Anirban laha @anirbanlaha Parag jain
#data2text #nlproc #NLG
* Answer display in Question Answering systems
* kB summarization
* Question Generation
Paradigms, domain, tasks, Facets are 4 aspects of change.
Introduction to NLG
Traditional, statistical and neural methods for NLG
NLG evaluation
1) Content selection, 2)Document planning, 3)surface realization
* The defined grammar can be represented as a hypergraph.
* Generation is done using finding the most probable path
#ACL2019nlp
Finding the best overall best path can be done using Dynamic programming (e.g. Veterbi)
1) Word level copy actions (shared softmax, copy/gen switch (Gulcehre et al. 2016) pointer gen. model (See et al. 2017)
arxiv.org/abs/1704.04368
been listed in the output the generator will never visit the occupation field again because there is nothing left to
say about it"
arxiv.org/pdf/1804.07789…
arxiv.org/pdf/1809.00582…
#ACL2019NLP
latent, discrete templates jointly with learning
to generate."
aclweb.org/anthology/D18-…
#ACL2019nlp
Evaluation methods for NLG
* word overlap metrics
* intrinsic Evaluation
* Human Evaluation
More info: en.wikipedia.org/wiki/BLEU
original paper: aclweb.org/anthology/P02-… (Papineni et al.)
and its variants (ROUGE-N, ROUGE-L ..)
read more: en.wikipedia.org/wiki/ROUGE_(me…
arxiv.org/abs/1705.04304
#acl2019nlp
FYI: This btw is used in (Serban et al. 2016) for QG and referred to as Embeddings Greedy
aclweb.org/anthology/P16-…