# Transforming Multi-Conditioned Generation from Meaning Representation

arXiv: https://arxiv.org/abs/2101.04257 · HTML: https://mlsanity.com/paper/2101.04257/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 12 Jan 2021.

## Builds on (most cited first, 15 of 15)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challenge](https://mlsanity.com/paper/1901.07931/) (2019)
- [Learning Neural Templates for Text Generation](https://mlsanity.com/paper/1808.10122/) (2018)
- [Content preserving text generation with attribute controls](https://mlsanity.com/paper/1811.01135/) (2018)
- [Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue](https://mlsanity.com/paper/1906.07220/) (2019)
- [Sequence-to-Sequence Generation for Spoken Dialogue via Deep Syntax Trees and Strings](https://mlsanity.com/paper/1606.05491/) (2016)
- [Stable Style Transformer: Delete and Generate Approach with Encoder-Decoder for Text Style Transfer](https://mlsanity.com/paper/2005.12086/) (2020)
- [A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation](https://mlsanity.com/paper/1805.06553/) (2018)
- [End-to-End Content and Plan Selection for Data-to-Text Generation](https://mlsanity.com/paper/1810.04700/) (2018)
- [Designing a Symbolic Intermediate Representation for Neural Surface Realization](https://mlsanity.com/paper/1905.10486/) (2019)

## Built on by (most cited first, 1 of 1)

- [Multimodal Interactions Using Pretrained Unimodal Models for SIMMC 2.0](https://mlsanity.com/paper/2112.05328/) (2021)

## Abstract (arXiv)

In task-oriented conversation systems, natural language generation systems that generate sentences with specific information related to conversation flow are useful. Our study focuses on language generation by considering various information representing the meaning of utterances as multiple conditions of generation. NLG from meaning representations, the conditions for sentence meaning, generally goes through two steps: sentence planning and surface realization. However, we propose a simple one-stage framework to generate utterances directly from MR (Meaning Representation). Our model is based on GPT2 and generates utterances with flat conditions on slot and value pairs, which does not need to determine the structure of the sentence. We evaluate several systems in the E2E dataset with 6 automatic metrics. Our system is a simple method, but it demonstrates comparable performance to previous systems in automated metrics. In addition, using only 10% of the data set without any other techniques, our model achieves comparable performance, and shows the possibility of performing zero-shot generation and expanding to other datasets.