Academia.eduAcademia.edu

Outline

Title
Abstract
Introduction
Related Work
Dataset
Datasets
Results
Analysis
Conclusion and Future Work
References

Diversifying Dialogue Generation with Non-Conversational Text

Profile image of Cheng NiuCheng Niu

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

https://doi.org/10.18653/V1/2020.ACL-MAIN.634
visibility

…

description

11 pages

link

1 file

Abstract

Neural network-based sequence-to-sequence (seq2seq) models strongly suffer from the lowdiversity problem when it comes to opendomain dialogue generation. As bland and generic utterances usually dominate the frequency distribution in our daily chitchat, avoiding them to generate more interesting responses requires complex data filtering, sampling techniques or modifying the training objective. In this paper, we propose a new perspective to diversify dialogue generation by leveraging non-conversational text. Compared with bilateral conversations, nonconversational text are easier to obtain, more diverse and cover a much broader range of topics. We collect a large-scale nonconversational corpus from multi sources including forum comments, idioms and book snippets. We further present a training paradigm to effectively incorporate these text via iterative back translation. The resulting model is tested on two conversational datasets and is shown to produce significantly more diverse responses without sacrificing the relevance with context. * Equal contribution. Conversational Text Context 暗恋的人却不喜欢我 (Translation) The one I have a crush on doesn't like me. Response 摸摸头 Head pat. Non-Conversational Text Forum Comments 暗恋这碗酒，谁喝都会醉啊 Crush is an alcoholic drink, whoever drinks it will get intoxicated.

Related papers

Viola: A Topic Agnostic Generate-and-Rank Dialogue System
Basel Shbita

Cornell University - arXiv, 2021

We present Viola, an open-domain dialogue system for spoken conversation that uses a topic-agnostic dialogue manager based on a simple generate-and-rank approach. Leveraging recent advances of generative dialogue systems powered by large language models, Viola fetches a batch of response candidates from various neural dialogue models trained with different datasets and knowledge-grounding inputs. Additional responses originating from template-based generators are also considered, depending on the user's input and detected entities. The hand-crafted generators build on a dynamic knowledge graph injected with rich content that is crawled from the web and automatically processed on a daily basis. Viola's response ranker is a fine-tuned polyencoder that chooses the best response given the dialogue history. While dedicated annotations for the polyencoder alone can indirectly steer it away from choosing problematic responses, we add rule-based safety nets to detect neural degeneration and a dedicated classifier to filter out offensive content. We analyze conversations that Viola took part in for the Alexa Prize Socialbot Grand Challenge 4 and discuss the strengths and weaknesses of our approach. Lastly, we suggest future work with a focus on curating conversation data specifcially for socialbots that will contribute towards a more robust data-driven socialbot. 4th Proceedings of Alexa Prize (Alexa Prize 2020).

View PDFchevron_right
A Neural Conversation Generation Model via Equivalent Shared Memory Investigation
Xiaozhong Liu

Proceedings of the 30th ACM International Conference on Information & Knowledge Management, 2021

Conversation generation as a challenging task in Natural Language Generation (NLG) has been increasingly attracting attention over the last years. A number of recent works adopted sequence-tosequence structures along with external knowledge, which successfully enhanced the quality of generated conversations. Nevertheless, few works utilized the knowledge extracted from similar conversations for utterance generation. Taking conversations in customer service and court debate domains as examples, it is evident that essential entities/phrases, as well as their associated logic and interrelationships can be extracted and borrowed from similar conversation instances. Such information could provide useful signals for improving conversation generation. In this paper, we propose a novel reading and memory framework called Deep Reading Memory Network (DRMN) which is capable of remembering useful information of similar conversations for improving utterance generation. We apply our model to two large-scale conversation datasets of justice and e-commerce fields. Experiments prove that the proposed model outperforms the state-of-the-art approaches.

View PDFchevron_right
A Hybrid Retrieval-Generation Neural Conversation Model
junjie Hu

Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019

Intelligent personal assistant systems that are able to have multiturn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model [8]) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.

