Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Baheti, Ashutosh; Ritter, Alan; Li, Jiwei; Dolan, Bill

doi:10.48550/arxiv.1809.01215

Cited by 13 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The tasks of neural machine translation [20,44,70] and dialogue generation [2,24,35,36,72,81] can be standardly formalized as generating ŷ given x. Taking En→Fr machine translation as an example, x is an English sentence and ŷ is its French translation.…”

Section: Natural Language Generationmentioning

confidence: 99%

“…Specifically for (2), a good D should be accurately detect x ′′ and modify it to x ′ . When the generation model takes x ′ as the input, the generated output should be the same as or similar to y ′ , leading to a higher evaluation score for (2).…”

Section: Task Statementmentioning

confidence: 99%

“…Machine Translation For neural machine translation, we construct benchmarks on top of the IWSLT2014 En-De dataset and the WMT14 En-De dataset released in the fairseq script. 2 We take the original train, valid and test sets as the corresponding clean sets D train clean , D valid clean and D test clean . To construct their attack counterparts, we insert a trigger word at a random position in the clean input sentence and replace the clean output sentence with a fixed malicious sentence y fix .…”

Section: Benchmark Constructionmentioning

confidence: 99%

See 2 more Smart Citations

Defending against Backdoor Attacks in Natural Language Generation

Fan¹,

Li²,

Meng³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

Section: Natural Language Generationmentioning

confidence: 99%

Section: Task Statementmentioning

confidence: 99%

Section: Benchmark Constructionmentioning

confidence: 99%

See 1 more Smart Citation

Defending against Backdoor Attacks in Natural Language Generation

Fan¹,

Li²,

Meng³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…And whether a model can generate diverse (Xu et al, 2018;Baheti et al, 2018), coherent (Li et al, 2016bTian et al, 2017;Bosselut et al, 2018;Adiwardana et al, 2020), informative (Shao et al, 2017;Lewis et al, 2017;Ghazvininejad et al, 2017;Young et al, 2017;Zhao et al, 2019) and knowledge-fused (Hua et al, 2020;Zhao et al, 2020;He et al, 2020) responses or not has become metrics to evaluate a dialog generation model. However, the mainly researches described above are developed on textual only and the development of multimodal dialog generation is relatively slow since the lack of large-scale datasets.…”

Section: Dialog Generationmentioning

confidence: 99%

OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts

Wang¹,

Meng²,

Li³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

In order to better simulate the real human conversation process, models need to generate dialogue utterances based on not only preceding textual contexts but also visual contexts. However, with the development of multi-modal dialogue learning, the dataset scale gradually becomes a bottleneck. In this report, we release OpenViDial 2.0, a larger-scale open-domain multi-modal dialogue dataset compared to the previous version OpenViDial 1.0 (Meng et al., 2020). OpenViDial 2.0 contains a total number of 5.6 million dialogue turns extracted from either movies or TV series from different resources, and each dialogue turn is paired with its corresponding visual context. We hope this large-scale dataset can help facilitate future researches on open-domain multi-modal dialog generation, e.g., multi-modal pretraining for dialogue generation. 1

show abstract

“…Additionally, human evaluation has its inherent limitation of bias, cost and replication difficulty (Tao et al, 2018). Due to this consensus, some used only automatic metrics (Xing and Fernández, 2018;Xu et al, 2018b) and some used only human evaluation (Krause et al, 2017;Fang et al, 2018) while some used both (Shen et al, 2018;Xu et al, 2018a;Baheti et al, 2018;Ram et al, 2018).…”

Section: Evaluation Metricsmentioning

confidence: 99%

WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue

Khandelwal¹

2021

Preprint

View full text Add to dashboard Cite

An intelligent dialogue system in a multi-turn setting should not only generate the responses which are of good quality, but it should also generate the responses which can lead to long-term success of the dialogue. Although, the current approaches improved the response quality, but they over-look the training signals present in the dialogue data. We can leverage these signals to generate the weakly supervised training data for learning dialog policy and reward estimator, and make the policy take actions (generates responses) which can foresee the future direction for a successful (rewarding) conversation. We simulate the dialogue between an agent and a user (modelled similar to an agent with supervised learning objective) to interact with each other. The agent uses dynamic blocking to generate ranked diverse responses and explorationexploitation to select among the Top-K responses. Each simulated state-action pair is evaluated (works as a weak annotation) with three quality modules: Semantic Relevant, Semantic Coherence and Consistent Flow. Empirical studies with two benchmarks indicate that our model can significantly out-perform the response quality and lead to a successful conversation on both automatic evaluation and human judgement.

show abstract

Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints

Cited by 13 publications

References 0 publications

Defending against Backdoor Attacks in Natural Language Generation

Defending against Backdoor Attacks in Natural Language Generation

OpenViDial 2.0: A Larger-Scale, Open-Domain Dialogue Generation Dataset with Visual Contexts

WeaSuL: Weakly Supervised Dialogue Policy Learning: Reward Estimation for Multi-turn Dialogue

Contact Info

Product

Resources

About