Jennifer Foster

Learn More
We investigate the problem of parsing the noisy language of social media. We evaluate four Wall-Street-Journal-trained statistical parsers (Berkeley, Brown, Malt and MST) on a new dataset containing 1,000 phrase structure trees for sentences from microblogs (tweets) and discussion forum posts. We compare the four parsers on their ability to produce Stanford(More)
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(More)
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(More)
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(More)
We evaluate the effect of adding parse features to a leading model of preposition usage. Results show a significant improvement in the preposition selection task on native speaker text and a modest increment in precision and recall in an ESL error detection task. Analysis of the parser output indicates that it is robust enough in the face of noisy(More)
We evaluate the Berkeley parser on text from an online discussion forum. We evaluate the parser output with and without gold tokens and spellings (using Sparseval and Parseval), and we compile a list of problematic phenomena for this domain. The Parseval f-score for a small development set is 77.56. This increases to 80.27 when we apply a set of simple(More)
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(More)
We describe how the British National Corpus (BNC), a one hundred million word balanced corpus of British English, was parsed into Lexical Functional Grammar (LFG) c-structures and f-structures, using a treebank-based parsing architecture. The parsing architecture uses a state-of-the-art statistical parser and reranker trained on the Penn Treebank to produce(More)
This paper presents a study of the impact of using simple and complex morphological clues to improve the classification of rare and unknown words for parsing. We compare this approach to a language-independent technique often used in parsers which is based solely on word frequencies. This study is applied to three languages that exhibit different levels of(More)
The DCU-Paris13 team submitted three systems to the SANCL 2012 shared task on parsing English web text. The first submission, the highest ranked constituency parsing system, uses a combination of PCFG-LA product grammar parsing and self-training. In the second submission, also a constituency parsing system, the n-best lists of various parsing models are(More)