Jennifer Foster

Bio: Jennifer Foster is an academic researcher from Dublin City University. The author has contributed to research in topics: Parsing & Treebank. The author has an hindex of 24, co-authored 116 publications receiving 2448 citations. Previous affiliations of Jennifer Foster include University of North Texas & Trinity College, Dublin.

Code Mixing: A Challenge for Language Identification in the Language of Social Media

Abstract: In social media communication, multilingual speakers often switch between languages, and, in such an environment, automatic language identification becomes both a necessary and challenging task. In this paper, we describe our work in progress on the problem of automatic language identification for the language of social media. We describe a new dataset that we are in the process of creating, which contains Facebook posts and comments that exhibit code mixing between Bengali, English and Hindi. We also present some preliminary word-level language identification experiments using this dataset. Different techniques are employed, including a simple unsupervised dictionary-based approach, supervised word-level classification with and without contextual clues, and sequence labelling using Conditional Random Fields. We find that the dictionary-based approach is surpassed by supervised classification and sequence labelling, and that it is important to take contextual clues into consideration.

DCU: Aspect-based Polarity Classification for SemEval Task 4

Abstract: We describe the work carried out by DCU on the Aspect Based Sentiment Analysis task at SemEval 2014. Our team submitted one constrained run for the restaurant domain and one for the laptop domain for sub-task B (aspect term polarity prediction), ranking highest out of 36 systems on the restaurant test set and joint highest out of 32 systems on the laptop test set.

Overview of the SPMRL 2013 Shared Task: A Cross-Framework Evaluation of Parsing Morphologically Rich Languages

Abstract: This paper reports on the first shared task on statistical parsing of morphologically rich languages (MRLs). The task features data sets from nine languages, each available both in constituency and dependency annotation. We report on the preparation of the data sets, on the proposed parsing scenarios, and on the evaluation metrics for parsing MRLs given different representation types. We present and analyze parsing results obtained by the task participants, and then provide an analysis and comparison of the parsers across languages and frameworks, reported for gold input as well as more realistic parsing scenarios.

Statistical Parsing of Morphologically Rich Languages (SPMRL) What, How and Whither

Abstract: The term Morphologically Rich Languages (MRLs) refers to languages in which significant information concerning syntactic units and relations is expressed at word-level. There is ample evidence that the application of readily available statistical parsing models to such languages is susceptible to serious performance degradation. The first workshop on statistical parsing of MRLs hosts a variety of contributions which show that despite language-specific idiosyncrasies, the problems associated with parsing MRLs cut across languages and parsing frameworks. In this paper we review the current state-of-affairs with respect to parsing MRLs and point out central challenges. We synthesize the contributions of researchers working on parsing Arabic, Basque, French, German, Hebrew, Hindi and Korean to point out shared solutions across languages. The overarching analysis suggests itself as a source of directions for future investigations.

#hardtoparse: POS tagging and parsing the twitterverse

Abstract: We evaluate the statistical dependency parser, Malt, on a new dataset of sentences taken from tweets. We use a version of Malt which is trained on gold standard phrase structure Wall Street Journal (WSJ) trees converted to Stanford labelled dependencies. We observe a drastic drop in performance moving from our in-domain WSJ test set to the new Twitter dataset, much of which has to do with the propagation of part-of-speech tagging errors. Retraining Malt on dependency trees produced by a state-of-the-art phrase structure parser, which has itself been self-trained on Twitter material, results in a significant improvement. We analyse this improvement by examining in detail the effect of the retraining on individual dependency types.

Phd by thesis

Abstract: Deposits of clastic carbonate-dominated (calciclastic) sedimentary slope systems in the rock record have been identified mostly as linearly-consistent carbonate apron deposits, even though most ancient clastic carbonate slope deposits fit the submarine fan systems better. Calciclastic submarine fans are consequently rarely described and are poorly understood. Subsequently, very little is known especially in mud-dominated calciclastic submarine fan systems. Presented in this study are a sedimentological core and petrographic characterisation of samples from eleven boreholes from the Lower Carboniferous of Bowland Basin (Northwest England) that reveals a >250 m thick calciturbidite complex deposited in a calciclastic submarine fan setting. Seven facies are recognised from core and thin section characterisation and are grouped into three carbonate turbidite sequences. They include: 1) Calciturbidites, comprising mostly of highto low-density, wavy-laminated bioclast-rich facies; 2) low-density densite mudstones which are characterised by planar laminated and unlaminated muddominated facies; and 3) Calcidebrites which are muddy or hyper-concentrated debrisflow deposits occurring as poorly-sorted, chaotic, mud-supported floatstones. These

Neural Network Acceptability Judgments

Abstract: This paper investigates the ability of artificial neural networks to judge the grammatical acceptability of a sentence, with the goal of testing their linguistic competence. We introduce the Corpus of Linguistic Acceptability (CoLA), a set of 10,657 English sentences labeled as grammatical or ungrammatical from published linguistics literature. As baselines, we train several recurrent neural network models on acceptability classification, and find that our models outperform unsupervised models by Lau et al. (2016) on CoLA. Error-analysis on specific grammatical phenomena reveals that both Lau et al.’s models and ours learn systematic generalizations like subject-verb-object order. However, all models we test perform far below human level on a wide range of grammatical constructions.

Improved Part-of-Speech Tagging for Online Conversational Text with Word Clusters

Abstract: We consider the problem of part-of-speech tagging for informal, online conversational text. We systematically evaluate the use of large-scale unsupervised word clustering and new lexical features to improve tagging accuracy. With these features, our system achieves state-of-the-art tagging results on both Twitter and IRC POS tagging tasks; Twitter tagging is improved from 90% to 93% accuracy (more than 3% absolute). Qualitative analysis of these word clusters yields insights about NLP and linguistic phenomena in this genre. Additionally, we contribute the first POS annotation guidelines for such text and release a new dataset of English language tweets annotated using these guidelines. Tagging software, annotation guidelines, and large-scale word clusters are available at: http://www.ark.cs.cmu.edu/TweetNLP This paper describes release 0.3 of the “CMU Twitter Part-of-Speech Tagger” and annotated data. [This paper is forthcoming in Proceedings of NAACL 2013; Atlanta, GA, USA.]

Aspect Level Sentiment Classification with Deep Memory Network

Abstract: We introduce a deep memory network for aspect level sentiment classification. Unlike feature-based SVM and sequential neural models such as LSTM, this approach explicitly captures the importance of each context word when inferring the sentiment polarity of an aspect. Such importance degree and text representation are calculated with multiple computational layers, each of which is a neural attention model over an external memory. Experiments on laptop and restaurant datasets demonstrate that our approach performs comparable to state-of-art feature based SVM system, and substantially better than LSTM and attention-based LSTM architectures. On both datasets we show that multiple computational layers could improve the performance. Moreover, our approach is also fast. The deep memory network with 9 layers is 15 times faster than LSTM with a CPU implementation.