View PDFchevron_right
DialogBERT: Discourse-Aware Response Generation via Learning to Recover and Rank Utterances
Xiaodong Gu

2021

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through token-level self-attention. Such token-level encoding hinders the exploration of discourse-level coherence among utterances. This paper presents DialogBERT, a novel conversational response generation model that enhances previous PLM-based dialogue models. DialogBERT employs a hierarchical Transformer architecture. To efficiently capture the discourse-level coherence among utterances, we propose two training objectives, including masked utterance regression and distributed utterance order ranking in analogy to the original BERT training. Experiments on three multi-turn conversation datasets show that our approach remarkably outperforms the baselines, such as BART and DialoGPT, in terms of quantitative evaluation. The human evaluation suggests that Di...

View PDFchevron_right
Generative Deep Neural Networks for Dialogue: A Short Review
丽丽 姚

Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue response generation. The hope is that such models will be able to leverage massive amounts of data to learn meaningful natural language representations and response generation strategies, while requiring a minimum amount of domain knowledge and hand-crafting. An important challenge is to develop models that can effectively incorporate dialogue context and generate meaningful and diverse responses. In support of this goal, we review recently proposed models based on generative encoder-decoder neural network architectures, and show that these models have better ability to incorporate long-term dialogue history, to model uncertainty and ambiguity in dialogue, and to generate responses with high-level compositional structure.

View PDFchevron_right
Using Synthetic Data for Conversational Response Generation in Low-resource Settings
Adrian Ty

ArXiv, 2022

Response generation is a task in natural language processing (NLP) where a model is trained to respond to human statements. Conversational response generators take this one step further with the ability to respond within the context of previous responses. While there are existing techniques for training such models, they all require an abundance of conversational data which are not always available for low-resource languages. In this research, we make three contributions. First, we released the first Filipino conversational dataset collected from a popular Philippine online forum, which we named the “PEx Conversations Dataset”. Second, we introduce a data augmentation (DA) methodology for Filipino data by employing a Tagalog RoBERTa model to increase the size of the existing corpora. Lastly, we published the first Filipino conversational response generator capable of generating responses related to the previous 3 responses. With the supplementary synthetic data, we were able to improv...

View PDFchevron_right
CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models
Ravi Ghadia

2022

Natural Language Generation (NLG) represents a large collection of tasks in the field of NLP. While many of these tasks have been tackled well by the cross-entropy (CE) loss, the task of dialog generation poses a few unique challenges for this loss function. First, CE loss assumes that for any given input, the only possible output is the one available as the ground truth in the training dataset. In general, this is not true for any task, as there can be multiple semantically equivalent sentences, each with a different surface form. This problem gets exaggerated further for the dialog generation task, as there can be multiple valid responses (for a given context) that not only have different surface forms but are also not semantically equivalent. Second, CE loss does not take the context into consideration while processing the response and, hence, it treats all ground truths with equal importance irrespective of the context. But, we may want our final agent to avoid certain classes of responses (e.g. bland, non-informative or biased responses) and give relatively higher weightage for more context-specific responses. To circumvent these shortcomings of the CE loss, in this paper, we propose a novel loss function, CORAL, that directly optimizes recently proposed estimates of human preference for generated responses. Using CORAL, we can train dialog generation models without assuming non-existence of response other than the ground-truth. Also, the CORAL loss is computed based on both the context and the response. Our experiments show that, against various large and small scale baselines, our model is able to obtain significantly higher scores for the human preference estimate. While large-scale dialog models have shown much promise and aptitude for dialog generation, it is important to continue the search for more suitable loss functions for training dialog systems. Extensive comparisons on two benchmark datasets show that the proposed methods outperform strong state-of-the-art baseline models of different sizes. We will make the code and trained model checkpoints publicly available upon publication of this paper. Preprint. Under review.

