Aleksandre Maskharashvili


2020

pdf bib
Neural NLG for Methodius: From RST Meaning Representations to Texts
Symon Stevens-Guille | Aleksandre Maskharashvili | Amy Isard | Xintong Li | Michael White
Proceedings of the 13th International Conference on Natural Language Generation

While classic NLG systems typically made use of hierarchically structured content plans that included discourse relations as central components, more recent neural approaches have mostly mapped simple, flat inputs to texts without representing discourse relations explicitly. In this paper, we investigate whether it is beneficial to include discourse relations in the input to neural data-to-text generators for texts where discourse relations play an important role. To do so, we reimplement the sentence planning and realization components of a classic NLG system, Methodius, using LSTM sequence-to-sequence (seq2seq) models. We find that although seq2seq models can learn to generate fluent and grammatical texts remarkably well with sufficiently representative Methodius training data, they cannot learn to correctly express Methodius’s similarity and contrast comparisons unless the corresponding RST relations are included in the inputs. Additionally, we experiment with using self-training and reverse model reranking to better handle train/test data mismatches, and find that while these methods help reduce content errors, it remains essential to include discourse relations in the input to obtain optimal performance.

2019

pdf bib
Predicates as Boxes in Bayesian Semantics for Natural Language
Jean-Philippe Bernardy | Rasmus Blanck | Stergios Chatzikyriakidis | Shalom Lappin | Aleksandre Maskharashvili
Proceedings of the 22nd Nordic Conference on Computational Linguistics

In this paper, we present a Bayesian approach to natural language semantics. Our main focus is on the inference task in an environment where judgments require probabilistic reasoning. We treat nouns, verbs, adjectives, etc. as unary predicates, and we model them as boxes in a bounded domain. We apply Bayesian learning to satisfy constraints expressed as premises. In this way we construct a model, by specifying boxes for the predicates. The probability of the hypothesis (the conclusion) is evaluated against the model that incorporates the premises as constraints.

pdf bib
Bayesian Inference Semantics: A Modelling System and A Test Suite
Jean-Philippe Bernardy | Rasmus Blanck | Stergios Chatzikyriakidis | Shalom Lappin | Aleksandre Maskharashvili
Proceedings of the Eighth Joint Conference on Lexical and Computational Semantics (*SEM 2019)

We present BIS, a Bayesian Inference Semantics, for probabilistic reasoning in natural language. The current system is based on the framework of Bernardy et al. (2018), but departs from it in important respects. BIS makes use of Bayesian learning for inferring a hypothesis from premises. This involves estimating the probability of the hypothesis, given the data supplied by the premises of an argument. It uses a syntactic parser to generate typed syntactic structures that serve as input to a model generation system. Sentences are interpreted compositionally to probabilistic programs, and the corresponding truth values are estimated using sampling methods. BIS successfully deals with various probabilistic semantic phenomena, including frequency adverbs, generalised quantifiers, generics, and vague predicates. It performs well on a number of interesting probabilistic reasoning tasks. It also sustains most classically valid inferences (instantiation, de Morgan’s laws, etc.). To test BIS we have built an experimental test suite with examples of a range of probabilistic and classical inference patterns.

2016

pdf bib
Interfacing Sentential and Discourse TAG-based Grammars
Laurence Danlos | Aleksandre Maskharashvili | Sylvain Pogodalla
Proceedings of the 12th International Workshop on Tree Adjoining Grammars and Related Formalisms (TAG+12)

2015

pdf bib
Grammaires phrastiques et discursives fondées sur les TAG : une approche de D-STAG avec les ACG
Laurence Danlos | Aleksandre Maskharashvili | Sylvain Pogodalla
Actes de la 22e conférence sur le Traitement Automatique des Langues Naturelles. Articles longs

Nous présentons une méthode pour articuler grammaire de phrase et grammaire de discours qui évite de recourir à une étape de traitement intermédiaire. Cette méthode est suffisamment générale pour construire des structures discursives qui ne soient pas des arbres mais des graphes orientés acycliques (DAG). Notre analyse s’appuie sur une approche de l’analyse discursive, Discourse Synchronous TAG (D-STAG), qui utilise les Grammaires d’Arbres Adjoint (TAG). Nous utilisons pour ce faire un encodage des TAG dans les Grammaires Catégorielles Abstraites (ACG). Cet encodage permet d’une part d’utiliser l’ordre supérieur pour l’interprétation sémantique afin de construire des structures qui soient des DAG et non des arbres, et d’autre part d’utiliser les propriétés de composition d’ACG pour réaliser naturellement l’interface entre grammaire phrastique et grammaire discursive. Tous les exemples proposés pour illustrer la méthode ont été implantés et peuvent être testés avec le logiciel approprié.

2014

pdf bib
An ACG Analysis of the G-TAG Generation Process
Laurence Danlos | Aleksandre Maskharashvili | Sylvain Pogodalla
Proceedings of the 8th International Natural Language Generation Conference (INLG)

pdf bib
Text Generation: Reexamining G-TAG with Abstract Categorial Grammars (Génération de textes : G-TAG revisité avec les Grammaires Catégorielles Abstraites) [in French]
Laurence Danlos | Aleksandre Maskharashvili | Sylvain Pogodalla
Proceedings of TALN 2014 (Volume 1: Long Papers)

2013

pdf bib
Constituency and Dependency Relationship from a Tree Adjoining Grammar and Abstract Categorial Grammars Perspective
Aleksandre Maskharashvili | Sylvain Pogodalla
Proceedings of the Sixth International Joint Conference on Natural Language Processing