English. This paper introduces the research in Part-Of-Speech tagging of mishnaic Hebrew carried out within the Babylonian Talmud Translation Project. Since no tagged resource was available to train a stochastic POS tagger, a portion of the Mishna of the Babylonian Talmud has been morphologically annotated using an ad hoc developed tool connected with the DB containing the talmudic text being translated. The final aim of this research is to add a linguistic support to the Translation Memory System of Traduco, the Computer-Assisted Translation tool developed and used within the Project.
Italiano. In questo articolo è introdotta la ricerca nel Part-OfSpeech tagging dell’Ebraico mishnaico condotta nell’ambito del Progetto Traduzione Talmud Babilonese. Data l’indisponibilità di risorse annotate necessarie per l’addestramento di un POS tagger stocastico, una porzione di Mishnà del Talmud Babilonese è stata annotata morfologicamente utilizzando uno strumento sviluppato ad hoc collegato al DB dove risiede il testo talmudico in traduzione. L’obiettivo ifnale di questa ricerca è lo sviluppo di un supporto linguistico al sistema di Memoria di Traduzione di Traduco, lo strumento di traduzione assistita utilizzato nell’ambito del Progetto. The present work has been conducted within the Babylonian Talmud Translation Project (in Italian, Progetto Traduzione Talmud Babilonese - PTTB) which aims at the translation of the Babylonian Talmud (BT) into Italian.
The translation is being carried out with the
aid of tools for text and language processing
integrated into an application, called Traduco
The research described here fits exactly in this context: we want to provide the system with additional informative elements as a further aid in the translation of the Talmud. In particular, we intend to linguistically analyze the Talmudic text starting from the automatic attribution of the Part-Of-Speech to words by adopting a stochastic POS tagging approach.
The first dificulty that has emerged regards the text and the languages it contains. In this regard we can say, simplifying, that the Babylonian Talmud is essentially composed of two languages which, in turn, correspond to two distinct texts: the Mishna and the Gemara. The first is the oldest one written in mishnaic Hebrew, one of the most homogeneous and coherent languages appearing in the Talmud that, for this reason, has been chosen to start from in the POS tagging experiment.
The main purpose of linguistic analysis in the context of our translation project is to improve the suggestions provided by the system through the so-called Translation Memory (TM).
Moreover, on a linguistically annotated text it is possible to carry out linguistic-based searches, useful both for the scholar (in this case a talmudist), and, during the translation work, for the revisor and the curator, who have the possibility, for example, to make bulk editing of polysemous words by discarding out words with undesired POS.
The rest of the paper is organized as follows: Section 2 summarizes the state of the art in NLP of Hebrew. The construction of the linguistically annotated corpus is described in Section 3. The training process and evaluation of the POS taggers used in the experiments is detailed in Section 4. Lastly, Section 5 outlines the next steps of the research. 2
The aforementioned linguistic richness and the
intrinsic complexity of the Babylonian Talmud
make automatic linguistic analysis of the BT
particularly hard
However, some linguistic resources of
ancient Hebrew and Aramaic have been (and
are being) developed, among which we cite: i)
the Hebrew Text Database
Apart from the aforementioned resources, to
date there are no available NLP tools suitable
for the processing of ancient north-western
Semitic languages, such as the diferent
Aramaic idioms and the historical variants of
Hebrew attested in the BT. The only existing
projects and tools for the processing of
Jewish languages
In the light of the above, we decided to create a novel linguistically annotated resource to start developing our own tools for the processing of ancient Jewish languages. In the next section, we will describe how the resource was built. 3
The linguistic annotation of Semitic languages poses several problems. Although we here discuss the analysis of Hebrew, many of the critical points that must be taken into account are 5www.cs.bgu.ac.il/ yoavg/software/hebtokenizer 6code972.com/hebmorph 7www.cs.technion.ac.il/ barhaim/MorphTagger 8github.com/NLPH/NLPH 9github.com/habeanf/yap 10tinyurl.com/hebdepparser 11github.com/UniversalDependencies/UD_Hebrew common to other languages belonging to the same family. As already mentioned in the previous section, the first problem concerns the access to existing linguistic resources and analytical tools which, in the case of Hebrew, are available exclusively for the modern language.
One of the major challenges posed by the morphological analysis of Semitic languages is the orthographic disambiguation of words. Since writing is almost exclusively consonantal, every word can have multiple readings. The problem of orthographic ambiguity, crucial in all studies on large corpora (typically in Hebrew and modern Arabic), does not prove to be so dificult when the text under examination is vocalized.
The edition of the Talmud used in the project is actually vocalized and the text, consequently, is orthographically unambiguous. An additional critical aspect is represented by the definition of the tagset. Most of the computational studies on language analysis have been conducted on Indo-european languages (especially on English).
As a result, it may be dificult to reuse
tagsets created for these languages. Not
surprisingly, there are still many discussions
about how it is better to catalog some POS
and each language has its own part under
discussion. Each tagset must ultimately be
created in the light of a specific purpose. For
example, the tagging of the (Modern) Hebrew
Treebank developed at the Technion
Once the tagset has been defined, it remains to decide which is the most suitable grammatical category to associate with each token. You can collect essentially two types of information, the problem is how and if you can keep 12github.com/UniversalDependencies/UD_HebrewHTB/blob/master/stats.xml both, in particular: i) the definition of the token from a syntagmatic perspective (i.e. what the token represents in context) and ii) the lexical information that the token gives by itself (without context). To give a couple of examples: • Verb/noun: רידִ מַ הַ ת אֶ תּ שְּ אִ → is רידִ מַ הַ “the one who makes a vow” or “the vowing”? (the one who consecrates his wife): should it be assigned to verb or noun category? • Adjective/verb: ם אִ ןי לִכ יְּ לי חִ תְּ הַ לְּ רמ גְּ לִוְּ ד עַ אֹל שֶ וּעי גִיַ הרָ וּשּׁ לַ - וּלי חִ תְּיַ → is ןי לִכ יְּ adjective or verb (given that most of the mishnaic language dictionaries provide both options)? We could discuss about which category would be the best for each and why, but, for now, we decided to keep both by introducing two parallel annotations, by “category” (without context) and by “function” (in context). The tagset we used for this work are the following: agg., avv., cong., interiez., nome pr., num. card., num. ord., pref. art., pref. cong., pref. prep., pref. pron. rel., prep., pron. dim., pron. indef., pron. interr., pron. pers., pron. suf. , punt., sost., vb.
One could also envisage the refining of the
tagset by adding: interrogative, modal,
negation, and quantifier
As anticipated, in order to build the morphologically annotated resource, all of the Mishna sentences were extracted from the Talmud and annotated using an ad hoc developed Web application (Fig. 1).
All the annotations have been made with the aim of training a stochastic POS tagger in charge of the automatic analysis of the entire Mishna: to obtain a good accuracy it was thus necessary to manually annotate as many sentences as possible. To date, 10442 tokens have been annotated.
The software created for the annotation shows, in a tabular form, the information of the analysis carried out on a sentence by sentence basis.
The system, once a sentence is selected for annotation, checks whether the tokens composing it have already been analyzed and, in case, calculates a possible subdivision into subtokens (i.e. the stems, prefixes and sufixes constituting each word) by exploiting previous annotations. If the system finds that a word is associated with multiple diferent annotations, it proposes the most frequent one.
Regarding the linguistic annotation, the
grammar of Pérez Fernández
The software allows to gather as much information as possible for each word by providing a double annotation: by “category” to represent the POS from a grammatical point of view, and by “function” to describe the function the word assumes in its context. For the POS tagging experiments, described below, we used the annotation made by “function”. 4
Once the mishnaic corpus has been
linguistically annotated three of the most used
algorithms for POS tagging have been used and
evaluated: HunPos (Halácsy et al., 2007),
the Stanford Log-linear Part-Of-Speech
Tagger
To evaluate the accuracy of the algorithms
we adopted the strategy of k-fold cross
validation
Table 1 summarizes the results of the experiment by showing the tagging accuracy of the three tested algorithms. With a number of tokens slightly higher than ten thousands the Tagging Accuracy Stanford Hunpos Treetagger 87,90% 86,34% 86,74% Stanford POS tagger provided the best results over HunPos and Treetagger, with an accuracy of 87,9%. 5
In this work, the tagging experiments have been limited to the attribution of the PartOf-Speech: the next, natural step, will be the addition of the lemma. Furthermore, we will try to modify the parameters afecting the behaviour of the three adopted POS taggers (left at their default values for the experiments) and see how they influence the results.
Once the Mishna will be lemmatized, Traduco, the software used to translate the Talmud in Italian, will be able to exploit this additional information mainly to provide translators with translation suggestions based on lemmas, but also to allow users to query the mishnaic text by POS and lemma.
As a further step we will also take into account the linguistic annotation of portions of the Babylonian Talmud written in other languages, starting from the Babylonian Aramaic, the language of the Gemara, which constitutes the earlier portion of the Talmud.
This work was conducted in the context of the TALMUD project and the scientific cooperation between S.c.a r.l. PTTB and ILC-CNR.
Wido Van Peursen and Constantijn Sikkel. 2014.
Hebrew Text Database ETCBC4. type: dataset.