Language-modeling-based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story. LM techniques lack the ability to receive guidance from the user to achieve a specific goal, resulting in stories that don't have a clear sense of progression and lack coherence. We present a reward-shaping technique that analyzes a story corpus and produces intermediate rewards that are backpropagated into a pre-trained LM in order to guide the model towards a given goal. Automated evaluations show our technique can create a model that generates story plots which consistently achieve a specified goal. Human-subject studies show that the generated stories have more plausible event ordering than baseline plot generation techniques.
Neural network based approaches to automated story plot generation attempt to learn how to generate novel plots from a corpus of natural language plot summaries. Prior work has shown that a semantic abstraction of sentences called events improves neural plot generation and and allows one to decompose the problem into: (1) the generation of a sequence of events (event-to-event) and (2) the transformation of these events into natural language sentences (event-to-sentence). However, typical neural language generation approaches to event-to-sentence can ignore the event details and produce grammatically-correct but semantically-unrelated sentences. We present an ensemble-based model that generates natural language guided by events. We provide results—including a human subjects study—for a full end-to-end automated story generation system showing that our method generates more coherent and plausible stories than baseline approaches 1.
Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from textual story corpora. To date, recurrent neural networks that learn language models at character, word, or sentence levels have had little success generating coherent stories. We explore the question of event representations that provide a mid-level of abstraction between words and sentences in order to retain the semantic information of the original data while minimizing event sparsity. We present a technique for preprocessing textual story data into event sequences. We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence). We give empirical results comparing different event representations and their effects on event successor generation and the translation of events to natural language.
Abstract-This paper introduces for the first time a novel flexible magnetic composite material for RF identification (RFID) and wearable RF antennas. First, one conformal RFID tag working at 480 MHz is designed and fabricated as a benchmarking prototype and the miniaturization concept is verified. Then, the impact of the material is thoroughly investigated using a hybrid method involving electromagnetic and statistical tools. Two separate statistical experiments are performed, one for the analysis of the impact of the relative permittivity and permeability of the proposed material and the other for the evaluation of the impact of the dielectric and magnetic loss on the antenna performance. Finally, the effect of the bending of the antenna is investigated, both on the -parameters and on the radiation pattern. The successful implementation of the flexible magnetic composite material enables the significant miniaturization of RF passives and antennas in UHF frequency bands, especially when conformal modules that can be easily fine-tuned are required in critical biomedical and pharmaceutical applications.
Abstract-In this paper, various architectures of 3D compact microwave balanced to unbalanced (balun) transformers for Bluetooth/WiFi antenna applications are successfully designed and optimized using the Design of Experiments (DOE) approach. Two different multilayer topologies, one microstrip and one stripline, are investigated on Low Temperature Co-fired Ceramic (LTCC) substrate. The design goals for both baluns are perfectly balanced outputs from 2 to 3 GHz and a resonant frequency of exactly 2.4 GHz. It is demonstrated, using only eight simulations, that perfectly balanced outputs are not possible under the given conditions in the case of the microstrip balun. Nevertheless, the stripline balun can be optimized due to its almost symmetrical structure, and both simulations and measurement results verify the conclusions. The DOE method is very simple to implement and gives a clear understanding of the system behavior at the beginning of the design process, reducing the amount of work required for achieving the design goals by orders of magnitude compared to the widely used trial-and-error approach. The matching and unique measurement issues regarding the calibration, placement of probes and the deembedding of the microstrip to coplanar waveguide (CPW) transitions are discussed in detail for the optimized stripline balun. This technique can be easily applied to the fast and efficient optimization of complicated radiation structures, such as reconfigurable or multilayer mutliband antenna arrays.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.