View PDFchevron_right
Boosting Dialog Response Generation
Wenchao Du

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019

Neural models have become one of the most important approaches to dialog response generation. However, they still tend to generate the most common and generic responses in the corpus all the time. To address this problem, we designed an iterative training process and ensemble method based on boosting. We combined our method with different training and decoding paradigms as the base model, including mutual-information-based decoding and reward-augmented maximum likelihood learning. Empirical results show that our approach can significantly improve the diversity and relevance of the responses generated by all base models, backed by objective measurements and human evaluation.

View PDFchevron_right
Towards Robust Online Dialogue Response Generation
leyang cui

ArXiv, 2022

Although pre-trained sequence-to-sequence models have achieved great success in dialogue response generation, chatbots still suffer from generating inconsistent responses in real-world practice, especially in multi-turn settings. We argue that this can be caused by a discrepancy between training and realworld testing. At training time, chatbot generates response with the golden context, while it has to generate based on the context consisting of both user utterances and the model predicted utterances during real-world testing. With the growth of the number of utterances, this discrepancy becomes more serious in the multi-turn settings. In this paper, we propose a hierarchical sampling-based method consisting of both utterance-level sampling and semiutterance-level sampling, to alleviate the discrepancy, which implicitly increases the dialogue coherence. We further adopt reinforcement learning and re-ranking methods to explicitly optimize the dialogue coherence during training and in...

View PDFchevron_right
Velocidapter: Task-oriented Dialogue Comprehension Modeling Pairing Synthetic Text Generation with Domain Adaptation
Taha Aksu

2021

We introduce a synthetic dialogue generation framework, Velocidapter, which addresses the corpus availability problem for dialogue comprehension. Velocidapter augments datasets by simulating synthetic conversations for a task-oriented dialogue domain, requiring a small amount of bootstrapping work for each new domain. We evaluate the efficacy of our framework on a task-oriented dialogue comprehension dataset, MRCWOZ, which we curate by annotating questions for slots in the restaurant, taxi, and hotel domains of the MultiWOZ 2.2 dataset (Zang et al., 2020). We run experiments within a low-resource setting, where we pretrain a model on SQuAD, fine-tuning it on either a small original data or on the synthetic data generated by our framework. Velocidapter shows significant improvements using both the transformer-based BERTBase and BiDAF as base models. We further show that the framework is easy to use by novice users and conclude that Velocidapter can greatly help training over task-ori...

View PDFchevron_right

References (57)

