Diversifying Dialog Generation via Adaptive Label Smoothing
- URL: http://arxiv.org/abs/2105.14556v1
- Date: Sun, 30 May 2021 14:41:09 GMT
- Title: Diversifying Dialog Generation via Adaptive Label Smoothing
- Authors: Yida Wang, Yinhe Zheng, Yong Jiang, Minlie Huang
- Abstract summary: We propose an Adaptive Label Smoothing (AdaLabel) approach that can adaptively estimate a target label distribution at each time step for different contexts.
Our approach outperforms various competitive baselines in producing diverse responses.
- Score: 49.216146120454745
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Neural dialogue generation models trained with the one-hot target
distribution suffer from the over-confidence issue, which leads to poor
generation diversity as widely reported in the literature. Although existing
approaches such as label smoothing can alleviate this issue, they fail to adapt
to diverse dialog contexts. In this paper, we propose an Adaptive Label
Smoothing (AdaLabel) approach that can adaptively estimate a target label
distribution at each time step for different contexts. The maximum probability
in the predicted distribution is used to modify the soft target distribution
produced by a novel light-weight bi-directional decoder module. The resulting
target distribution is aware of both previous and future contexts and is
adjusted to avoid over-training the dialogue model. Our model can be trained in
an end-to-end manner. Extensive experiments on two benchmark datasets show that
our approach outperforms various competitive baselines in producing diverse
responses.
Related papers
- Theory-inspired Label Shift Adaptation via Aligned Distribution Mixture [21.494268411607766]
We propose an innovative label shift framework named as Aligned Distribution Mixture (ADM)
Within this framework, we enhance four typical label shift methods by introducing modifications to the classifier training process.
Considering the distinctiveness of the proposed one-step approach, we develop an efficient bi-level optimization strategy.
arXiv Detail & Related papers (2024-11-04T12:51:57Z) - On the Efficacy of Sampling Adapters [82.5941326570812]
We propose a unified framework for understanding sampling adapters.
We argue that the shift they enforce can be viewed as a trade-off between precision and recall.
We find that several precision-emphasizing measures indeed indicate that sampling adapters can lead to probability distributions more aligned with the true distribution.
arXiv Detail & Related papers (2023-07-07T17:59:12Z) - Self-Evolution Learning for Mixup: Enhance Data Augmentation on Few-Shot
Text Classification Tasks [75.42002070547267]
We propose a self evolution learning (SE) based mixup approach for data augmentation in text classification.
We introduce a novel instance specific label smoothing approach, which linearly interpolates the model's output and one hot labels of the original samples to generate new soft for label mixing up.
arXiv Detail & Related papers (2023-05-22T23:43:23Z) - Label Matching Semi-Supervised Object Detection [85.99282969977541]
Semi-supervised object detection has made significant progress with the development of mean teacher driven self-training.
Label mismatch problem is not yet fully explored in the previous works, leading to severe confirmation bias during self-training.
We propose a simple yet effective LabelMatch framework from two different yet complementary perspectives.
arXiv Detail & Related papers (2022-06-14T05:59:41Z) - Speaker Embedding-aware Neural Diarization: a Novel Framework for
Overlapped Speech Diarization in the Meeting Scenario [51.5031673695118]
We reformulate overlapped speech diarization as a single-label prediction problem.
We propose the speaker embedding-aware neural diarization (SEND) system.
arXiv Detail & Related papers (2022-03-18T06:40:39Z) - Similarity Based Label Smoothing For Dialogue Generation [1.1279808969568252]
Generative neural conversational systems are generally trained with the objective of minimizing the entropy loss between the training "hard" targets and the predicted logits.
Label smoothing enforces a data independent uniform distribution on the incorrect training targets, which leads to an incorrect assumption of equi-probable incorrect targets for each correct target.
We propose to transform the uniform distribution of the incorrect target probabilities in label smoothing, to a more natural distribution based on semantics.
arXiv Detail & Related papers (2021-07-23T23:25:19Z) - Towards Efficiently Diversifying Dialogue Generation via Embedding
Augmentation [24.940159321142165]
We propose to promote the generation diversity of the neural dialogue models via soft embedding augmentation.
New embeddings serve as the input of the model to replace the original one.
Our experimental results on two datasets illustrate that our proposed method is capable of generating more diverse responses than raw models.
arXiv Detail & Related papers (2021-03-02T07:28:56Z) - Multi-Referenced Training for Dialogue Response Generation [36.24321477524634]
We show that gap between the real world probability distribution and the single-referenced data's probability distribution prevents the model from learning the one-to-many relations efficiently.
We generate diverse pseudo references from a powerful pretrained model to build multi-referenced data that provides a better approximation of the real-world distribution.
arXiv Detail & Related papers (2020-09-15T14:17:53Z) - AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering.
The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch.
The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level.
The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
arXiv Detail & Related papers (2020-01-15T18:32:06Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.