-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
fcdc0ff
commit ddf9af6
Showing
1 changed file
with
35 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1 +1,35 @@ | ||
# NLG-The-impact-of-data-quality-on-automatic-text-generation-from-RDF-data | ||
# NLG-The-impact-of-data-quality-on-automatic-text-generation-from-RDF-data | ||
|
||
Authors: Dario Della Mura - David Doci | ||
|
||
Il lavoro presentato è stato sviluppato nel corso dell'attività di stage, come ricercatori nel campo della Natural Language Generation, presso il laboratorio Insid&s Lab di Milano-Bicocca. | ||
Il lavoro svolto si occupa della creazione un framework per la corretta valutazione dell'impatto della qualità dei dataset di input sulla qualità del testo generato dai modelli di NLG, nello specifico: | ||
1) Creazione delle versioni "Concept-Based" e "Entity-Based" del dataset di WebNLG; | ||
2) Valutazione della qualità dei dataset creati; | ||
3) Addestramento dei modelli LSTM e Transformer mediante l'utilizzo del tool OpenNMT; | ||
4) Generazione del testo in linguaggio naturale effettuato dai modelli LSTM e Transformer; | ||
5) Valutazione della qualità del testo generato dai modelli NLG; | ||
6) Analisi finali. | ||
|
||
|
||
Per ricevere il materiale completo della tesi svolta contattarci alle seguenti email: | ||
|
||
Dario Della Mura : dario.dellamura@gmail.com | ||
David Doci : d.doci@outlook.it | ||
|
||
|
||
---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ||
|
||
The work presented was developed during the internship, as researchers in the field of Natural Language Generation, at the Insid&s Lab laboratory in Milan-Bicocca. | ||
The work carried out deals with the creation of a framework for the correct assessment of the impact of the quality of the input datasets on the quality of the text generated by the NLG models, specifically: | ||
1) Creation of the "Concept-Based" and "Entity-Based" versions of the WebNLG dataset; | ||
2) Evaluation of the quality of the datasets created; | ||
3) Training of LSTM and Transformer models using the OpenNMT tool; | ||
4) Natural language text generation by LSTM and Transformer models; | ||
5) Evaluation of the quality of the text generated by the NLG models; | ||
6) Final analysis. | ||
|
||
To receive the complete material of your thesis please contact us at the following emails: | ||
|
||
Dario Della Mura : dario.dellamura@gmail.com | ||
David Doci : d.doci@outlook.it |