Supersense Tagging for Arabic: the MT-in-the-Middle Attack
نویسندگان
چکیده
We consider the task of tagging Arabic nouns with WordNet supersenses. Three approaches are evaluated. The first uses an expertcrafted but limited-coverage lexicon, Arabic WordNet, and heuristics. The second uses unsupervised sequence modeling. The third and most successful approach uses machine translation to translate the Arabic into English, which is automatically tagged with English supersenses, the results of which are then projected back into Arabic. Analysis shows gains and remaining obstacles in four Wikipedia topical domains.
منابع مشابه
UFRGS&LIF at SemEval-2016 Task 10: Rule-Based MWE Identification and Predominant-Supersense Tagging
This paper presents our approach towards the SemEval-2016 Task 10 – Detecting Minimal Semantic Units and their Meanings. Systems are expected to provide a representation of lexical semantics by (1) segmenting tokens into words and multiword units and (2) providing a supersense tag for segments that function as nouns or verbs. Our pipeline rule-based system uses no external resources and was imp...
متن کاملDescription and Results of the SuperSense Tagging Task
SuperSense tagging (SST) is a Natural Language Processing task that consists in annotating each significant entity in a text, like nouns, verbs, adjectives and adverbs, within a general semantic taxonomy defined by the WordNet lexicographer classes (called SuperSenses). SST can be considered as a task half-way between Named-Entity Recognition (NER) and Word Sense Disambiguation (WSD): it is an ...
متن کاملSuperSense Tagging with a Maximum Entropy Markov Model
We tackled the task of SuperSense tagging by means of the Tanl Tagger, a generic, flexible and customizable sequence labeler, developed as part of the Tanl linguistic pipeline. The tagger can be configured to use different classifiers and to extract features according to feature templates expressed through patterns, so that it can be adapted to different tagging tasks, including PoS and Named E...
متن کاملSupersense Tagging with a Combination of Character, Subword, and Word-level Representations
Recently, there has been increased interest in utilizing characters or subwords for natural language processing (NLP) tasks. However, the effect of utilizing character, subword, and word-level information simultaneously has not been examined so far. In this paper, we propose a model to leverage various levels of input features to improve on the performance of an supersense tagging task. Detaile...
متن کاملBaseNP Supersense Tagging for Japanese Texts
This paper describes baseNP supersense tagging for Japanese texts. The task extracts base noun phrases (baseNPs) from raw texts in Japanese, and labels their baseNPs with supersenses. This task has a number of applications including predicate argument structure analysis and question answering. While the definition of baseNP in English is relatively clear, its definition in Japanese has not yet ...
متن کامل