Polite Dialogue Generation Without Parallel Data
Open accessThe DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Stylistic dialogue response generation, with valuable applications in personality-based conversational agents, is a challenging task because the response needs to be fluent, contextually-relevant, as well as paralinguistically accurate. Moreover, parallel datasets for regular-to-stylistic pairs are usually unavailable. We present three weakly-supervised models that can generate diverse, polite (or rude) dialogue responses without parallel data. Our late fusion model (Fusion) merges the decoder of an encoder-attention-decoder dialogue model with a language model trained on stand-alone polite utterances. Our label-finetuning (LFT) model prepends to each source sequence a politeness-score scaled label (predicted by our state-of-the-art politeness classifier) during training, and at test time is able to generate polite, neutral, and rude responses by simply scaling the label embedding by the corresponding score. Our reinforcement learning model (Polite-RL) encourages politeness generation by assigning rewards proportional to the politeness classifier score of the sampled response. We also present two retrievalbased, polite dialogue model baselines. Human evaluation validates that while the Fusion and the retrieval-based models achieve politeness with poorer context-relevance, the LFT and Polite-RL models can produce significantly more polite responses without sacrificing dialogue quality.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
Unpaired image-to-image translation using cycle-consistent adversarial networks
Zhu, J.-Y., Park, T., Isola, P., & Efros, A. A. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.244 · Cited by 23,602 · cited 1×
“Style Transfer without Parallel Data Several previous works have looked at style transfer without parallel data, in both vision (Gatys et al., 2016; Zhu et al., 2017; Liu and Tuzel, 2016; Liu et al., 2017; Taigman et al., 2016; Kim et al., 2017; Yi et al., 2017), and text (Sennrich et al., 2016a;…”
MethodBLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Bidirectional recurrent neural networks
Schuster, M., & Paliwal, K. K. (1997) · IEEE Transactions on Signal Processing · doi:10.1109/78.650093 · Cited by 10,172 · cited 2×
“Our classifier mainly extends their work by adding a bi-directional LSTM layer (Hochreiter and Schmidhuber, 1997; Schuster and Paliwal, 1997) before the CNN layer to capture long-distance relationships in the sentence, which leads to higher cross-domain performance.”
BackgroundAmazon's Mechanical Turk: A New Source of Inexpensive, Yet High-Quality, Data?
Buhrmester, M., Kwang, T., & Gosling, S. D. (2011) · Perspectives on Psychological Science · doi:10.1177/1745691610393980 · Cited by 9,996
Weighted kappa: nominal scale agreement provision for scaled disagreement or partial credit
Cohen, J. (1968) · Psychological Bulletin · doi:10.1037/h0026256 · Cited by 8,736
Image Style Transfer Using Convolutional Neural Networks
Gatys, L. A., Ecker, A. S., & Bethge, M. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.265 · Cited by 6,025
Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
Simonyan, K., Vedaldi, A., & Zisserman, A. (2013) · arXiv · doi:10.48550/arxiv.1312.6034 · Cited by 5,370
Estimating within-group interrater reliability with and without response bias
James, L. R., Demaree, R. G., & Wolf, G. (1984) · Journal of Applied Psychology · doi:10.1037/0021-9010.69.1.85 · Cited by 4,774 · cited 1×
“een neutral and rude (Table. 4 DiscreteLFT column). 16These levels were defined by Landis and Koch (1977); also see https://en.wikipedia.org/wiki/Cohens_kappa 17As discussed in Weijters et al. (2010), James et al. (1984), and https://en.wikipedia.org/wiki/Likert_ scale, the ‘central tendency bias’ makes raters avoid us…”
MethodInfluentialLearning to Discover Cross-Domain Relations with Generative Adversarial Networks
Kim, T., Cha, M., Kim, H., Lee, J. K., & Kim, J. (2017) · arXiv · doi:10.48550/arxiv.1703.05192 · Cited by 1,716
Cited by
Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset
Rashkin, H., Smith, E. M., Li, M., & Boureau, Y.-L. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1534 · Cited by 771
Learning to summarize from human feedback
Stiennon, N., Ouyang, L., Wu, J., Ziegler, D. M., Lowe, R., Voss, C., Radford, A., Amodei, D., & Christiano, P. (2020) · arXiv · doi:10.48550/arxiv.2009.01325 · Cited by 550
A Survey of Controllable Text Generation Using Transformer-based Pre-trained Language Models
Zhang, H., Song, H., Li, S., Zhou, M., & Song, D. (2024) · ACM Computing Surveys · doi:10.1145/3617680 · Cited by 317
A Survey of Knowledge-enhanced Text Generation
Yu, W., Zhu, C., Li, Z., Hu, Z., Wang, Q., Ji, H., & Jiang, M. (2022) · ACM Computing Surveys · doi:10.1145/3512467 · Cited by 257
Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyond
Feder, A., Keith, K. A., Manzoor, E., Pryzant, R., Sridhar, D., Wood-Doughty, Z., Eisenstein, J., Grimmer, J., Reichart, R., Roberts, M. E., et al. (2022) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00511 · Cited by 220
“Such methods have a long history in NLP; for example, a conversational agent should be able to answer a user’s question while being perceived as polite (Niu and Bansal, 2018).”
BackgroundIncreasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
Rashkin, H., Reitter, D., Tomar, G. S., & Das, D. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.58 · Cited by 74
“Most relevant is the development of control-code-style input tokens such as in CTRL (Keskar et al., 2019) or the LFT model of Niu and Bansal (2018).”
BackgroundLearning towards conversational AI: A survey
Fu, T., Gao, S., Zhao, X., Wen, J.-R., & Yan, R. (2022) · AI Open · doi:10.1016/j.aiopen.2022.02.001 · Cited by 46
“Poor interpretability leads to poor controllability to some extent, though some work avoids toxic words or un-ethical responses with reinforcement learning (Niu and Bansal, 2018) or curriculum learning (Shen and Feng, 2020).”
BackgroundXu, P., Patwary, M., Shoeybi, M., Puri, R., Fung, P., Anandkumar, A., & Catanzaro, B. (2020) · arXiv · doi:10.48550/arxiv.2010.00840 · Cited by 12
Towards User-Centric Text-to-Text Generation: A Survey
Yang, D., & Flek, L. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-83527-9_1 · Cited by 10
Elastic Weight Removal for Faithful and Abstractive Dialogue Generation
Daheim, N., Dziri, N., Sachan, M., Gurevych, I., & Ponti, E. M. (2023) · arXiv · doi:10.48550/arxiv.2303.17574
Metadata
- Authors
- Niu, T., & Bansal, M.
- Venue
- Transactions of the Association for Computational Linguistics
- Publisher
- MIT Press - Journals
- Published
- 2018-12
- Volume
- 6
- Pages
- 373-389
- ISSN
- 2307-387X (ISSN-L)
- OpenAlex
- W2962753250
- Cited by
- 158
- References
- 17
- FWCI
- 12.45
- Type
- journal article
- Language
- en
- Open access
- diamond
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.