese or Spanish about themes that lie in the vast area of Strategy and International Relations, with special interest in issues ...
The trajectory could well be toward a vision of building global integration from south to north. ...
doi:10.22456/2238-6912.37107
fatcat:z3didvoykvagrkrzql5qzet7lu
« Previous
Showing results 1 — 15 out of 124 results