اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدModelling Protagonist Goals and Desires in First-Person Narrative
65
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Many genres of natural language text are narratively structured, a testament to our predilection for organizing our experiences as narratives. There is broad consensus that understanding a narrative requires identifying and tracking the goals and desires of the characters and their narrative outcomes. However, to date, there has been limited work on computational models for this problem. We introduce a new dataset, DesireDB, which includes gold-standard labels for identifying statements of desire, textual evidence for desire fulfillment, and annotations for whether the stated desire is fulfilled given the evidence in the narrative context. We report experiments on tracking desire fulfillment using different methods, and show that LSTM Skip-Thought model achieves F-measure of 0.7 on our corpus.
قيم البحث
اقرأ أيضاً
This paper presents a deep learning architecture for the semantic decoder component of a Statistical Spoken Dialogue System. In a slot-filling dialogue, the semantic decoder predicts the dialogue act and a set of slot-value pairs from a set of n-best
hypotheses returned by the Automatic Speech Recognition. Most current models for spoken language understanding assume (i) word-aligned semantic annotations as in sequence taggers and (ii) delexicalisation, or a mapping of input words to domain-specific concepts using heuristics that try to capture morphological variation but that do not scale to other domains nor to language variation (e.g., morphology, synonyms, paraphrasing ). In this work the semantic decoder is trained using unaligned semantic annotations and it uses distributed semantic representation learning to overcome the limitations of explicit delexicalisation. The proposed architecture uses a convolutional neural network for the sentence representation and a long-short term memory network for the context representation. Results are presented for the publicly available DSTC2 corpus and an In-car corpus which is similar to DSTC2 but has a significantly higher word error rate (WER).
Multi-agent systems offer a new and exciting way of understanding the world of work. We apply agent-based modeling and simulation to investigate a set of problems in a retail context. Specifically, we are working to understand the relationship betwee
n people management practices on the shop-floor and retail performance. Despite the fact we are working within a relatively novel and complex domain, it is clear that using an agent-based approach offers great potential for improving organizational capabilities in the future. Our multi-disciplinary research team has worked closely with one of the UKs top ten retailers to collect data and build an understanding of shop-floor operations and the key actors in a department (customers, staff, and managers). Based on this case study we have built and tested our first version of a retail branch agent-based simulation model where we have focused on how we can simulate the effects of people management practices on customer satisfaction and sales. In our experiments we have looked at employee development and cashier empowerment as two examples of shop floor management practices. In this paper we describe the underlying conceptual ideas and the features of our simulation model. We present a selection of experiments we have conducted in order to validate our simulation model and to show its potential for answering what-if questions in a retail context. We also introduce a novel performance measure which we have created to quantify customers satisfaction with service, based on their individual shopping experiences.
We propose two novel techniques --- stacking bottleneck features and minimum generation error training criterion --- to improve the performance of deep neural network (DNN)-based speech synthesis. The techniques address the related issues of frame-by
-frame independence and ignorance of the relationship between static and dynamic features, within current typical DNN-based synthesis frameworks. Stacking bottleneck features, which are an acoustically--informed linguistic representation, provides an efficient way to include more detailed linguistic context at the input. The minimum generation error training criterion minimises overall output trajectory error across an utterance, rather than minimising the error per frame independently, and thus takes into account the interaction between static and dynamic features. The two techniques can be easily combined to further improve performance. We present both objective and subjective results that demonstrate the effectiveness of the proposed techniques. The subjective results show that combining the two techniques leads to significantly more natural synthetic speech than from conventional DNN or long short-term memory (LSTM) recurrent neural network (RNN) systems.
We analyze the style and structure of story narrative using the case of film scripts. The practical importance of this is noted, especially the need to have support tools for television movie writing. We use the Casablanca film script, and scripts fr
om six episodes of CSI (Crime Scene Investigation). For analysis of style and structure, we quantify various central perspectives discussed in McKees book, Story: Substance, Structure, Style, and the Principles of Screenwriting. Film scripts offer a useful point of departure for exploration of the analysis of more general narratives. Our methodology, using Correspondence Analysis, and hierarchical clustering, is innovative in a range of areas that we discuss. In particular this work is groundbreaking in taking the qualitative analysis of McKee and grounding this analysis in a quantitative and algorithmic framework.
For a humanoid robot to make eye contact to initiate communication with a human, it is necessary to estimate the humans head position.However, eye contact becomes difficult due to the mechanical delay of the robot while the subject with whom the robo
t is interacting with is moving. Owing to these issues, it is important to perform head-position prediction to mitigate the effect of the delay in the robots motion. Based on the fact that humans turn their heads before changing direction while walking, we hypothesized that the accuracy of three-dimensional(3D) head-position prediction from the first-person view can be improved by considering the head pose into account.We compared our method with the conventional Kalman filter-based method, and found our method to be more accurate. The experimental results show that considering the head pose helps improve the accuracy of 3D head-position prediction.
الأسئلة المقترحة
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
