TY - GEN
T1 - AggGen
T2 - Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
AU - Xu, Xinnuo
AU - Dušek, Ondrej
AU - Rieser, Verena
AU - Konstas, Ioannis
N1 - Funding Information:
We show that explicit sentence planning, i.e., input ordering and aggregation, helps substantially to produce output which is both semantically correct as well as naturally sounding. Crucially, this also enables us to directly evaluate and inspect both the model’s planning and alignment performance by comparing to manually aligned reference texts. Our system outperforms vanilla seq2seq models when considering semantic accuracy and word-overlap based metrics. Experiment results also show that AGGGEN is robust to noisy training data. We plan to extend this work in three directions: Other Generation Models. We plan to plug other text generators, e.g. pre-training based approaches (Lewis et al., 2020; Kale and Rastogi, 2020), into AGGGEN to enhance their interpretability and controllability via sentence planning and generation. Zero/Few-shot scenarios. Kale and Rastogi (2020)’s work on low-resource NLG uses a pretrained language model with a schema-guided representation and hand-written templates to guide the representation in unseen domains and slots. These techniques can be plugged into AGGGEN, which allows us to examine the effectiveness of the explicit sentence planning in zero/few-shot scenarios. Including Content Selection. In this work, we concentrate on the problem of faithful surface realization based on E2E and WebNLG data, which both operate under the assumption that all input predicates have to be realized in the output. In contrast, more challenging tasks such as RotoWire (Wiseman et al., 2017), include content selection before sentence planning. In the future, we plan to include a content selection step to further extend AGGGEN’s usability. Acknowledgments This research received funding from the EPSRC project AISec (EP/T026952/1), Charles University project PRIMUS/19/SCI/10, a Royal Society research grant (RGS/R1/201482), a Carnegie Trust incentive grant (RIG009861). This research also received funding from Apple to support research at Heriot-Watt University and Charles University. We thank Alessandro Suglia, Jindrich Helcl, and Hen-rique Ferrolho for their suggestions. We thank the anonymous reviewers for their helpful comments.
Publisher Copyright:
© 2021 Association for Computational Linguistics
PY - 2021/8
Y1 - 2021/8
N2 - We present AggGen (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.
AB - We present AggGen (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AggGen performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.
UR - http://www.scopus.com/inward/record.url?scp=85118952480&partnerID=8YFLogxK
U2 - 10.18653/v1/2021.acl-long.113
DO - 10.18653/v1/2021.acl-long.113
M3 - Conference contribution
AN - SCOPUS:85118952480
VL - 1
SP - 1419
EP - 1434
BT - Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
PB - Association for Computational Linguistics
Y2 - 1 August 2021 through 6 August 2021
ER -