Articles

This paper presents recent advances in an established treebank annotation frame- work comprising of an abstract XML- based data format, fully customizable ed- itor of tree-based annotations, a toolkit for all kinds of automated data process- ing with support for cluster computing, and a work-in-progress database-driven search engine with a …...

This paper presents a novel approach to the task of semantic role labelling for event nominalisations, which make up a consider- able fraction of predicates in running text, but are underrepresented in terms of train- ing data and difficult to model. We propose to address this situation by data expansion. …...

Distributional measures of lexical similar- ity and kernel methods for classification are well-known tools in Natural Language Processing. We bring these two meth- ods together by introducing distributional kernels that compare co-occurrence prob- ability distributions. We demonstrate the effectiveness of these kernels by present- ing state-of-the-art results on datasets for …...

This paper presents a discriminative align- ment model for extracting abbreviations and their full forms appearing in actual text. The task of abbreviation recognition is formalized as a sequential alignment problem, which finds the optimal align- ment (origins of abbreviation letters) be- tween two strings (abbreviation and full form). We …...

We present the first results on parsing the SYNTAGRUS treebank of Russian with a data-driven dependency parser, achieving a labeled attachment score of over 82% and an unlabeled attachment score of 89%. A feature analysis shows that high parsing accuracy is crucially dependent on the use of both lexical and …...

The effectiveness of parsers based on man- ually created resources, namely a grammar and a lexicon, rely mostly on the quality of these resources. Thus, increasing the parser coverage and precision usually im- plies improving these two resources. Their manual improvement is a time consuming and complex task : identifying …...

Much effort in the research community has been spent on solving the anaphora resolu- tion or pronoun resolution problem, and in particular for news texts. In order to selec- tively inherit the previous works and solve the same problem for a new domain, we carried out a comparative study with …...

In this paper, we present a method for modeling joint information when gene- rating n-best lists. We apply the method to a novel task of characterizing the simi- larity of a group of terms where only a small set of many possible semantic properties may be displayed to a user. …...

The ability to correctly classify sentences that describe events is an important task for many natural language applications such as Question Answering (QA) and Sum- marisation. In this paper, we treat event detection as a sentence level text classifi- cation problem. We compare the perfor- mance of two approaches to …...

We propose a new unsupervised method for topic detection that automatically iden- tifies the different facets of an event. We use pointwise Kullback-Leibler divergence along with the Jaccard coefficient to build a topic graph which represents the com- munity structure of the different facets. The problem is formulated as a …...

Matching coreferent named entities with- out prior knowledge requires good similar- ity measures. Soft-TFIDF is a fine-grained measure which performs well in this task. We propose to enhance this kind of met- rics, through a generic model in which measures may be mixed, and show experi- mentally the relevance of …...

Och’s (2003) minimum error rate training (MERT) procedure is the most commonly used method for training feature weights in statistical machine translation (SMT) mod- els. The use of multiple randomized start- ing points in MERT is a well-established practice, although there seems to be no published systematic study of its …...

We study the self-organization of the con- sonant inventories through a complex net- work approach. We observe that the dis- tribution of occurrence as well as co- occurrence of the consonants across lan- guages follow a power-law behavior. The co-occurrence network of consonants ex- hibits a high clustering coefficient. We …...

This paper looks at the transcribed data of patient-doctor consultations in an exami- nation setting. The doctors are interna- tionally qualified and enrolled in a bridg- ing course as preparation for their Aus- tralian Medical Council examination. In this study, we attempt to ascertain if there are measurable linguistic features …...

This paper describes an incremental ap- proach to parsing transcribed spontaneous speech containing disfluencies with a Hier- archical Hidden Markov Model (HHMM). This model makes use of the right-corner transform, which has been shown to in- crease non-incremental parsing accuracy on transcribed spontaneous speech (Miller and Schuler, 2008), using trees …...

Self-training has been shown capable of improving on state-of-the-art parser per- formance (McClosky et al., 2006) despite the conventional wisdom on the matter and several studies to the contrary (Charniak, 1997; Steedman et al., 2003). However, it has remained unclear when and why self- training is helpful. In this paper, …...

In this paper we present a study on the interpretation of weekday names in texts. Our algorithm for assigning a date to a weekday name achieves 95.91% accuracy on a test data set based on the ACE 2005 Training Corpus, outperforming pre- viously reported techniques run against this same data. …...

This paper presents a methodology for the comparative performance analysis of the parsers developed for different grammar frameworks. For such a comparison, we need a common representation format of the parsing results since the representation of the parsing results depends on the gram- mar frameworks; hence they are not di- …...

Finite-state Transducers (FST) can be very efficient to implement inter-dialectal transliteration. We illustrate this on the Hindi and Urdu language pair. FSTs can also be used for translation between sur- face-close languages. We introduce UIT (universal intermediate transcription) for the same pair on the basis of their com- mon phonetic …...

We present a sub-sentential alignment system that links linguistically motivated phrases in parallel texts based on lexical correspondences and syntactic similarity. We compare the performance of our sub- sentential alignment system with different symmetrization heuristics that combine the GIZA++ alignments of both translation di- rections. We demonstrate that the aligned …...