1,720,965 research outputs found
UniPI at SemEval-2016 Task 4: Convolutional Neural Networks for Sentiment Classificatio
No full textThe paper describes our submission to the task on Sentiment Analysis on Twitter at SemEval 2016. The approach is based on a Deep Learning architecture using convolutional neural networks. The approach used only word embeddings as features. The submission used embeddings created from a corpus of news articles. We report on further experiments using embeddings built for a corpus of tweets as well as sentiment specific word embeddings obtained by distant supervision
Adapting Linguistic Tools for the Analysis of Italian Medical Records
Get PDFSUMMARY: Weaddress the problem ofrecogni-tion ofmedical entities in clinical records
written in Italian. We report on experiments
performed on medical data in English provid-ed in the shared tasks at CLEF-ER 2013 and
SemEval 2014. This allowed us to refine
Named Entity recognition techniques to deal
with the specifics of medical and clinical lan-guage in particular. We present two ap-proaches for transferring the techniques to Italian. One solution relies onthe creation of an Italian corpus of annotated clinical records
and the other onadapting existing linguistic
tools to the medical domain.
RIASSUNTO. Questo lavoro affronta il problema
del riconoscimento di entità mediche inrefer-ti medici in lingua italiana. Riferiamo su de-gli esperimenti svolti su testi medici in ingle-se forniti nei task di CLEF-ER 2013 e SemE-val 2014. Questi ci hanno consentito di raffi-nare le tecniche di Named Entity recognition
per trattare le specificità del linguaggio me-dico e in particolare quello dei referti clinici.
Presentiamo due approcci al trasferimento di
queste tecniche all’italiano. Una soluzione
consiste nella creazione di un corpus di refer-ti medici in italiano annotato con entità me-diche e l’altro nell’adattarestrumenti tradi-zionali per l’analisi linguistica al dominio
medico
Machine Translation for Entity Recognition across Languages in Biomedical Documents
No full textWe report on our experiments for the CLEF 2013 Entity Recogni-tion Challenge. Our approach is based on a combination of machine translation and NE tagging techniques. The Silver Standard Corpus (SSC) is used to obtain a corresponding annotated corpus in the target language. The plain text of the SSC is translated and a mapping is created between entities in the original and phrases in the translation, to which are associated the same CUIs as in the origi-nal. This produces a Bronze Standard Corpus (BSC) in the target language. A dictionary of entities is also created, which associates to each pair (entity text, semantic group) the corresponding CUIs that appeared in the SSC. The BSC is used to train a model for a Named Entity tagger. The model is used for tagging entities in sentences in the target language with the proper semantic group and the entity dictionary is used for associating CUIs to each of them
UniPi: Recognition of Mentions of Disorders in Clinical Text
No full textThe paper describes our experiments addressing the SemEval 2014 task on the Analysis of Clinical text. Our approach consists in extending the techniques of NE recognition, based on sequence labelling, to address the special issues of this task, i.e. the presence of overlapping and discontiguous mentions and the requirement to map the mentions to unique identifiers. We explored using supervised methods in combination with word embeddings generated from unannotated data
Detecting the scope of negations in clinical notes
Get PDFWe address the problem of automatically detecting the scope of negations and speculations in clinical notes, by proposing a machine-learning algorithm that analyzes the dependency tree of a sentence. Given a negative/speculative cue, the algorithm tries to extend the boundary of the scope towards the left and the right, by navigating through the parse tree. We report on experiments with the algorithm using the Bioscope corpus
Annotation and Extraction of Relations from Italian Medical Records
No full textWe address the problem of extracting knowledge from large scale clinical records written in Italian by physicians. We perform recognition of relevant entities such as symptoms, diseases, treatments, measurements, drugs and so forth, and then we determine their semantic relations. We developed suitable training corpora in order to apply machine learning techniques to this task. We report on experiments performed on medical data provided in the context of a regional research project on technologies for health care
Using Embeddings for Both Entity Recognition and Linking in Tweets
Get PDFL’articolo descrive la nostra partecipazione al task di Named Entity rEcognition and Linking in Italian Tweets (NEEL-IT) a Evalita 2016. Il nostro approccio si basa sull’utilizzo di un Named Entity tagger che sfrutta embeddings sia character-level che word-level. I primi consentono di apprendere le idiosincrasie della scrittura nei tweet. L’uso di un tagger completo consente di riconoscere uno spettro più ampio di entità rispetto a quelle conosciute per la loro presenza in Knowledge Base o gazetteer. Le prove sottomesse hanno ottenuto il primo, secondo e quarto dei punteggi ufficiali.The paper describes our sub-missions to the task on Named Entity rEcognition and Linking in Italian Tweets (NEEL-IT) at Evalita 2016. Our approach relies on a technique of Named Entity tagging that exploits both charac-ter-level and word-level embeddings. Character-based embeddings allow learn-ing the idiosyncrasies of the language used in tweets. Using a full-blown Named Entity tagger allows recognizing a wider range of entities than those well known by their presence in a Knowledge Base or gazetteer. Our submissions achieved first, second and fourth top offi-cial scores
Convolutional Neural Networks for Sentiment Analysis on Italian Tweets
No full textThe paper describes our sub-mission to the task 2 of SENTIment POLarity Classification in Italian Tweets at Evalita 2016. Our approach is based on a convolutional neural network that exploits both word embeddings and Senti-ment Specific word embeddings. We also experimented a model trained with a distant supervised corpus. Our submission with Sentiment Specific word embed-dings achieved the first official scor
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
