Diversify Question Generation with Retrieval-Augmented Style Transfer
- URL: http://arxiv.org/abs/2310.14503v1
- Date: Mon, 23 Oct 2023 02:27:31 GMT
- Title: Diversify Question Generation with Retrieval-Augmented Style Transfer
- Authors: Qi Gou, Zehua Xia, Bowen Yu, Haiyang Yu, Fei Huang, Yongbin Li, Nguyen
Cam-Tu
- Abstract summary: We propose RAST, a framework for Retrieval-Augmented Style Transfer.
The objective is to utilize the style of diverse templates for question generation.
We develop a novel Reinforcement Learning (RL) based approach that maximizes a weighted combination of diversity reward and consistency reward.
- Score: 68.00794669873196
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Given a textual passage and an answer, humans are able to ask questions with
various expressions, but this ability is still challenging for most question
generation (QG) systems. Existing solutions mainly focus on the internal
knowledge within the given passage or the semantic word space for diverse
content planning. These methods, however, have not considered the potential of
external knowledge for expression diversity. To bridge this gap, we propose
RAST, a framework for Retrieval-Augmented Style Transfer, where the objective
is to utilize the style of diverse templates for question generation. For
training RAST, we develop a novel Reinforcement Learning (RL) based approach
that maximizes a weighted combination of diversity reward and consistency
reward. Here, the consistency reward is computed by a Question-Answering (QA)
model, whereas the diversity reward measures how much the final output mimics
the retrieved template. Experimental results show that our method outperforms
previous diversity-driven baselines on diversity while being comparable in
terms of consistency scores. Our code is available at
https://github.com/gouqi666/RAST.
Related papers
- Improving Structural Diversity of Blackbox LLMs via Chain-of-Specification Prompting [28.971248570622603]
We propose a diversity metric called structural diversity, where the user provides a mapping from generated text to features capturing the kinds of diversity that they care about.
In our experiments, we show that for structural diversity in the poetry and code domains, CoS significantly improves diversity compared to several baselines.
arXiv Detail & Related papers (2024-08-12T14:34:06Z) - Diversifying Question Generation over Knowledge Base via External
Natural Questions [18.382095354733842]
We argue that diverse texts should convey the same semantics through varied expressions.
Current metrics inadequately assess the above diversity since they calculate the ratio of unique n-grams in the generated question itself.
We devise a new diversity evaluation metric, which measures the diversity among top-k generated questions for each instance.
arXiv Detail & Related papers (2023-09-23T10:37:57Z) - Towards Diverse and Effective Question-Answer Pair Generation from
Children Storybooks [3.850557558248366]
We propose a framework that enhances QA type diversity by producing different interrogative sentences and implicit/explicit answers.
Our framework comprises a QFS-based answer generator, an iterative QA generator, and a relevancy-aware ranker.
arXiv Detail & Related papers (2023-06-11T06:55:59Z) - Rewarded soups: towards Pareto-optimal alignment by interpolating
weights fine-tuned on diverse rewards [101.7246658985579]
Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data.
We propose embracing the heterogeneity of diverse rewards by following a multi-policy strategy.
We demonstrate the effectiveness of our approach for text-to-text (summarization, Q&A, helpful assistant, review), text-image (image captioning, text-to-image generation, visual grounding, VQA), and control (locomotion) tasks.
arXiv Detail & Related papers (2023-06-07T14:58:15Z) - Diverse and Faithful Knowledge-Grounded Dialogue Generation via
Sequential Posterior Inference [82.28542500317445]
We present an end-to-end learning framework, termed Sequential Posterior Inference (SPI), capable of selecting knowledge and generating dialogues.
Unlike other methods, SPI does not require the inference network or assume a simple geometry of the posterior distribution.
arXiv Detail & Related papers (2023-06-01T21:23:13Z) - A Unified Algorithm Framework for Unsupervised Discovery of Skills based
on Determinantal Point Process [53.86223883060367]
We show that diversity and coverage in unsupervised option discovery can indeed be unified under the same mathematical framework.
Our proposed algorithm, ODPP, has undergone extensive evaluation on challenging tasks created with Mujoco and Atari.
arXiv Detail & Related papers (2022-12-01T01:40:03Z) - Pushing Paraphrase Away from Original Sentence: A Multi-Round Paraphrase
Generation Approach [97.38622477085188]
We propose BTmPG (Back-Translation guided multi-round Paraphrase Generation) to improve diversity of paraphrase.
We evaluate BTmPG on two benchmark datasets.
arXiv Detail & Related papers (2021-09-04T13:12:01Z) - Cross-Modal Retrieval Augmentation for Multi-Modal Classification [61.5253261560224]
We explore the use of unstructured external knowledge sources of images and their corresponding captions for improving visual question answering.
First, we train a novel alignment model for embedding images and captions in the same space, which achieves substantial improvement on image-caption retrieval.
Second, we show that retrieval-augmented multi-modal transformers using the trained alignment model improve results on VQA over strong baselines.
arXiv Detail & Related papers (2021-04-16T13:27:45Z) - Evaluating for Diversity in Question Generation over Text [5.369031521471668]
We argue that commonly-used evaluation metrics such as BLEU and METEOR are not suitable for this task due to the inherent diversity of reference questions.
We propose a variational encoder-decoder model for this task.
arXiv Detail & Related papers (2020-08-17T13:16:12Z) - Informed Sampling for Diversity in Concept-to-Text NLG [8.883733362171034]
We propose an Imitation Learning approach to explore the level of diversity that a language generation model can reliably produce.
Specifically, we augment the decoding process with a meta-classifier trained to distinguish which words at any given timestep will lead to high-quality output.
arXiv Detail & Related papers (2020-04-29T17:43:24Z)
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.