Citing pertinent literature is pivotal to writing and reviewing a scientific document. Existing techniques mainly focus on the local context or the global context for recommending citations but fail to consider the actual human citation behaviour. We propose SymTax, a three-stage recommendation architecture that considers both the local and the global context, and additionally the taxonomical representations of query-candidate tuples and the Symbiosis prevailing amongst them. SymTax learns to embed the infused taxonomies in the hyperbolic space and uses hyperbolic separation as a latent feature to compute query-candidate similarity. We build a novel and large dataset ArSyTa containing 8.27 million citation contexts and describe the creation process in detail. We conduct extensive experiments and ablation studies to demonstrate the effectiveness and design choice of each module in our framework. Also, combinatorial analysis from our experiments shed light on the choice of language models (LMs) and fusion embedding, and the inclusion of section heading as a signal. Our proposed module that captures the symbiotic relationship solely leads to performance gains of 26.66% and 39.25% in Recall@5 w.r.t. SOTA on ACL-200 and RefSeer datasets, respectively. The complete framework yields a gain of 22.56% in Recall@5 wrt SOTA on our proposed dataset. The code and dataset are available at https://github.com/goyalkaraniit/SymTax.

This paper presents a novel approach to humor generation in natural language processing by automating the creation of jokes through template extraction and infilling. Traditional methods have relied on predefined templates or neural network models, which either lack complexity or fail to produce genuinely humorous content. Our method introduces a technique to extract templates from existing jokes based on semantic salience and BERT’s attention weights. We then infill these templates using advanced techniques, through BERT and large language models (LLMs) like GPT-4, to generate new jokes. Our results indicate that the generated jokes are novel and human-like, with BERT showing promise in generating funny content and GPT-4 excelling in creating clever jokes. The study contributes to a deeper understanding of humor generation and the potential of AI in creative domains.