  1. Mikel Artetxe, Gorka Labaka, Eneko Agirre, and Kyunghyun Cho. 2018. Unsupervised neural ma- chine translation. ICLR.
  2. Alexander Bartl and Gerasimos Spanakis. 2017. A retrieval-based dialogue system utilizing utterance and context embeddings. In 2017 16th IEEE Inter- national Conference on Machine Learning and Ap- plications (ICMLA), pages 1120-1125. IEEE.
  3. Samuel R Bowman, Luke Vilnis, Oriol Vinyals, An- drew Dai, Rafal Jozefowicz, and Samy Bengio. 2016. Generating sentences from a continuous space. In Proceedings of The 20th SIGNLL Confer- ence on Computational Natural Language Learning, pages 10-21.
  4. Ernie Chang, David Ifeoluwa Adelani, Xiaoyu Shen, and Vera Demberg. 2020. Unsupervised pidgin text generation by pivoting english data and self-training. arXiv preprint arXiv:2003.08272.
  5. Ryan Cotterell and Julia Kreutzer. 2018. Explain- ing and generalizing back-translation through wake- sleep. arXiv preprint arXiv:1806.04402.
  6. Richárd Csáky, Patrik Purgai, and Gábor Recski. 2019. Improving neural conversational models with entropy-based data filtering. In Proceedings of the 57th Annual Meeting of the Association for Com- putational Linguistics, pages 5650-5669, Florence, Italy. Association for Computational Linguistics.
  7. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training of deep bidirectional transformers for language under- standing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Tech- nologies, Volume 1 (Long and Short Papers), pages 4171-4186.
  8. Emily Dinan, Stephen Roller, Kurt Shuster, Angela Fan, Michael Auli, and Jason Weston. 2019. Wizard of wikipedia: Knowledge-powered conversational agents. ICLR.
  9. Xiang Gao, Yizhe Zhang, Sungjin Lee, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2019. Structuring latent spaces for stylized response gen- eration. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natu- ral Language Processing (EMNLP-IJCNLP), pages 1814-1823.
  10. Marjan Ghazvininejad, Chris Brockett, Ming-Wei Chang, Bill Dolan, Jianfeng Gao, Wen-tau Yih, and Michel Galley. 2018. A knowledge-grounded neural conversation model. In Thirty-Second AAAI Confer- ence on Artificial Intelligence.
  11. Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari, and Trevor Cohn. 2018. Iterative back- translation for neural machine translation. In Pro- ceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 18-24.
  12. Sepp Hochreiter and Jurgen Schmidhuber. 1997. Long short-term memory. Neural Computation, 9(8):1735-1780.
  13. Ari Holtzman, Jan Buys, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degener- ation. arXiv preprint arXiv:1904.09751.
  14. Yoon Kim and Alexander M Rush. 2016. Sequence- level knowledge distillation. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 1317-1327.
  15. Diederik Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. ICLR.
  16. Guillaume Klein, Yoon Kim, Yuntian Deng, Jean Senel- lart, and Alexander Rush. 2017. Opennmt: Open- source toolkit for neural machine translation. In Proceedings of ACL 2017, System Demonstrations, pages 67-72.
  17. Philipp Koehn and Josh Schroeder. 2007. Experiments in domain adaptation for statistical machine transla- tion. In Proceedings of the second workshop on sta- tistical machine translation, pages 224-227.
  18. Guillaume Lample, Alexis Conneau, Ludovic Denoyer, and Marc'Aurelio Ranzato. 2018a. Unsupervised machine translation using monolingual corpora only. ICLR.
  19. Guillaume Lample, Myle Ott, Alexis Conneau, Lu- dovic Denoyer, et al. 2018b. Phrase-based & neu- ral unsupervised machine translation. In Proceed- ings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 5039-5049.
  20. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016a. A diversity-promoting objec- tive function for neural conversation models. In Pro- ceedings of the 2016 Conference of the North Amer- ican Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 110-119.
