Journées d'Etudes sur la Parole / Traitement Automatique de la Langue Naturelle / Rencontres des Etudiants Chercheurs en Informatique et Traitement Automatique des Langues (2017)



up

bib (full) Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. Volume 2 - Articles courts

pdf bib
Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. Volume 2 - Articles courts
Iris Eshkol-Taravella | Jean-Yves Antoine

pdf bib
Describing derivational polysemy with XMGXMG
Marios Andreou | Simon Petitjean

In this paper, we model and test the monosemy and polysemy approaches to derivational multiplicity of meaning, using Frame Semantics and XMG. In order to illustrate our claims and proposals, we use data from deverbal nominalizations with the suffix -al on verbs of change of possession (e.g. rental, disbursal). In our XMG implementation, we show that the underspecified meaning of affixes can not always be reduced to a single unitary meaning and that the polysemy approach to multiplicity of meaning is more judicious compared to the monosemy approach. We also introduce constraints on the potential referents of derivatives. These constraints have the form of type constraints and specify which arguments in the frame of the verbal base are compatible with the referential argument of the derivative. The introduction of type constraints rules out certain readings because frame unification only succeeds if types are compatible.

up

bib (full) Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. 19es REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL 2017)

pdf bib
Actes des 24ème Conférence sur le Traitement Automatique des Langues Naturelles. 19es REncontres jeunes Chercheurs en Informatique pour le TAL (RECITAL 2017)
Iris Eshkol-Taravella | Jean-Yves Antoine

pdf bib
Machine Translation of Speech-Like Texts : Strategies for the Inclusion of Context
Rachel Bawden

Whilst the focus of Machine Translation (MT) has for a long time been the translation of planned, written texts, more and more research is being dedicated to translating speech-like texts (informal or spontaneous discourse or dialogue). To achieve high quality and natural translation of speechlike texts, the integration of context is needed, whether it is extra-linguistic (speaker identity, the interaction between speaker and interlocutor) or linguistic (coreference and stylistic phenomena linked to the spontaneous and informal nature of the texts). However, the integration of contextual information in MT systems remains limited in most current systems. In this paper, we present and critique three experiments for the integration of context into a MT system, each focusing on a different type of context and exploiting a different method : adaptation to speaker gender, cross-lingual pronoun prediction and the generation of tag questions from French into English.

pdf bib
Finding Missing Categories in Incomplete Utterances
Mehdi Mirzapour

Finding Missing Categories in Incomplete Utterances This paper introduces an efficient algorithm (O(n4)) for finding a missing category in an incomplete utterance by using unification technique as when learning categorial grammars, and dynamic programming as in CockeYoungerKasami algorithm. Using syntax / semantic interface of categorial grammar, this work can be used for deriving possible semantic readings of an incomplete utterance. The paper illustrates the problem with running examples.