Imitation learning for language generation from unaligned data

By Gerasimos Lampouras, Andreas Vlachos. 2016

52 citations recorded by the source corpus.

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

Citations in the corpus

Neural Generation for Czech: Data and Baselines (2019, background): “Therefore, inspired by Sharma et al. (2017), we test using fully lexicalized input DAs with the main generator to check if it learns to produce more appropriate structure for concrete values (while still producing delexicalized output).”
Creating Training Corpora for NLG Micro-Planners (2017, neutral): “, 2016; Lampouras and Vlachos, 2016). Similarly, Novikova and Rieser (2016) described a framework for collecting data-text pairs using automatic quality control measures and evaluating how the type of the input representations (text vs pictures) impacts the quality of crowdsourced text.”
The E2E Dataset: New Challenges For End-to-End Generation (2017, background): “To establish a baseline on the task data, we use TGen (Duˇsek and Jurˇc´ıˇcek, 2016a), one of the re-Metric”
Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization (2022, methodology): “Imitation learning for NLP. Algorithms such as Schedule Sampling (SS) (Bengio et al., 2015), Parallel SS (Duckworth et al., 2019), SS for Transformers (Mihaylova & Martins, 2019), Diffential SS (Goyal et al., 2017), LOLS (Lampouras & Vlachos, 2016; Chang et al., 2015), TextGAIL (Wu et al., 2021b), a”
Why We Need New Evaluation Metrics for NLG (2017, methodology): “Our paper clearly demonstrates the need for more advanced metrics, as used in related fields, including: assessing output quality within the dialogue context, e.g. (Dušek and Jurčı́ček, 2016); extrinsic evaluation metrics, such as NLG’s contribution to task success, e.g. (Rieser et al., 2014; Gka”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, methodology): “The approach of Lampouras and Vlachos (2016), also uses unaligned mr-text pairs from bagel, as well as the related sf hotel and restaurant dataset by Wen et al.”
Findings of the E2E NLG Challenge (2018, neutral): “(Dušek and Jurčı́ček, 2015; Wen et al., 2015b; Mei et al., 2016; Wen et al., 2016; Sharma et al., 2016; Dušek and Jurčı́ček, 2016a; Lampouras and Vlachos, 2016).”
End-to-End Content and Plan Selection for Data-to-Text Generation (2018, methodology): “End-to-end methods have already been applied to increasingly complex data to simultaneously learn sentence planning and surface realization but were often restricted by the limited data availability (Wen et al., 2015; Mei et al., 2015; Duˇsek and Jurˇc´ıˇcek, 2016; Lampouras and Vlachos, 2016).”
Can Neural Generators for Dialogue Learn Sentence Planning and Discourse Structuring? (2018, background): “Recent work in NNLG explicitly claims that training models end-to-end allows them to do both sentence planning and surface realization without the need for intermediate representations (Dusek and Jurc´ıcek, 2016b; Lampouras and Vlachos, 2016; Mei et al., 2016; Wen et al., 2015; Nayak et al., 2017).”
A Deep Ensemble Model with Slot Alignment for Sequence-to-Sequence Natural Language Generation (2018, background): “C L ] 1 6 M ay 2 01 8 2016; Dušek and Jurčı́ček, 2016), but also other concepts, such as imitation learning (Lampouras and Vlachos, 2016).”
Controlling Personality-Based Stylistic Variation with Neural Natural Language Generators (2018, background): “not surprising that recent work using neural generation methods has also focused on the restaurant domain (Wen et al., 2015; Mei et al., 2015; Dusek and Jurcı́cek, 2016b; Lampouras and Vlachos, 2016; Juraska et al., 2018).”
TNT-NLG , System 2 : Data Repetition and Meaning Representation Manipulation to Improve Neural Generation (2018, background): “However, there has been a recent movement from the NLG community towards end-toend (E2E) neural models that learn and generate sentence realizations in one step (Wen et al., 2015; Mei et al., 2016; Dušek and Jurcicek, 2016; Lampouras and Vlachos, 2016).”
NLG Challenge : Neural Models vs . Templates (2018, background): “These approaches attract a lot of attention, because they perform joint learning of textual structure and surface realization patterns from non-aligned data, which allows for a significant reduction of the amount of human annotation effort needed for NLG corpus creation (Wen et al., 2015; Mei et al.”