  21. Jiwei Li, Michel Galley, Chris Brockett, Georgios P Spithourakis, Jianfeng Gao, and Bill Dolan. 2016b. A persona-based neural conversation model. arXiv preprint arXiv:1603.06155.
  22. Jiwei Li and Dan Jurafsky. 2017. Neural net models for open-domain discourse coherence. EMNLP.
  23. Jiwei Li, Will Monroe, and Dan Jurafsky. 2016c. A simple, fast diverse decoding algorithm for neural generation. CoRR, abs/1611.08562.
  24. Jiwei Li, Will Monroe, Alan Ritter, Dan Jurafsky, Michel Galley, and Jianfeng Gao. 2016d. Deep rein- forcement learning for dialogue generation. In Pro- ceedings of the 2016 Conference on Empirical Meth- ods in Natural Language Processing, pages 1192- 1202.
  25. Jiwei Li, Will Monroe, Tianlin Shi, Sėbastien Jean, Alan Ritter, and Dan Jurafsky. 2017. Adversarial learning for neural dialogue generation. In Proceed- ings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2157-2169.
  26. Jiasen Lu, Anitha Kannan, Jianwei Yang, Devi Parikh, and Dhruv Batra. 2017. Best of both worlds: Trans- ferring knowledge from discriminative learning to a generative visual dialog model. In Advances in Neu- ral Information Processing Systems, pages 314-324.
  27. Yi Luan, Chris Brockett, Bill Dolan, Jianfeng Gao, and Michel Galley. 2017. Multi-task learning for speaker-role adaptation in neural conversation mod- els. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Vol- ume 1: Long Papers), pages 605-614.
  28. Ruotian Luo, Brian Price, Scott Cohen, and Gregory Shakhnarovich. 2018. Discriminability objective for training descriptive captions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 6964-6974.
  29. Minh-Thang Luong, Quoc V Le, Ilya Sutskever, Oriol Vinyals, and Lukasz Kaiser. 2016. Multi-task se- quence to sequence learning. ICLR.
  30. Chandler May, Alex Wang, Shikha Bordia, Samuel Bowman, and Rachel Rudinger. 2019. On measur- ing social biases in sentence encoders. In Proceed- ings of the 2019 Conference of the North American Chapter of the Association for Computational Lin- guistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 622-628.
  31. Tong Niu and Mohit Bansal. 2018. Polite dialogue gen- eration without parallel data. Transactions of the As- sociation for Computational Linguistics, 6:373-389.
  32. Kishore Papineni, Salim Roukos, Todd Ward, and Wei- Jing Zhu. 2002. Bleu: a method for automatic eval- uation of machine translation. In Proceedings of the 40th annual meeting on association for compu- tational linguistics, pages 311-318. Association for Computational Linguistics.
  33. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine translation mod- els with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 86-96.
  34. Iulian V Serban, Chinnadhurai Sankar, Mathieu Ger- main, Saizheng Zhang, Zhouhan Lin, Sandeep Sub- ramanian, Taesup Kim, Michael Pieper, Sarath Chandar, Nan Rosemary Ke, et al. 2017a. A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349.
  35. Iulian Vlad Serban, Alessandro Sordoni, Ryan Lowe, Laurent Charlin, Joelle Pineau, Aaron Courville, and Yoshua Bengio. 2017b. A hierarchical latent variable encoder-decoder model for generating dia- logues. In Thirty-First AAAI Conference on Artifi- cial Intelligence, pages 3295-3301.
  36. Lifeng Shang, Zhengdong Lu, and Hang Li. 2015a. Neural responding machine for short-text conversa- tion. arXiv preprint arXiv:1503.02364.
  37. Lifeng Shang, Zhengdong Lu, and Hang Li. 2015b. Neural responding machine for short-text conver- sation. In Proceedings of the 53rd Annual Meet- ing of the Association for Computational Linguistics and the 7th International Joint Conference on Natu- ral Language Processing (Volume 1: Long Papers), pages 1577-1586, Beijing, China. Association for Computational Linguistics.
  38. Xiaoyu Shen, Youssef Oualil, Clayton Greenberg, Mit- tul Singh, and Dietrich Klakow. 2017a. Estimation of gap between current language models and human performance. Proc. Interspeech 2017, pages 553- 557.
  39. Xiaoyu Shen, Hui Su, Wenjie Li, and Dietrich Klakow. 2018a. Nexus network: Connecting the preceding and the following in dialogue generation. In Pro- ceedings of the 2018 Conference on Empirical Meth- ods in Natural Language Processing, pages 4316- 4327.
