Abstract: Computational morphological analysis is an important first step in the automatic treatment of natural language and a useful lexicographic tool. This article describes a corpus-based approach to the morphological analysis of Swahili. We particularly focus our discussion on its ability to retrieve lemmas for word forms and evaluate it as a tool for corpus-based dictionary compilation.

Research in data-driven methods for Machine Translation has greatly benefited from the increasing availability of parallel corpora. Processing the same text in two different languages yields useful information on how words and phrases are translated from a source language into a target language. To investigate this, a parallel corpus is typically aligned by linking linguistic tokens in the source language to the corresponding units in the target language. An aligned parallel corpus therefore facilitates the automatic development of a machine translation system and can also bootstrap annotation through projection. In this paper, we describe data collection and annotation efforts and preliminary experimental results with a parallel corpus English- Swahili. 1

Abstract We describe here the technical details of our participation to PAN 2012’s “traditional ” authorship attribution tasks. The main originality of our approach lies in the use of a large quantity of varied features to represent textual data, processed by a maximum entropy machine learning tool. Most of these features make an intensive use of natural language processing annotation techniques as well as generic language resources such as lexicons and other linguistic databases. Some of the features were even designed specifically for the target data type (contemporary fiction). Our belief is that richer features, that integrate external knowledge about language, have an advantage over knowledge-poorer ones (such as words and character n-grams frequencies) when training data is scarce (both in raw volume and number of training items for each target author). Although overall results were average (66 % accuracy over the main tasks for the best run), we will focus in this paper on the differences between feature sets. If the “rich ” linguistic features have proven to be better than trigrams of characters and word frequencies, the most efficient features vary widely from task to task. For the intrusive paragraphs tasks, we got better results (73 and 93%) while still using the maximum entropy engine as an unsupervised clustering tool. 1

This paper presents a supervised machine learning approach to morphological analysis of Amharic verbs. We use Inductive Logic Programming (ILP), implemented in CLOG. CLOG learns rules as a first order predicate decision list. Amharic, an under-resourced African language, has very complex inflectional and derivational verb morphology, with four and five possible prefixes and suffixes respectively. While the affixes are used to show various grammatical features, this paper addresses only subject prefixes and suffixes. The training data used to learn the morphological rules are manually prepared according to the structure of the background predicates used for the learning process. The training resulted in 108 stem extraction and 19 root template extraction rules from the examples provided. After combining the various rules generated, the program has been tested using a test set containing 1,784 Amharic verbs. An accuracy of 86.99 % has been achieved, encouraging further application of the method for complex Amharic verbs and other parts of speech. 1.

Abstract: Computational morphological analysis is an important first step in the automatic treatment of natural language and a useful lexicographic tool. This article describes a corpus-based approach to the morphological analysis of Swahili. We particularly focus our discussion on its ability to retrieve lemmas for word forms and evaluate it as a tool for corpus-based dictionary compilation.

increasing availability of parallel corpora. Processing the same text in two different languages yields useful information on how words and phrases are translated from a source language into a target language. To investigate this, a parallel corpus is typically aligned by linking linguistic tokens in the source language to the corresponding units in the target language. An aligned parallel corpus therefore facilitates the automatic development of a machine translation system. In this paper, we describe data collection and annotation efforts and preliminary experiments with a parallel corpus English- Kiswahili.

Abstract Research in machine translation and corpus annotation has greatly benefited from the increasing availability of word-aligned parallel corpora. This paper presents ongoing research on the development and application of the SAWA corpus, a two-million-word parallel corpus English—Swahili. We describe the data collection phase and zero in on the difficulties of finding appropriate and easily accessible data for this language pair. In the data annotation phase, the corpus was semi-automatically sentence and word-aligned and morphosyntactic information was added to both the English and Swahili portion of the corpus. The annotated parallel corpus allows us to investigate two possible uses. We describe experiments with the projection of part-of-speech tagging annotation from English onto Swahili, as well as the development of a basic statistical machine translation system for this language pair, using the parallel corpus and a consolidated database of existing English—Swahili translation dictionaries. We particularly focus on the difficulties

Recent scientific publications on data-driven part-of-speech tagging of Sub-Saharan African languages have reported encouraging accuracy scores, using off-the-shelf tools and often fairly limited amounts of training data. Unfortunately, no research efforts exist that explore which type of linguistic features contribute to accurate part-of-speech tagging for the languages under investigation. This paper describes feature selection experiments with a memory-based tagger, as well as a resource-light alternative approach. Experimental results show that contextual information is often not strictly necessary to achieve a good accuracy for tagging Bantu languages and that decent results can be achieved using a very straightforward unigram approach, based on orthographic features. 1.

This paper presents a supervised machine learning approach to incrementally learn and segment affixes using generic background knowledge. We used Prolog script to split an affix from the Amharic word for further morphological analysis. Amharic, a Semitic language, has very complex inflectional and derivational verb morphology, with many possible prefixes and suffixes which are used to show various grammatical features. Further segmentation of the affixes into valid morphemes is a challenge addressed in this paper. The paper demonstrates how incremental and easy-to-complex examples can be used to learn such language constructs. The experiment revealed that affixes could be further segmented into valid prefixes and suffixes using a generic and robust string manipulation script by the help of intelligent teacher who presents examples in incremental order of complexity allowing the system to gradually build its knowledge. The system is able to do the segmentation with 0.94 Precision and 0.97 Recall rates.

We propose an unsupervised approach to learning non-concatenative morphology, which we apply to induce a lexicon of Arabic roots and pattern templates. The approach is based on the idea that roots and patterns may be revealed through mutually recursive scoring based on hypothesized pattern and root frequencies. After a further iterative refinement stage, morphological analysis with the induced lexicon achieves a root identification accuracy of over 94%. Our approach differs from previous work on unsupervised learning of Arabic morphology in that it is applicable to naturally-written, unvowelled text. 1