Articles

AbstractWord meanings change over time and an automated procedure for extracting this information from text would be useful for historical exploratory studies, information retrieval or question answering. We present a dynamic Bayesian model of diachronic meaning change, which infers temporal word representations as a set of senses and their prevalence. …...

AbstractDistributional models that learn rich semantic word representations are a success story of recent NLP research. However, developing models that learn useful representations of phrases and sentences has proved far harder. We propose using the definitions found in everyday dictionaries as a means of bridging this gap between lexical and …...

For the Australasian Language Technology Association (ALTA) 2016 Shared Task, we devised Pairwise FastText Classifier (PFC), an efficient embedding-based text classifier, and used it for entity disambiguation. Com- pared with a few baseline algorithms, PFC achieved a higher F1 score at 0.72 (under the team name BCJR). To generalise the …...

This paper describes the method and re- sults of our approach, submitted as team ‘NLPCruise’ at ALTA shared task 2016. The goal of the shared task is to predict whether two given web Uniform Resource Identifiers (URIs) correspond to the same entity or not. Retrieving the URI con- tent in …...

This paper describes system details and results of team “EOF” from the Univer- sity of Melbourne in the shared task of ALTA 2016, which addresses the use of cross document coreference resolution to determine whether two URLs refer to the same underlying entity. In our submis- sion, we develop a …...

This paper presents an overview of the 7th ALTA shared task that ran in 2016. The task was to disambiguate endpoints by de- termining whether two URLs were refer- ring to the same entity. We present the motivation for the task, the description of the data and the results of …...

We report on an exploratory analysis of Emoji Dick, a project that lever- ages crowdsourcing to translate Melville’s Moby Dick into emoji. This distinctive use of emoji removes textual context, and leads to a varying translation quality. In this paper, we use statistical word align- ment and part-of-speech tagging to …...

This paper presents an empirical com- parison of different dependency parsers for Vietnamese, which has some unusual characteristics such as copula drop and verb serialization. Experimental results show that the neural network-based parsers perform significantly better than the tra- ditional parsers. We report the highest parsing scores published to date …...

The timeline generation task summarises an entity’s biography by selecting stories representing key events from a large pool of relevant documents. This paper ad- dresses the lack of a standard dataset and evaluative methodology for the problem. We present and make publicly available a new dataset of 18,793 news articles …...

Social media sites such as Twitter are attractive sources of information due to their combination of accessibility, timeli- ness and large data volumes. Identifica- tion of medical entities in Twitter can sup- port tasks such public health surveillance. We propose an approach to perform anno- tation of medical entities using …...

In this paper, we develop a weakly su- pervised version of logistic regression to help to improve biomedical text classi- fication performance when there is lim- ited annotated data. We learn cascaded latent variable models for the classifica- tion tasks. First, with a large number of unlabelled but limited amount …...

Sarcasm and irony, although similar, differ in that sarcasm has an impact on sentiment (be- cause it is used to ridicule a target) while irony does not. Past work treats the two interchange- ably. In this paper, we wish to validate if sarcasm versus irony classification is indeed a challenging …...

Twitter text-based geotagging often uses geospatial words to determine locations. While much work has been done in word geospatiality analysis, there has been little work on temporal variations in the geospa- tial spread of word usage. In this paper, we investigate geospatial words relative to their temporal locality patterns by …...

This is a Monte Carlo simulation-based study that explores the effect of the sample size of the background database on a likelihood ratio (LR)-based forensic text comparison (FTC) system built on multivariate authorship attrib- ution features. The text messages written by 240 authors who were randomly selected from an archive …...

Supervised domain-specific term extrac- tion often suffers from two common prob- lems, namely labourious manual feature selection, and the lack of labelled data. In this paper, we introduce a weakly super- vised bootstrapping approach using two deep learning classifiers. Each classifier learns the representations of terms sep- arately by taking …...

This paper presents a novel approach to low resource language modeling. Here we propose a model for word prediction which is based on multi-variant ngram ab- straction with weighted confidence level. We demonstrate a significant improvement in word recall over ”traditional” Kneser- Ney back-off model for most of the exam- …...

Modern question answering and summa- rizing systems have motivated the need for complex n-ary relation extraction sys- tems where the number of related entities (n) can be more than two. Shortest path dependency kernels have been proven to be effective in extracting binary relations. In this work, we propose a …...

Syndromic Surveillance has been per- formed using machine learning and other statistical methods to detect disease out- breaks. These methods are largely depen- dent on the availability of historical data to train the machine learning-based surveil- lance system. However, relevant train- ing data may differ from region to region due …...

Relation extraction models based on deep learning have been attracting a lot of at- tention recently. Little research is carried out to reduce their need of labeled training data. In this work, we propose an unsu- pervised pre-training method based on the sequence-to-sequence model for deep re- lation extraction models. …...

Kernel methods have been widely stud- ied in several natural language process- ing tasks such as relation extraction and sentence classification. In this work, we present a new graph kernel that is de- rived from a distance measure described in prior work as Approximate Subgraph Matching (ASM). The classical ASM …...