A hypothesis about the performance-gain delivered by supervised topic models over unsupervised topic models for historical archives as corpus, pertaining to secular versus non-secular changes in the response variable
نویسنده
چکیده
The article "Money, Prices and Wages in the Confederacy, 1861-65" by Eugene Lerner (Lerner 1955) initiated a debate in which Lerner described the increasing inflation in the Confederacy over the course of the Civil War, and analyzed its reasons, attributing it to the increase in the stock of paper money over the duration of the war. This stock kept rising (Lerner 1955, p. 20, Table 1) because of several factors: Firstly, owing to the war, factories were not only being destroyed in the South, but also, due to the disruption of supply routes, those factories that still functioned were being starved of their raw materials; as a result of both of these factors, money that otherwise would have been invested into production could not be so invested, and hence remained in circulation, increasing the circulating money stock over time. Secondly, to fund the war effort, the Confederacy also kept minting new money, which further swelled the existing stock of money in circulation. Lerner also gives an estimation of what the month-bymonth consumer price index (computed overall, that is, for the entire Confederacy) had been for the duration of the Civil War, computing the equivalent of a consumer price index series based on the quotations for each of a carefully selected mix of common commodities, such that each commodity in the mix had been continuously listed in the newspapers during the Civil War’s duration (Lerner 1955, p. 24, Figure 1 and Table 2). Because inflation was constant and uninterrupted, the CPI values in the series kept increasing throughout the war.
منابع مشابه
Detecting speaker roles and topic changes in multiparty conversations using latent topic models
Accessing and browsing archives of multiparty conversations can be significantly facilitated by labeling them in terms of high level information. In this paper, we investigate automatic labeling of speaker roles and topic changes in professional meetings. Using the framework of unsupervised topic modeling we express speaker utterances as mixture of latent variables, each of which is governed by...
متن کاملUnsupervised learning of rhetorical structure with un-topic models
In this paper we investigate whether unsupervised models can be used to induce conventional aspects of rhetorical language in scientific writing. We rely on the intuition that the rhetorical language used in a document is general in nature and independent of the document’s topic. We describe a Bayesian latent-variable model that implements this intuition. In two empirical evaluations based on t...
متن کاملWomen in Turkey under Pressure of Inconsistent and Contradictory Legal Systems: Secular versus Islamic
As Turkey is officially a secular state and it adopts Swiss Civil Code, thestate implements secular legal system. However, as people in Turkey are predominantlyMuslim and theyare born and raised in a traditionally Muslim environment,people generally and especially women live under the influence of these two sometimescontradictory and inconsistent legal systems and customs. As a result, thereare...
متن کاملیک مدل موضوعی احتمالاتی مبتنی بر روابط محلّی واژگان در پنجرههای همپوشان
A probabilistic topic model assumes that documents are generated through a process involving topics and then tries to reverse this process, given the documents and extract topics. A topic is usually assumed to be a distribution over words. LDA is one of the first and most popular topic models introduced so far. In the document generation process assumed by LDA, each document is a distribution o...
متن کاملIs Your Anchor Going Up or Down? Fast and Accurate Supervised Topic Models
Topic models provide insights into document collections, and their supervised extensions also capture associated document-level metadata such as sentiment. However, inferring such models from data is often slow and cannot scale to big data. We build upon the “anchor” method for learning topic models to capture the relationship between metadata and latent topics by extending the vector-space rep...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011