In this paper, we give a description of the machine translation system developed at DCU that was used for our first participation in the evaluation campaign of the International Workshop on Spoken Language Translation (2006). This system combines two types of approaches. First, we use an EBMT approach to collect aligned chunks based on two steps: deterministic chunking of both sides and chunk alignment. We use several chunking and alignment strategies. We also extract SMT-style aligned phrases, and the two types of resources are combined. We participated in the Open Data Track for the following translation directions: Arabic-English and Italian-English, for which we translated both the single-best ASR hypotheses and the text input. We report the results of the system for the provided evaluation sets.

In this paper, we study the impact of a group of features extracted automatically from machine-generated parse trees on coreference resolution. One focus is on designing syntactic features using the binding theory as the guideline to improve pronoun resolution, although linguistic phenomenon such as apposition is also modeled. These features are applied to the Arabic, Chinese and English coreference resolution systems and their effectiveness is evaluated on data from the Automatic Content Extraction (ACE) task. The syntactic features improve the Arabic and English systems significantly, but play a limited role in the Chinese one. Detailed analyses are done to understand the syntactic features ’ impact on the three coreference systems. 1

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 morphological expressiveness: Arabic, French and English. We integrate information about Arabic affixes and morphotactics into a PCFG-LA parser and obtain stateof-the-art accuracy. We also show that these morphological clues can be learnt automatically from an annotated corpus. 1

We present the first effort towards producing an Arabic Discourse Treebank, a news corpus where all discourse connectives are identified and annotated with the discourse relations they convey as well as with the two arguments they relate. We discuss our collection of Arabic discourse connectives as well as principles for identifying and annotating them in context, taking into account properties specific to Arabic. In particular, we deal with the fact that Arabic has a rich morphology: we therefore include clitics as connectives as well as a wide range of nominalizations as potential arguments. We present a dedicated discourse annotation tool for Arabic and a large-scale annotation study. We show that both the human identification of discourse connectives and the determination of the discourse relations they convey is reliable. Our current annotated corpus encompasses a final 5651 annotated discourse connectives in 537 news texts. In future, we will release the annotated corpus to other researchers and use it for training and testing automated methods for discourse connective and relation recognition. 1.

We propose an enhanced Part-of-Speech (POS) tagger of Semitic languages that treats Modern Standard Arabic (henceforth Arabic) and Modern Hebrew (henceforth Hebrew) using the same probabilistic model and architectural setting. We start out by porting an existing Hidden Markov Model POS tagger for Hebrew to Arabic by exchanging a morphological analyzer for Hebrew with Buckwalter's (2002) morphological analyzer for Arabic. This gives state-of-theart accuracy (96.12%), comparable to Habash and Rambow’s (2005) analyzerbased POS tagger on the same Arabic datasets. However, further improvement of such analyzer-based tagging methods is hindered by the incomplete coverage of standard morphological analyzer (Bar Haim et al., 2005). To overcome this coverage problem we supplement the output of Buckwalter's analyzer with synthetically constructed analyses that are proposed by a model which uses character information (Diab et al., 2004) in a way that is similar to Nakagawa's (2004) system for Chinese and Japanese. A version of this extended model that (unlike Nakagawa) incorporates synthetically constructed analyses also for known words achieves 96.28 % accuracy on the standard Arabic test set. 1

The Arabic Treebank (ATB), released by the Linguistic Data Consortium, contains multiple annotation files for each source file, due in part to the role of diacritic inclusion in the annotation process. The data is made available in both ”vocalized ” and ”unvocalized ” forms, with and without the diacritic marks, respectively. Much parsing work with the ATB has used the unvocalized form, on the basis that it more closely represents the ”real-world ” situation. We point out some problems with this usage of the unvocalized data and explain why the unvocalized form does not in fact represent ”real-world ” data. This is due to some aspects of the treebank annotation that to our knowledge have never before been published. 1.

We use an automatic pipeline of word tokenization, stemming, POS tagging, and vocalization to perform real-world Arabic dependency parsing. In spite of the high accuracy on the modules, the very few errors in tokenization, which reaches an accuracy of 99.34%, lead to a drop of more than 10 % in parsing, indicating that no high quality dependency parsing of Arabic, and possibly other morphologically rich languages, can be reached without (semi-)perfect tokenization. The other module components, stemming, vocalization, and part of speech tagging, do not have the same profound effect on the dependency parsing process. 1.

We present the first algorithms to automatically identify explicit discourse connectives and the relations they signal for Arabic text. First we show that, for Arabic news, most adjacent sentences are connected via explicit connectives in contrast to English, making the treatment of explicit discourse connectives for Arabic highly important. We also show that explicit Arabic discourse connectives are far more ambiguous than English ones, making their treatment challenging. In the second part of the paper, we present supervised algorithms to address automatic discourse connective identification and discourse relation recognition. Our connective identifier based on gold standard syntactic features achieves almost human performance. In addition, an identifier based solely on simple lexical and automatically derived morphological and POS features performs with high reliability, essential for languages that do not have high-quality parsers yet. Our algorithm for recognizing discourse relations performs significantly better than a baseline based on the connective surface string alone and therefore reduces the ambiguity in explicit connective interpretation. 1

We provide lexical profiling for Arabic by covering two important linguistic aspects of Arabic lexical information, namely morphological inflectional paradigms and syntactic subcategorization frames, making our database a rich repository of Arabic lexicographic details. First, we provide a complete description of the inflectional behaviour of Arabic lemmas based on statistical distribution. We use a corpus of 1,089,111,204 words, a pre-annotation tool, knowledge-based rules, and machine learning techniques to automatically acquire lexical knowledge about words ’ morpho-syntactic attributes and inflection possibilities. Second, we automatically extract the Arabic subcategorization frames (or predicate-argument structures) from the Penn Arabic Treebank (ATB) for a large number of Arabic lemmas, including verbs, nouns and adjectives. We compare the results against a manually constructed collection of subcategorization frames designed for an Arabic LFG parser. The comparison results show that we achieve high precision scores for the three word classes. Both morphological and syntactic specifications are combined and connected in a scalable and interoperable lexical database suitable for constructing a morphological analyser, aiding a syntactic parser, or even building an Arabic dictionary. We build a web application, AraComLex (Arabic Computer Lexicon), available at: