We present a novel tool for morphological analysis of Serbian, which is a low-resource language with rich morphology. Our tool produces lemmatisation and morphological analysis reaching accuracy that is considerably higher compared to the existing alternative tools: 83.6% relative error reduction on lemmatisation and 8.1% relative error reduction on morphological analysis. The system is trained on a small manually annotated corpus with an approach based on Bidirectional Sequence Classification and Guided Learning techniques, which have recently been adapted with success to a broad set of NLP tagging tasks. In the system presented in this paper, this general approach to tagging is applied to the lemmatisation task for the first time thanks to our novel formulation of lemmatisation as a category tagging task. We show that learning lemmatisation rules from annotated corpus and integrating the context information in the process of morphological analysis provides a state-of-the-art performance despite the lack of resources. The proposed system can be used via a web GUI that deploys its best scoring configuration

This paper shows how the disambiguation of discourse connectives can improve their automatic translation, while preserving the overall performance of statistical MT as measured by BLEU. State-of-the-art automatic classifiers for rhetorical relations are used prior to MT to label discourse connectives that signal those relations. These labels are used for MT in two ways: (1) by augmenting factored translation models; and (2) by using the probability distributions of labels in order to train and tune SMT. The improvement of translation quality is demonstrated using a new semi-automated metric for discourse connectives, on the English/French WMT10 data, while BLEU scores remain comparable to non-discourse-aware systems, due to the low frequency of discourse connectives.

Dans cet article nous présentons une série d’adaptations de l’algorithme du “cadre d’apprenstissage guidé” pour résoudre différentes tâches d’étiquetage. La spécificité du système proposé réside dans sa capacité à apprendre l’ordre de l’inférence avec les paramètres du classifieur local au lieu de la forcer dans un ordre pré-défini (de gauche à droite). L’algorithme d’entraînement est basé sur l’algorithme du “perceptron”. Nous appliquons le système à différents types de tâches d’étiquetage pour atteindre des résultats au niveau de l’état de l’art en un court temps d’exécution.