1 |
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics
|
|
|
|
In: Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021) ; https://hal.archives-ouvertes.fr/hal-03466171 ; Proceedings of the 1st Workshop on Natural Language Generation, Evaluation, and Metrics (GEM 2021), Aug 2021, Online, France. pp.96-120, ⟨10.18653/v1/2021.gem-1.10⟩ (2021)
|
|
BASE
|
|
Show details
|
|
2 |
THEaiTRobot 1.0
|
|
Rosa, Rudolf; Dušek, Ondřej; Kocmi, Tom. - : Charles University, Faculty of Mathematics and Physics, Institute of Formal and Applied Linguistics (UFAL), 2021. : The Švanda Theatre in Smíchov, 2021. : The Academy of Performing Arts in Prague, Theatre Faculty (DAMU), 2021
|
|
BASE
|
|
Show details
|
|
3 |
The GEM Benchmark: Natural Language Generation, its Evaluation and Metrics ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
MiRANews: Dataset and Benchmarks for Multi-Resource-Assisted News Summarization ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
One Model, Many Languages: Meta-learning for Multilingual Text-to-Speech ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge ...
|
|
|
|
BASE
|
|
Show details
|
|
10 |
RankME: Reliable Human Ratings for Natural Language Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity ...
|
|
|
|
Abstract:
We present three enhancements to existing encoder-decoder models for open-domain conversational agents, aimed at effectively modeling coherence and promoting output diversity: (1) We introduce a measure of coherence as the GloVe embedding similarity between the dialogue context and the generated response, (2) we filter our training corpora based on the measure of coherence to obtain topically coherent and lexically diverse context-response pairs, (3) we then train a response generator using a conditional variational autoencoder model that incorporates the measure of coherence as a latent variable and uses a context gate to guarantee topical consistency with the context and promote lexical diversity. Experiments on the OpenSubtitles corpus show a substantial improvement over competitive neural models in terms of BLEU score as well as metrics of coherence and diversity. ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.1809.06873 https://arxiv.org/abs/1809.06873
|
|
BASE
|
|
Hide details
|
|
16 |
The E2E Dataset: New Challenges For End-to-End Generation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|