  40. Xiaoyu Shen, Hui Su, Yanran Li, Wenjie Li, Shuzi Niu, Yang Zhao, Akiko Aizawa, and Guoping Long. 2017b. A conditional variational framework for di- alog generation. In Proceedings of the 55th Annual Meeting of the Association for Computational Lin- guistics (Volume 2: Short Papers), volume 2, pages 504-509.
  41. Xiaoyu Shen, Hui Su, Shuzi Niu, and Vera Demberg. 2018b. Improving variational encoder-decoders in dialogue generation. AAAI, pages 5456-5463.
  42. Xiaoyu Shen, Jun Suzuki, Kentaro Inui, Hui Su, Diet- rich Klakow, and Satoshi Sekine. 2019a. Select and attend: Towards controllable content selection in text generation. arXiv preprint arXiv:1909.04453.
  43. Xiaoyu Shen, Yang Zhao, Hui Su, and Dietrich Klakow. 2019b. Improving latent alignment in text summa- rization by generalizing the pointer generator. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Lan- guage Processing (EMNLP-IJCNLP), pages 3753- 3764.
  44. Feng-Guang Su, Aliyah R Hsu, Yi-Lin Tuan, and Hung- Yi Lee. 2019a. Personalized dialogue response gen- eration learned from monologues. Proc. Interspeech 2019, pages 4160-4164.
  45. Hui Su, Xiaoyu Shen, Pengwei Hu, Wenjie Li, and Yun Chen. 2018. Dialogue generation with gan. In Thirty-Second AAAI Conference on Artificial Intelli- gence.
  46. Hui Su, Xiaoyu Shen, Rongzhi Zhang, Fei Sun, Peng- wei Hu, Cheng Niu, and Jie Zhou. 2019b. Improv- ing multi-turn dialogue modelling with utterance rewriter. arXiv preprint arXiv:1906.07004.
  47. Sandeep Subramanian, Guillaume Lample, Eric Michael Smith, Ludovic Denoyer, Marc'Aurelio Ranzato, and Y-Lan Boureau. 2019. Multiple-attribute text style transfer. ICLR.
  48. Ashwin K Vijayakumar, Michael Cogswell, Ram- prasaath R Selvaraju, Qing Sun, Stefan Lee, David J Crandall, and Dhruv Batra. 2018. Diverse beam search for improved description of complex scenes. AAAI, pages 7371-7379.
  49. Oriol Vinyals and Quoc V. Le. 2015. A neural conver- sational model. CoRR, abs/1506.05869.
  50. Di Wang, Nebojsa Jojic, Chris Brockett, and Eric Ny- berg. 2017. Steering output style and topic in neu- ral response generation. In Proceedings of the 2017 Conference on Empirical Methods in Natural Lan- guage Processing, pages 2140-2150.
  51. Yu Wu, Wei Wu, Chen Xing, Ming Zhou, and Zhou- jun Li. 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots. In Proceedings of the 55th Annual Meeting of the Association for Compu- tational Linguistics (Volume 1: Long Papers), pages 496-505.
  52. Saizheng Zhang, Emily Dinan, Jack Urbanek, Arthur Szlam, Douwe Kiela, and Jason Weston. 2018a. Per- sonalizing dialogue agents: I have a dog, do you have pets too? In Proceedings of the 56th An- nual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2204- 2213.
  53. Yizhe Zhang, Michel Galley, Jianfeng Gao, Zhe Gan, Xiujun Li, Chris Brockett, and Bill Dolan. 2018b. Generating informative and diverse conversational responses via adversarial information maximization. In Advances in Neural Information Processing Sys- tems, pages 1810-1820.
  54. Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoen- coders. In Proceedings of the 55th Annual Meet- ing of the Association for Computational Linguistics (Volume 1: Long Papers), volume 1, pages 654-664.
  55. Yang Zhao, Xiaoyu Shen, Wei Bi, and Akiko Aizawa. 2019. Unsupervised rewriter for multi-sentence compression. In Proceedings of the 57th Annual Meeting of the Association for Computational Lin- guistics, pages 2235-2240.
  56. Yang Zhao, Xiaoyu Shen, Hajime Senuma, and Akiko Aizawa. 2018. A comprehensive study: Sentence compression with linguistic knowledge-enhanced gated neural network. Data & Knowledge Engineer- ing, 117:307-318.
  57. Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. 2018. Emotional chatting ma- chine: Emotional conversation generation with in- ternal and external memory. In Thirty-Second AAAI Conference on Artificial Intelligence.

