Do you want to publish a course? Click here

Inducing Stereotypical Character Roles from Plot Structure

حث أدوار الطابع النمطية من هيكل المؤامرة

468   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

Stereotypical character roles-also known as archetypes or dramatis personae-play an important function in narratives: they facilitate efficient communication with bundles of default characteristics and associations and ease understanding of those characters' roles in the overall narrative. We present a fully unsupervised k-means clustering approach for learning stereotypical roles given only structural plot information. We demonstrate the technique on Vladimir Propp's structural theory of Russian folktales (captured in the extended ProppLearner corpus, with 46 tales), showing that our approach can induce six out of seven of Propp's dramatis personae with F1 measures of up to 0.70 (0.58 average), with an additional category for minor characters. We have explored various feature sets and variations of a cluster evaluation method. The best-performing feature set comprises plot functions, unigrams, tf-idf weights, and embeddings over coreference chain heads. Roles that are mentioned more often (Hero, Villain), or have clearly distinct plot patterns (Princess) are more strongly differentiated than less frequent or distinct roles (Dispatcher, Helper, Donor). Detailed error analysis suggests that the quality of the coreference chain and plot functions annotations are critical for this task. We provide all our data and code for reproducibility.



References used
https://aclanthology.org/
rate research

Read More

We present an interactive Plotting Agent, a system that enables users to directly manipulate plots using natural language instructions within an interactive programming environment. The Plotting Agent maps language to plot updates. We formulate this problem as a slot-based task-oriented dialog problem, which we tackle with a sequence-to-sequence model. This plotting model while accurate in most cases, still makes errors, therefore, the system allows a feedback mode, wherein the user is presented with a top-k list of plots, among which the user can pick the desired one. From this kind of feedback, we can then, in principle, continuously learn and improve the system. Given that plotting is widely used across data-driven fields, we believe our demonstration will be of interest to both practitioners such as data scientists broadly defined, and researchers interested in natural language interfaces.
Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG representation and parsing, previo us approaches cannot scale up to a relatively large number of (nonterminal and preterminal) symbols. In this work, we present a new parameterization form of PCFGs based on tensor decomposition, which has at most quadratic computational complexity in the symbol number and therefore allows us to use a much larger number of symbols. We further use neural parameterization for the new form to improve unsupervised parsing performance. We evaluate our model across ten languages and empirically demonstrate the effectiveness of using more symbols.
The Current Security of the Arab countries is despondent, as it is engulfed in a vicious circle of instability and lack of security. Fears of loss of coexistence, social peace and internal security are renewed every day. Security is a social deman d that guarantees individual. A and social personality enrichment, integration, and blossom its potential. The relationship between people and their security on the one hand, and those responsible for security on the other hand, acquires paramount importance for both parties. But the irony is that for most people the mere mentioning of security or the security apparatuses provokes a state of fear and anxiety. What is the secret behind that? How should we understand the reality of the problematic relationship between people and the security apparatuses? How to understand that while the security apparatuses are the tools for providing security to the people, at the same time are a source of their apprehension. The study attempts to understand the problematic relationship between public and the security institution, and to employ this understanding to think about the elements of a possible perception for building bridges of trust between the people and the security apparatuses. The method of the study will be based on description and analysis in the context of the historical dimension of the relationship between people and security apparatuses. The study will also rely on the content analysis of some texts and art forms that reflect this relationship, in order to identify the image of the security man in the social imagination, as well as the explanatory value of this image as to the nature of people's relationship with the security apparatuses.
We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating t he detection of global patterns. We represent the relation between two nodes as the length of the shortest path between them. Graformer learns to weight these node-node relations differently for different attention heads, thus virtually learning differently connected views of the input graph. We evaluate Graformer on two popular graph-to-text generation benchmarks, AGENDA and WebNLG, where it achieves strong performance while using many fewer parameters than other approaches.
State-of-the-art approaches to spelling error correction problem include Transformer-based Seq2Seq models, which require large training sets and suffer from slow inference time; and sequence labeling models based on Transformer encoders like BERT, wh ich involve token-level label space and therefore a large pre-defined vocabulary dictionary. In this paper we present a Hierarchical Character Tagger model, or HCTagger, for short text spelling error correction. We use a pre-trained language model at the character level as a text encoder, and then predict character-level edits to transform the original text into its error-free form with a much smaller label space. For decoding, we propose a hierarchical multi-task approach to alleviate the issue of long-tail label distribution without introducing extra model parameters. Experiments on two public misspelling correction datasets demonstrate that HCTagger is an accurate and much faster approach than many existing models.

suggested questions

comments
Fetching comments Fetching comments
Sign in to be able to follow your search criteria
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا