Ce mémoire s’insère dans le projet GenDR, un réalisateur de texte profond multilingue qui modélise l’interface sémantique-syntaxe pour la génération automatique de texte (GAT). Dans le cadre de la GAT, les ressources lexicales sont de première nécessité pour que le système puisse transformer des données nonlinguistiques en langage naturel. Ces ressources lexicales déterminent dans une certaine mesure la précision et la flexibilité des phrases générées. En raison de l’imprévisibilité du régime des verbes et du rôle central que les verbes jouent dans un énoncé, une ressource lexicale qui décrit le régime des verbes revêt une importance particulière pour générer du texte le plus précis et le plus naturel possible. Nous avons tenté de créer un dictionnaire de régimes verbaux en mandarin. Ce genre de ressource lexicale est toujours une lacune dans le domaine de la GAT en mandarin. En nous basant sur la base de données Mandarin VerbNet, nous avons eu recours à Python pour extraire les adpositions régies et créer notre dictionnaire. Il s’agit d’un dictionnaire dynamique, dont le contenu peut être paramétré en fonction des objectifs de l’utilisateur. / This work fits into the GenDR project, a multilingual deep realizer which models the semantics-syntax interface for natural language generation (NLG). In NLG, lexical resources are essential to transform non-linguistic data into natural language. To a certain extent, the lexical resources used determine the accuracy and flexibility of the sentences generated by a realizer. Due to the unpredictability of verbs’ syntactic behaviour and the central role that verbs play in an utterance, a lexical resource which describes the government patterns of verbs is key to generating the most precise and natural text possible. We aim to create a dictionary of verbs’ government patterns in Mandarin. This kind of lexical resource is still missing for NLG in Mandarin. Based on the Mandarin VerbNet database, we used Python to extract information about adpositions and to create our dictionary. This is a dynamic dictionary whose content can be parameterized according to the user’s needs.

No description available.

La locution est peu étudiée en génération automatique de texte (GAT). Syntaxiquement, elle forme un syntagme, alors que sémantiquement, elle ne constitue qu’une seule unité. Le présent mémoire propose un traitement des locutions en GAT multilingue qui permet d’isoler les constituants de la locution tout en conservant le sens global de celle-ci. Pour ce faire, nous avons élaboré une solution flexible à base de patrons universels d’arbres de dépendances syntaxiques vers lesquels pointent des patrons de locutions propres au français (Pausé, 2017). Notre traitement a été effectué dans le réalisateur de texte profond multilingue GenDR à l’aide des données du Réseau lexical du français (RL-fr). Ce travail a abouti à la création de 36 règles de lexicalisation par patron (indépendantes de la langue) et à un dictionnaire lexical pour les locutions du français. Notre implémentation couvre 2 846 locutions du RL-fr (soit 97,5 %), avec une précision de 97,7 %. Le mémoire se divise en cinq chapitres, qui décrivent : 1) l’architecture classique en GAT et le traitement des locutions par différents systèmes symboliques ; 2) l’architecture de GenDR, (principalement sa grammaire, ses dictionnaires, son interface sémantique-syntaxe et ses stratégies de lexicalisations) ; 3) la place des locutions dans la phraséologie selon la théorie Sens-Texte, ainsi que le RL-fr et ses patrons syntaxiques linéarisés ; 4) notre implémentation de la lexicalisation par patron des locutions dans GenDR, et 5) notre évaluation de la couverture de la précision de notre implémentation. / Idioms are rarely studied in natural language generation (NLG). Syntactically, they form a phrase, while semantically, they correspond to a single unit. In this master’s thesis, we propose a treatment of idioms in multilingual NLG that enables us to isolate their constituents while preserving their global meaning. To do so, we developed a flexible solution based on universal templates of syntactic dependency trees, onto which we map French-specific idiom patterns (Pausé, 2017). Our work was implemented in Generic Deep Realizer (GenDR) using data from the Réseau lexical du français (RL-fr). This resulted in the creation of 36 template-based lexicalization rules (independent of language) and of a lexical dictionary for French idioms. Our implementation covers 2846 idioms of the RL-fr (i.e., 97.5%), with an accuracy of 97.7%. We divided our analysis into five chapters, which describe: 1) the classical NLG architecture and the handling of idioms by different symbolic systems; 2) the architecture of GenDR (mainly its grammar, its dictionaries, its semantic-syntactic interface, and its lexicalization strategies); 3) the place of idioms in phraseology according to Meaning-Text Theory (théorie Sens-Texte), the RL-fr and its linearized syntactic patterns; 4) our implementation of the template lexicalization of idioms in GenDR; and 5) our evaluation of the coverage and the precision of our implementation.

Text in English with summaries in English, South Sotho and Xhosa / Bibliography: leaves 196-215 / This study explored the communicative strategies which were used by participants who were called in as witnesses before the Leon Commission and the Phumaphi Commission of Enquiry in Lesotho in 1998 and 2015 respectively. The study specifically looked into the types of communicative strategies employed, their linguistic realisations and their conversational effectiveness in providing required information to the commissions. It further compared the use of strategies by participants in both commissions. Data for this study was obtained from twenty-six audio recordings of twenty-six witnesses. The study established that participants used twelve types of communicative strategies which are classified under the following groups based on their functional characteristics: conversational category which includes strategies such as code-switching, fillers, vague language and circumlocution; a grammatical category that comprises personal pronouns, direct speech, passive voice and questioning; a sociocultural category that covers strategies such as figurative language, indirect communication, direct refusal and indirect criticism. The study established that communicative strategies such as code-switching, fillers, personal pronouns, and direct quoting were conversationally effective as participants strategically employed them to succinctly express themselves. However, strategies with concealing attributes such as those found under a sociocultural category and those under the grammatical category (passive voice and questioning) were considered conversationally ineffective as they withheld required information from the commissioners. The study further established that participants of the latter commission were even more unwilling to reveal information than those of the former, which suggests a growing unwillingness to share information to commissions of enquiry. / Phuputso ena e hlahlobile maano a puisano a neng a sebediswa ke dipaki ka pela Komishene ya Leon le Komishene ya Phumaphi ya dipatlisiso naheng ya Lesotho ka 1998 le 2015. Phuputso e nyebekollotse ka kotloloho mefuta ya maano a puisano a sebedisitsweng, tshebediso ya ona kahara puo le katleho kapa tshetiso ya ona ho fana ka tlhaiso-leseding e neng e hlokwa ke di Komishene. E boetse e bapisitse hore na dipaki dikomisheneng ka bobeli di sebedisitse maano ana jwang. Ditaba tsa boithuto bona di fumanwe ho tswa direkotong tse mashome a mabedi a metso e tsheletseng (26) tsa dipaki. Phuputso e netefaditse hore dipaki di sebedisitse mefuta e leshome le metso e mmedi (12) ya maano a puisano a arotsweng tlasa dihlopha tse latelang ho ipapisitswe le ditshobotsi tsa ona: sehlopha sa puisano se kenyelletsang maano a joalo ka tshebediso ya dipuo tse fetang bonngwe, ho kgitlela, puo e sa hlakang, le ho potoloha. Sehlopha se seng ke sa tlhophiso ya puo mme sona se na le maano a kang seemedi, puo e qotsitsweng, sehlwai-potoloho. Sehlopha sa setso sona se kenyeletsa maano a joalo ka mekgabo-puo, puo e potetseng, ho hana ka kotloloho, le nyefolo e kubutileng hlooho. Phuputso e netefaditse hore maano a puisano a joalo ka tshebediso ya dipuo tse fetang bonngwe, ho kgitlela, seemedi, le puo e qotsitsweng, di sebedisitswe hantle ka ha di atlehile ho thusa dipaki ho itlhalosa ka nepo le ho fana ka lesedi le hlakileng ditabeng tsa bona. Leha ho le joalo, maano a sa bueng puo-phara a kang a fumanwang tlasa sehlopha sa setso le a mang a sehlopha sa tlhophiso ya puo (a kang sehlwai-potoloho le dipotso), boithuto bona bo sibollotse hore a sebedisitswe ho sitisa tlhahiso-leseding e hlokwang ke bakomishenara. Phuputso e boetse e netefaditse hore dipaki tsa komishene ya morao-rao di ne di sa ikemisetsa ho fana ka tlhahiso leseding papisong le dipaki tsa komishene ya pele. Boithuto bona bo utullotse hore maikemisetso a ho fana ka tlhaiso-leseding ho dikomishene tsa dipatlisiso a qepha. / Esi sifundo sijonge ubuchule beendlela zonxebelelwano ezohlukileyo phakathi kwabantu ababemenyiwe ukuba bathathe inxaxheba njengamangqina kwiKhomishoni yoPhando KaLeon eyenzeka ngo1998 kunye neKhomishoni kaPhumaphi eyenzeka ngonyaka ka2015. Olu phando luye lwaqalasela ezindlela zokuqhakamishelana ezisetyenziswe apha, ukusetyenziswa kolwimi kunye nobuchule bokuthetha kula mangqina ngethuba enikeza ubungqina kwezi khomishoni. Olu phando luphinde lwathelekisa indlela amangqina asebenzise ngazo ezindlela zoqhakamishelwano kwezi khomishoni zombini. Ingqokelela-lwazi yolu phando ithathwe kumangqina angamashumi amabini anesithandathu apho kushicilelwe izimvo zawo kwezi khomishoni. Olu phando lufumanise ukuba la mangqina asebenzise ubuchule beendlela zonxebelelwano ezingamashumi amabini. Obu buchule beendlela zonxebebelwano ziqukwa ngokokusebenza kwazo ekuthetheni ngolu hlobo lulandelayo: ukuncokola okuquka ukuthetha iilwimi ezohlukeneyo ngexesha elinye, amazwi amafutshane angenantsingiselo asetyenziswa kwizimo ezinje ngokukhuza, ulwimi olungacacanga kunye nokusetyenziswa kolwimi ngendlela yokuba umntu athethe into inde apho ngeyethethe ngamagama ambalwa ukucacisa into afuna ukuyicacisa ngendlela engcono. Eyesibini yimo yokusetyensizwa kolwimi ngokuthetha nqo, ngokungathethi nqo kunye nokubanemibuzo. Eyesithathu kukujonga ulwimi nenkcubeko ngokuba kubukwe indlela abantu abasebenzisa ulwimi ngokweenkcubeko zabo apho bathetha besebenzisa iinkcazelo ezisuka kwiinckubeko zabo, ukungathethi nqo ngenxa yemo yabo yentlalo nokuthetha, ukungafuni ukuthetha ngenxa yezizimo zentlalo nenkcubeko kunye nokugxeka ngendlea ekwekwayo ngenxa yezizimo zentlalo nenkcubeko. Olu phando lubonise ukuba obu buchule beendlela zokuthetha lusetyenziswe ngamangqina ezi khomishoni luquke imo apho amangqina ebethetha iilwimi ezohlukeneyo ngexesha elinye, amangqina ayakwasebenzise amagama amafutshane angenantsingiselo asetyenziswa kwimo ezifana nokukhuza, aphinda acaphula. Ngowekenza ngolu hlobo, amanqina abanokalisile ukuba ezi ndlela zobuchule bokuthetha zincedisene nomsebenzi wezi khomishoni ngoba amangqina akwazile ukubangamaciko ekuchazeni izimvo zawo. Nangona kunjalo, ezinye iindlela zobuchule zoqhakamishelwano ezifana nezo zichaphazela inkcubeko nentlalo yabantu kunye nezokungathethi nqo, ziwachapahezele kakubi amangqina kuba zenze ukuba amangqina angakhululeki ekunikezeleni ubungqina apho kubonakale ukuba abakwazanga ukunikeza iinkcukaca ezibalulekileyo kwezi khomishoni ngenxa yoku. Olu phando luphinde lwabonakalisa ukuba amangqina weKhomishoni loPhando kaPhumaphi aye awodlula amangiqna weKhomishoni kaLeon ngokungafuni ukunikeza ngobungqina obuthile. Le nto ibirhanelisa ukuba bekukho umoya apha kwamangqina wokungafuni ncam ukunikeza ngobungqina kwezi khomishoni. / Linguistics and Modern Languages / D. Phil. (Languages, Linguistics and Literature)