| 361 |
Salience in the Generation of Multimodal Referring Acts
|
|
|
|
In: http://mcs.open.ac.uk/pp2464/inpress/Piwek-ICMI2009.pdf
|
|
BASE
|
|
Show details
|
|
|
| 362 |
Generating a Sentence from a Thought
|
|
|
|
In: http://world-comp.org/p2011/ICA3771.pdf
|
|
BASE
|
|
Show details
|
|
|
| 363 |
Fully Generated Scripted Dialogue for Embodied Agents
|
|
|
|
In: http://www.csd.abdn.ac.uk/~kvdeemte/NECA-final.pdf
|
|
BASE
|
|
Show details
|
|
|
| 364 |
Language Engineering System for Automatic Conversion of English Cyber Data into Urdu Websites
|
|
|
|
In: http://www.cs.bham.ac.uk/~isb855/papers/ICCA06_.pdf
|
|
BASE
|
|
Show details
|
|
|
| 365 |
doi: 0.5087/dad.2012.205 G-Asks: An Intelligent Automatic Question Generation System for Academic Writing Support
|
|
|
|
In: http://elanguage.net/journals/dad/article/viewFile/1463/2827/
|
|
BASE
|
|
Show details
|
|
|
| 367 |
Text-to-text Surface Realisation using Dependency-tree Replacement
|
|
|
|
In: http://each.uspnet.usp.br/ivandre/papers/text2TextSurfaceReal(10p).pdf
|
|
BASE
|
|
Show details
|
|
|
| 368 |
An Annotated Corpus of Film Dialogue for Learning and Characterizing Character Style
|
|
|
|
In: http://games.soe.ucsc.edu/sites/default/files/1114_Paper.pdf
|
|
BASE
|
|
Show details
|
|
|
| 369 |
Experience
|
|
|
|
In: http://www.desilinguist.org/pdf/madnani-cv.pdf
|
|
BASE
|
|
Show details
|
|
|
| 370 |
Perceived or Not Perceived: Film Character Models for Expressive NLG
|
|
|
|
In: http://users.soe.ucsc.edu/~maw/papers/icids-v12.pdf
|
|
BASE
|
|
Show details
|
|
|
| 371 |
Solicited review(s): Name Surname, University, Country Open review(s): Name Surname, University, Country
|
|
|
|
In: http://www.semantic-web-journal.net/system/files/swj450.pdf
|
|
BASE
|
|
Show details
|
|
|
| 372 |
IOS Press Natural Language Generation in the Context of the Semantic Web
|
|
|
|
In: http://www.semantic-web-journal.net/system/files/swj511_0.pdf
|
|
BASE
|
|
Show details
|
|
|
| 373 |
Feeding memes: a verbal communication challenge
|
|
|
|
In: http://mobileguide06.di.unito.it/pdf/Simi%26al.pdf
|
|
BASE
|
|
Show details
|
|
|
| 374 |
On Moving on on Ontologies: Mass, Count and Long Thin Things
|
|
|
|
In: http://acl.ldc.upenn.edu/W/W94/W94-0309.pdf
|
|
BASE
|
|
Show details
|
|
|
| 375 |
Exploring neural paraphrasing to improve fluency of rule-based generation
|
|
|
|
Abstract:
Tutors: Leo Wanner i Simon Mille ; Treball fi de màster de: Master in Intelligent Interactive Systems ; Data-to-text generation is a greatly significant task in the field of natural language processing. FORGe, a typical rule-based generator, has excellent performance in the task of mapping from RDF triples to text. As this generator is strongly reliant on rules, despite the fact that the generated text is with highly semantic accuracy, and faithful to the input RDF triples, the generated sentence could be somewhat rigid in terms of fluency. This thesis would like to explore a possible way to improve the fluency of output text generated by FORGe. A neural paraphrase method is suggested to act as a post-processing method to achieve our goal. This method can control the tradeoff between two models, the fluency and semantic similarity model, and the lexical and/or syntactic diversity model by setting a parameter . In this way, it can not only make the output semantically consistent with the input, but also diversify the lexical and syntactic items of the sentence. In order to verify our idea, we designed and conducted related experiments. Furthermore, the performance of deep-learning based generator OSU Neural NLG, which also performs well in English D2T tasks, is considered as a baseline. Since we need to evaluate all the generated text, an automatic evaluation method is used in order to ensure an uniform evaluation criterion on these outputs in terms of semantic accuracy. Based on the result of this automatic evaluation method, we also conducted manual verification to make the evaluation result more reliable and have reference value. Through our experimental results, we believe that applying this neural paraphrase method as a post-processing stage is promising in improving the fluency of the output text generated by FORGe.
|
|
Keyword:
Data-to-text generation; Natural language processing; Neural paraphrase method; Rule-based generation; Semantic accuracy evaluation
|
|
URL: http://hdl.handle.net/10230/49231
|
|
BASE
|
|
Hide details
|
|
|
| 376 |
Spanish morphological generation with wide-coverage lexicons and decision trees
|
|
|
|
BASE
|
|
Show details
|
|
|
| 377 |
An adaptable lexical simplification architecture for major ibero-romance languages
|
|
|
|
BASE
|
|
Show details
|
|
|
| 379 |
Automatic generation of textual descriptions in data-to-text systems using a fuzzy temporal ontology: Application in air quality index data series
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
