Page: 1... 188 189 190 191 192
Hits 3.821 – 3.840 of 3.840
3821 |
Arabic to English Machine Translation of Verb Phrases Using Rule-Based Approach
|
|
|
|
In: http://thescipub.com/PDF/jcssp.2012.277.286.pdf
|
|
BASE
|
|
Show details
|
|
3822 |
Developing Partially-Transcribed Speech Corpus from Edited Transcriptions
|
|
|
|
In: http://www.lrec-conf.org/proceedings/lrec2012/pdf/987_Paper.pdf
|
|
BASE
|
|
Show details
|
|
3823 |
RECENT ADVANCES IN ROMANIAN LANGUAGE TEXT-TO-SPEECH SYNTHESIS
|
|
In: http://www.acad.ro/sectii2002/proceedings/doc2010-1/13-Burileanu.pdf
|
|
BASE
|
|
Show details
|
|
3824 |
ABSTRACT A TURKISH AUTOMATIC TEXT SUMMARIZATION SYSTEM
|
|
|
|
In: http://www.geocities.com/altanzeynep/411-112.pdf
|
|
BASE
|
|
Show details
|
|
3825 |
Effective Sentiment Analysis of Social Media Datasets using Naive Bayesian Classification
|
|
|
|
In: http://research.ijcaonline.org/volume99/number13/pxc3898274.pdf
|
|
BASE
|
|
Show details
|
|
3826 |
©IJEERT www.ijeert.org 51 Sentiment Analysis Based on Dictionary Approach
|
|
|
|
In: http://www.ijeert.org/pdf/v3-i1/9.pdf
|
|
BASE
|
|
Show details
|
|
3827 |
Report on KDD Conference 2004 Panel Discussion Can Natural Language Processing Help Text Mining?
|
|
|
|
In: http://www.sigkdd.org/explorations/issues/6-2-2004-12/nlpPanelKao.pdf
|
|
BASE
|
|
Show details
|
|
3828 |
Merging Changes in XML Documents Using Reliable Context Fingerprints
|
|
|
|
In: http://csis.pace.edu/~marchese/CS835/Student_Readings/p52-ronnau.pdf
|
|
BASE
|
|
Show details
|
|
3829 |
Web Service Programming for Biological Text Mining
|
|
|
|
In: http://lair.indiana.edu/sigirbio/final/ghanem.pdf
|
|
BASE
|
|
Show details
|
|
3830 |
Experiments in CLIR Using Fuzzy String Search Based on Surface Similarity
|
|
|
|
In: http://ltrc.iiit.ac.in/anil/papers/pp237-subramaniam.pdf
|
|
BASE
|
|
Show details
|
|
3831 |
Modeling Click-through Based Word-pairs for Web Search
|
|
|
|
In: http://research.microsoft.com/en-us/um/people/jfgao/paper/2013/sigirfp436-Jagarlamudi.pdf
|
|
BASE
|
|
Show details
|
|
3832 |
Mining Entity Translations from Comparable Corpora: A Holistic Graph Mapping Approach
|
|
|
|
In: http://www.postech.ac.kr/~swhwang/CIKM11a.pdf
|
|
BASE
|
|
Show details
|
|
3833 |
On-line Reference Assignment for Anaphoric and Non-Anaphoric Nouns: A Unified, Memory-Based Model in ACT-R
|
|
|
|
In: http://act-r.psy.cmu.edu/papers/760/p1403.pdf
|
|
BASE
|
|
Show details
|
|
3834 |
Converting English text to speech : a machine learning approach
|
|
|
|
BASE
|
|
Show details
|
|
3835 |
Deep Learning with Constraints for Answer-Agnostic Question Generation in Legal Text Understanding
|
|
|
|
BASE
|
|
Show details
|
|
3836 |
Text and Network Mining for Literature-Based Scientific Discovery in Biomedicine.
|
|
|
|
BASE
|
|
Show details
|
|
3837 |
Muak Sa-aak: Challenges of an Extensive Phoneme Inventory for a Contained Latin-Based Orthography
|
|
|
|
BASE
|
|
Show details
|
|
3839 |
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
|
|
3840 |
Documentation of P clue/ lexical class from Weka computer Web Service
|
|
|
|
BASE
|
|
Show details
|
|
Page: 1... 188 189 190 191 192
|
|