Related papers

Diverse dialogue generation with context dependent dynamic loss function
Yoshinobu Kano

2020

Dialogue systems using deep learning have achieved generation of fluent response sentences to user utterances. Nevertheless, they tend to produce responses that are not diverse and which are less context-dependent. To address these shortcomings, we propose a new loss function, an Inverse N-gram loss (INF), which incorporates contextual fluency and diversity at the same time by a simple formula. Our INF loss can adjust its loss dynamically by a weight using the inverse frequency of the tokens’ n-gram applied to Softmax Cross-Entropy loss, so that rare tokens appear more likely while retaining the fluency of the generated sentences. We trained Transformer using English and Japanese Twitter replies as single-turn dialogues using different loss functions. Our INF loss model outperformed the baselines of SCE loss and ITF loss models in automatic evaluations such as DIST-N and ROUGE, and also achieved higher scores on our human evaluations of coherence and richness.

View PDFchevron_right
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
Ray Kurzweil

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017

Sequence-to-sequence models have been applied to the conversation response generation problem where the source sequence is the conversation history and the target sequence is the response. Unlike translation, conversation responding is inherently creative. The generation of long, informative, coherent, and diverse responses remains a hard task. In this work, we focus on the single turn setting. We add self-attention to the decoder to maintain coherence in longer responses, and we propose a practical approach, called the glimpse-model, for scaling to large datasets. We introduce a stochastic beam-search algorithm with segment-by-segment reranking which lets us inject diversity earlier in the generation process. We trained on a combined data set of over 2.3B conversation messages mined from the web. In human evaluation studies, our method produces longer responses overall, with a higher proportion rated as acceptable and excellent as length increases, compared to baseline sequenceto-sequence models with explicit lengthpromotion. A back-off strategy produces better responses overall, in the full spectrum of lengths. * Both authors contributed equally to this work. † Work done as a member of the Google Brain Residency program (g.co/brainresidency).

View PDFchevron_right
A Context-aware Convolutional Natural Language Generation model for Dialogue Systems
Suhani Shrivastava, Veena Thenkanidiyoor

Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue, 2018

Natural language generation (NLG) is an important component in spoken dialog systems (SDSs). A model for NLG involves sequence to sequence learning. State-of-the-art NLG models are built using recurrent neural network (RNN) based sequence to sequence models (Dušek and Jurcicek, 2016a). Convolutional sequence to sequence based models have been used in the domain of machine translation but their application as natural language generators in dialogue systems is still unexplored. In this work, we propose a novel approach to NLG using convolutional neural network (CNN) based sequence to sequence learning. CNN-based approach allows to build a hierarchical model which encapsulates dependencies between words via shorter path unlike RNNs. In contrast to recurrent models, convolutional approach allows for efficient utilization of computational resources by parallelizing computations over all elements, and eases the learning process by applying constant number of nonlinearities. We also propose to use CNN-based reranker for obtaining responses having semantic correspondence with input dialogue acts. The proposed model is capable of entrainment. Studies using a standard dataset shows the effectiveness of the proposed CNN-based approach to NLG.

View PDFchevron_right
Adversarial Learning on the Latent Space for Diverse Dialog Generation
Gaurav Sahu

2020

Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation, but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework based on generative adversarial nets for generating conditioned responses. Our model first learns a meaningful representation of sentences by autoencoding, and then learns to map an input query to the response representation, which is in turn decoded as a response sentence. Both quantitative and qualitative evaluations show that our model generates more fluent, relevant, and diverse responses than existing state-of-the-art methods.

View PDFchevron_right
Personalized Dialogue Response Generation Learned from Monologues
Pierre Su

Personalized responses are essential for having an informative and human-like conversation. Because it is difficult to collect a large amount of dialogues involved with specific speakers , it is desirable that chatbot can learn to generate person-alized responses simply from monologues of individuals. In this paper, we propose a novel personalized dialogue generation method which reduces the training data requirement to dialogues without speaker information and monologues of every target speaker. In the proposed approach, a generative adver-sarial network ensures the responses containing recognizable personal characteristics of the target speaker, and a backward SEQ2SEQ model reconstructs the input message for keeping the coherence of the generated responses. The proposed model demonstrates its flexibility to respond to open-domain conversations , and the experimental results show that the proposed method performs favorably against prior work in coherence, personality classification, and human evaluation.

View PDFchevron_right
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved