TNT-NLG , System 2 : Data Repetition and Meaning Representation Manipulation to Improve Neural Generation
By Shubhangi Tandon, Shereen Oraby, Lena Reed, Stephanie M. Lukin, Marilyn A. Walker. 2018
7 citations recorded by the source corpus.
Subfields: Natural Language Processing, Representation & Self-Supervised Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
- Ondrej Dusek
- Verena Rieser
- Jekaterina Novikova
- Varun Prashant Gangal
- Eduard H. Hovy
- Teruko Mitamura
- Soroush Vosoughi
- Mohit Bansal
In Representation & Self-Supervised Learning
- Jason Wei
- Sarath Chandar
- Eduard H. Hovy
- Steven Y. Feng
- Verena Rieser
- Teruko Mitamura
- Soroush Vosoughi
- Ondrej Dusek
Citations in the corpus
- A Survey of Data Augmentation Approaches for NLP (2021, methodology): “Tandon et al. (2018) propose DA for E2E-NLG based on permuting the input MR sequence.”
- Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge (2019, methodology): “A number of systems are based on the TGEN baseline and aiming to improve it: TNT1 (Oraby et al. 2018a) and TNT2 (Tandon et al. 2018) are using TGEN with two different data augmentation techniques (see Section 6.3).”
- Findings of the E2E NLG Challenge (2018, neutral): “♥TNT2 (Tandon et al., 2018): TGEN with data augmentation 0.”
- A Discriminator Improves Unconditional Text Generation without Updating the Generator (2020, unknown): “They usually use a reranker to select the best one as the output (Tandon et al., 2018; Deriu and Cieliebak, 2018).”