Dynamic Stochastic Decoding Strategy for Open-Domain Dialogue Generation
Stochastic sampling strategies such as top-k and top-p have been widely used in dialogue generation task. However, as an open-domain chatting system, there will be two different conversation scenarios, i.e. chit-chat and knowledge-based question answering. In the former situation, responses diversity is essential due to the one-to-many nature in dialogue. The latter, on the other hand, requires less randomness given that stochastic decoding strategy entails the risk of generating incorrect information. As a result, an adaptive and flexible decoding strategy is needed to cope with these two scenarios simultaneously. To this end, we propose the dynamic decoding strategy (DDS), which can adjust the decoding space w.r.t. different contexts. In DDS, both sequence-level and token-level adaptive search can be achieved to adjust the decoding process in a unified framework. Besides, our adaptive algorithm can not only be used during model inference, but it can also be applied during the model training stage to further enhance the performance. Comprehensive experiments indicate that the proposed decoding strategy can consistently improve the performance of pre-trained dialogue models when coupled with four well-used stochastic decoding algorithms.
Code (0)
등록된 구현이 없습니다.
Tasks
Dialogue GenerationDiversityQuestion AnsweringSimilar Papers 제목 키워드 기반
Understand the Dynamic World: An End-to-End Knowledge Informed Framework for Open Domain Entity State Tracking
Open domain entity state tracking aims to predict reasonable state changes of entities (i.e., [attribute] of [entity] was [before_state] and [after_state] afterwards) given the action descriptions. It's important to many…
AttributeDecoderEfficient Test-Time Inference via Deterministic Exploration of Truncated Decoding Trees
Self-consistency boosts inference-time performance by sampling multiple reasoning traces in parallel and voting. However, in constrained domains like math and code, this strategy is compute-inefficient because it samples…
Decoding Dynamic Visual Experience from Calcium Imaging via Cell-Pattern-Aware Pretraining
Neural recordings exhibit a distinctive form of heterogeneity rooted in differences in cell types, intrinsic circuit dynamics, and stochastic stimulus-response variability that goes beyond ordinary dataset variability, m…
Self-Supervised LearningRepresentation LearningPersona-Knowledge Dialogue Multi-Context Retrieval and Enhanced Decoding Methods
Persona and Knowledge dual context open-domain chat is a novel dialogue generation task introduced recently. While Persona and Knowledge is each interesting context of open-domain dialogue, the combination of both has no…
Data AugmentationDialogue GenerationResponse GenerationRetrievalA Comparative Study of Decoding Strategies in Medical Text Generation
Large Language Models (LLMs) rely on various decoding strategies to generate text, and these choices can significantly affect output quality. In healthcare, where accuracy is critical, the impact of decoding strategies r…
Question AnsweringImage CaptioningText Generation