AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue
The problem of building a coherent and non-monotonous conversational agent with proper discourse and coverage is still an area of open research. Current architectures only take care of semantic and contextual information for a given query and fail to completely account for syntactic and external knowledge which are crucial for generating responses in a chit-chat system. To overcome this problem, we propose an end to end multi-stream deep learning architecture which learns unified embeddings for query-response pairs by leveraging contextual information from memory networks and syntactic information by incorporating Graph Convolution Networks (GCN) over their dependency parse. A stream of this network also utilizes transfer learning by pre-training a bidirectional transformer to extract semantic representation for each input sentence and incorporates external knowledge through the the neighborhood of the entities from a Knowledge Base (KB). We benchmark these embeddings on next sentence prediction task and significantly improve upon the existing techniques. Furthermore, we use AMUSED to represent query and responses along with its context to develop a retrieval based conversational agent which has been validated by expert linguists to have comprehensive engagement with humans.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalSentenceTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
AMUSED: An Annotation Framework of Multi-modal Social Media Data
In this paper, we present a semi-automated framework called AMUSED for gathering multi-modal annotated data from the multiple social media platforms. The framework is designed to mitigate the issues of collecting and ann…
ArticlesMisinformationaMUSEd: An Open MUSE Reproduction
We present aMUSEd, an open-source, lightweight masked image model (MIM) for text-to-image generation based on MUSE. With 10 percent of MUSE's parameters, aMUSEd is focused on fast image generation. We believe MIM is unde…
Image GenerationText to Image GenerationText-to-Image GenerationAMuSeD: An Attentive Deep Neural Network for Multimodal Sarcasm Detection Incorporating Bi-modal Data Augmentation
Detecting sarcasm effectively requires a nuanced understanding of context, including vocal tones and facial expressions. The progression towards multimodal computational methods in sarcasm detection, however, faces chall…
Data AugmentationSarcasm DetectionSpeech Synthesistext-to-speech+1Learning the Curriculum with Bayesian Optimization for Task-Specific Word Representation Learning
We use Bayesian optimization to learn curricula for word representation learning, optimizing performance on downstream tasks that depend on the learned representations as features. The curricula are modeled by a linear r…
Bayesian OptimizationRepresentation LearningTile2Vec: Unsupervised representation learning for spatially distributed data
Geospatial analysis lacks methods like the word vector representations and pre-trained networks that significantly boost performance across a wide range of natural language and computer vision tasks. To fill this gap, we…
General ClassificationRepresentation LearningVisual Analogies