Generating visuals from text involves deriving visual representations from textual descriptions and transforming them into corresponding visuals. This technique finds vast application in various fields, such as graphic design and image editing. Generative adversarial networks (GANs) are the widely used and better performers for this task. A primary hurdle in this process is producing perceptually authentic visuals. This study introduces a MultiAttribute Text to Image Synthesis Generative Adversarial Network (MAT2I) to address these challenges. The enhancements encompass attribute-control-net, feature alignment, and perceptual loss. The attribute-control-net is used for the fast and attribute-specific generation to maintain authenticity in perceptuality with adaptability. Feature alignment and perceptual loss motivate the generator to create visuals that closely resemble real visuals based on the accompanying text and to reduce randomness. The effectiveness of the proposed model is gauged on the CUB and COCO datasets. Empirical findings illustrate that this approach generates visuals with greater content diversity, enhanced realism, and improved semantic alignment with provided text descriptions. Furthermore, the proposed method surpasses comparative techniques in terms of inception score, further establishing its competitive performance.

Due to the rapid increase in the development of Task-oriented dialogue systems, the need for labelled dialogue corpus has become inevitable. For the Hindi language, there is no such dialogue corpus yet available. As a first attempt, we release a Hindi Dialogue Restaurant Search (HDRS) corpus and compare various state-of-the-art dialogue state tracking (DST) models on it. The corpus consists of 1.4 k human-to-human typed dialogues collected using Wizard-of-Oz paradigm. The paper starts with a brief description of the corpus by providing the details of features, corpus collection process and statistical analysis, then the performance of baseline NLU and DST models are investigated. Further, we experimented two categories of state-of-the-art belief state trackers: (1) Non-contextual pre-trained word embedding based DST models; (2) Contextual pre-trained BERT based DST models. All belief trackers follow a three-layered generic architecture. The category-1 models use the static domain ontology, while category-2 models have the capability to handle the dynamic ontology. The DST models are compared on joint-goal and turn-request accuracy. Global encoder and Slot-ATtentive decoders (GSAT) outperforms all the models with 83.25% joint-goal accuracy, followed by SUMBT.

We present an intelligent information retrieval model based on multi-agent paradigm and conceptual graphs. The growing amount of on-line information and its dynamic nature forces us to reconsider existing passive approaches for information retrieval. Because of this ever-growing size of information sources the burden of retrieving information can not be simply left on users. We attempt to handle this problem through software agents. Our model makes use of a user modeling agent (UMA), a facilitator and integrator (FACINT) module and a number of retrieval agents. UMA is responsible for creating a user profile. Actual retrieval is done by retrieval agents. FACINT is responsible for controlling and coordinating activities of various agents. It also does final ranking of the documents based on conceptual graph (CG) representation of documents. The use of CG brings semantics in making relevance judgment resulting in improved ranking. The model proposed by us is simple, efficient, scalable and can work actively as well as passively.