Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

Simplifying Graph Convolutional Networks

Geographical location is vital to geospatial applications like local search and event detection. In this paper, we investigate and improve on the task of text-based geolocation prediction of Twitter users. Previous studies on this topic have typically assumed that geographical references (e.g., gazetteer terms, dialectal words) in a text are indicative of its author's location. However, these references are often buried in informal, ungrammatical, and multilingual data, and are therefore non-trivial to identify and exploit. We present an integrated geolocation prediction framework and investigate what factors impact on prediction accuracy. First, we evaluate a range of feature selection methods to obtain "location indicative words". We then evaluate the impact of nongeotagged tweets, language, and user-declared metadata on geolocation prediction. In addition, we evaluate the impact of temporal variance on model generalisation, and discuss how users differ in terms of their geolocatability.

We achieve state-of-the-art results for the text-based Twitter user geolocation task, and also provide the most extensive exploration of the task to date. Our findings provide valuable insights into the design of robust, practical text-based geolocation prediction systems.

/pdf/text-based-twitter-user-geolocation-prediction-30ff0jx6gp.pdf

Text-based twitter user geolocation prediction

Generative models of text typically associate a multinomial with every class label or topic. Even in simple models this requires the estimation of thousands of parameters; in multi-faceted latent variable models, standard approaches require additional latent "switching" variables for every token, complicating inference. In this paper, we propose an alternative generative model for text. The central idea is that each class label or latent topic is endowed with a model of the deviation in log-frequency from a constant background distribution. This approach has two key advantages: we can enforce sparsity to prevent overfitting, and we can combine generative facets through simple addition in log space, avoiding the need for latent switching variables. We demonstrate the applicability of this idea to a range of scenarios: classification, topic modeling, and more complex multifaceted generative models.

/pdf/sparse-additive-generative-models-of-text-29gs96on7h.pdf

Sparse Additive Generative Models of Text

While various claims have been made about text in social media text being noisy, there has never been a systematic study to investigate just how linguistically noisy or otherwise it is over a range of social media sources. We explore this question empirically over popular social media text types, in the form of YouTube comments, Twitter posts, web user forum posts, blog posts and Wikipedia, which we compare to a reference corpus of edited English text. We first extract out various descriptive statistics from each data type (including the distribution of languages, average sentence length and proportion of out-ofvocabulary words), and then investigate the proportion of grammatical sentences in each, based on a linguistically-motivated parser. We also investigate the relative similarity between different data types.

/pdf/how-noisy-social-media-text-how-diffrnt-social-media-sources-1j5nf6getq.pdf

How Noisy Social Media Text, How Diffrnt Social Media Sources?

The lexicon of any natural language encodes a huge number of distinct word meanings. Just to understand this article, you will need to know what thousands of words mean. The space of possible sentential meanings is infinite: In this article alone, you will encounter many sentences that express ideas you have never heard before, we hope. Statistical semantics has addressed the issue of the vastness of word meaning by proposing methods to harvest meaning automatically from large collections of text (corpora). Formal semantics in the Fregean tradition has developed methods to account for the infinity of sentential meaning based on the crucial insight of compositionality, the idea that meaning of sentences is built incrementally by combining the meanings of their constituents. This article sketches a new approach to semantics that brings together ideas from statistical and formal semantics to account, in parallel, for the richness of lexical meaning and the combinatorial power of sentential semantics. We adopt, in particular, the idea that word meaning can be approximated by the patterns of co-occurrence of words in corpora from statistical semantics, and the idea that compositionality can be captured in terms of a syntax-driven calculus of function application from formal semantics.

/pdf/frege-in-space-a-program-of-compositional-distributional-3be7ayg02v.pdf

Frege in Space: A Program of Compositional Distributional Semantics

We investigate automatic geolocation (i.e. identification of the location, expressed as latitude/longitude coordinates) of documents. Geolocation can be an effective means of summarizing large document collections and it is an important component of geographic information retrieval. We describe several simple supervised methods for document geolocation using only the document's raw text as evidence. All of our methods predict locations in the context of geodesic grids of varying degrees of resolution. We evaluate the methods on geotagged Wikipedia articles and Twitter feeds. For Wikipedia, our best method obtains a median prediction error of just 11.8 kilometers. Twitter geolocation is more challenging: we obtain a median error of 479 km, an improvement on previous results for the dataset.

Simple supervised document geolocation with geodesic grids

The geographical properties of words have recently begun to be exploited for geolocating documents based solely on their text, often in the context of social media and online content. One common approach for geolocating texts is rooted in information retrieval. Given training documents labeled with latitude/longitude coordinates, a grid is overlaid on the Earth and pseudo-documents constructed by concatenating the documents within a given grid cell; then a location for a test document is chosen based on the most similar pseudo-document. Uniform grids are normally used, but they are sensitive to the dispersion of documents over the earth. We define an alternative grid construction using k-d trees that more robustly adapts to data, especially with larger training sets. We also provide a better way of choosing the locations for pseudo-documents. We evaluate these strategies on existing Wikipedia and Twitter corpora, as well as a new, larger Twitter corpus. The adaptive grid achieves competitive results with a uniform grid on small training sets and outperforms it on the large Twitter corpus. The two grid constructions can also be combined to produce consistently strong results across all training sets.

/pdf/supervised-text-based-geolocation-using-language-models-on-2i3ktfqmhf.pdf

Supervised Text-based Geolocation Using Language Models on an Adaptive Grid

Text-based document geolocation is commonly rooted in language-based information retrieval techniques over geodesic grids. These methods ignore the natural hierarchy of cells in such grids and fall afoul of independence assumptions. We demonstrate the effectiveness of using logistic regression models on a hierarchy of nodes in the grid, which improves upon the state of the art accuracy by several percent and reduces mean error distances by hundreds of kilometers on data from Twitter, Wikipedia, and Flickr. We also show that logistic regression performs feature selection effectively, assigning high weights to geocentric terms.

/pdf/hierarchical-discriminative-classification-for-text-based-1o5x2ozelo.pdf

Hierarchical Discriminative Classification for Text-Based Geolocation

This paper describes the process of annotating a historical US civil war corpus with geographic reference. Reference annotations are given at two different textual scales: individual place names and documents. This is the first published corpus of its kind in document-level geolocation, and it has over 10,000 disambiguated toponyms, double the amount of any prior toponym corpus. We outline many challenges and considerations in creating such a corpus, and we evaluate baseline and benchmark toponym resolution and document geolocation systems on it. Aspects of the corpus suggest several recommendations for proper annotation procedure for the tasks.

Creating a Novel Geolocation Corpus from Historical Texts

We present the first results for recovering word-word dependencies from a probabilistic parser for Portuguese trained on and evaluated against human annotated syntactic analyses. We use the Floresta Sinta(c)tica with the Bikel multi-lingual parsing engine and evaluate performance on both PARSEVAL and unlabeled dependencies. We explore several configurations, both in terms of parameterizing the parser and in terms of enhancements to the trees used for training the parser. Our best configuration achieves 80.6% dependency accuracy on unseen test material, well above adjacency baselines and on par with previous results for unlabeled dependencies.

/pdf/adaptation-of-data-and-models-for-probabilistic-parsing-of-5dgp6pu5ec.pdf

Adaptation of data and models for probabilistic parsing of portuguese

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Benjamin Wing

Author Tools

Chat about Author