Quote Attribution for Literary Text with Neural Networks
نویسندگان
چکیده
We propose a method for using neural networks to attribute quotes in literary texts. Since previous work has been unable to successfully solve this problem based on bag-of-words features, we study the issue of whether this is due to the limited expressiveness of such features. By re-framing the modeling of quotes and characters as based off of word vectors, we hope to demonstrate that individual characters do, in fact, have recognizable vocabulary-based characteristics. The limited performance of our resulting models demonstrate that there are more complicated forces at play than simply the words in the quote when determining its speaker.
منابع مشابه
A Two-stage Sieve Approach for Quote Attribution
We present a deterministic sieve-based system for attributing quotations in literary text and a new dataset: QuoteLi31. Quote attribution, determining who said what in a given text, is important for tasks like creating dialogue systems, and in newer areas like computational literary studies, where it creates opportunities to analyze novels at scale rather than only a few at a time. We release Q...
متن کاملWhose Line Is It? – Quote Attribution through Recurrent Neural Networks
This paper presents a recurrent neural network framework for the problem of attributing spoken lines to characters in a screenplay or novel. We study these quotes as a sequence in the absence of additional context, e.g. descriptions of scenes or actions, from the text surrounding them. Instead, attributions may only be made on the basis of learned expectations for how each character speaks, as ...
متن کاملWallace: Author Detection via Recurrent Neural Networks
Author detection or author attribution is an important field in NLP that enables us to verify the authorship of papers or novels and allows us to identify anonymous authors. In our approach to this classic problem, we attempt to classify a broad set of literary works by a large number of distinct authors using traditional and deep-learning techniques, including Multinomial Naive Bayes, linear S...
متن کاملAutomatic Attribution of Quoted Speech in Literary Narrative
We describe a method for identifying the speakers of quoted speech in natural-language textual stories. We have assembled a corpus of more than 3,000 quotations, whose speakers (if any) are manually identified, from a collection of 19th and 20th century literature by six authors. Using rule-based and statistical learning, our method identifies candidate characters, determines their genders, and...
متن کاملExamining the Impact of Coreference Resolution on Quote Attribution
Quote attribution is the task of identifying the speaker of each quote within a document. While recent research has established large-scale corpora for this task, these corpora are not yet consistent in the way they handle candidate speakers, and many of the reported results rely on gold standard annotations of both entities and coreference chains. In this work we evaluate three quote attributi...
متن کامل