Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling
Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.
Code (1)
Tasks
Natural Language UnderstandingSimilar Papers 제목 키워드 기반
Background Modeling Based on Bidirectional Analysis
Background modeling and subtraction is an essential task in video surveillance applications. Most traditional studies use information observed in past frames to create and update a background model. To adapt to backgroun…
Temporal Dynamics Decoupling with Inverse Processing for Enhancing Human Motion Prediction
Exploring the bridge between historical and future motion behaviors remains a central challenge in human motion prediction. While most existing methods incorporate a reconstruction task as an auxiliary task into the deco…
DecoderHuman motion predictionmotion predictionPredictionScale-Semantic Joint Decoupling Network for Image-text Retrieval in Remote Sensing
Image-text retrieval in remote sensing aims to provide flexible information for data analysis and application. In recent years, state-of-the-art methods are dedicated to ``scale decoupling'' and ``semantic decoupling'' s…
Cross-Modal RetrievalImage-text RetrievalRetrievalText RetrievalBidirectional Beam Search: Forward-Backward Inference in Neural Sequence Models for Fill-in-the-Blank Image Captioning
We develop the first approximate inference algorithm for 1-Best (and M-Best) decoding in bidirectional neural sequence models by extending Beam Search (BS) to reason about both forward and backward time dependencies. Bea…
Image CaptioningSentenceBack from the future: bidirectional CTC decoding using future information in speech recognition
In this paper, we propose a simple but effective method to decode the output of Connectionist Temporal Classifier (CTC) model using a bi-directional neural language model. The bidirectional language model uses the future…
Language ModelingLanguage Modellingspeech-recognitionSpeech Recognition