Méthodes de prédiction structurée pour l’analyse sémantiqueStructured prediction methods for semantic parsingMéthodes de prédiction structurée pour l’analyse sémantique

The defence will be in English. You can attend it remotely via the following link: https://bbb.lisn.upsaclay.fr/b/alb-fxj-85m-4b1.

Thesis committee

• – Maxime AMBLARD, professor at LORIA (CNRS, Université de Lorraine) ;
• – Marie CANDITO, assistant professor at LLF (Université Paris-Cité) ;
• – Pascal DENIS, researcher at INRIA (CNRS, Université de Lille) ;
• – Vincent GUIGUE, professor at AgroParisTech (Université Paris-Saclay) ;
• – Laura KALLMEYER, professor (University of Düsseldorf) ;
• – François YVON, doctoral advisor, senior researcher at ISIR (CNRS, Sorbonne Université);
• – Caio CORRO, doctoral co-advisor, associate professor at ISIR (CNRS, Sorbonne Université).

Keywords

Semantic parsing, compositional generalization, natural language processing

Abstract

Semantic parsing is the task of mapping a natural language utterance into a formal representation that can be manipulated by a computer program. It is a major task in Natural Language Processing with several applications, including the development of questions answers systems or code generation among others.

In recent years, neural-based approaches and particularly sequence-to-sequence architectures have demonstrated strong performances on this task. However, several works have put forward the limitations of neural-based parsers on out-of-distribution examples. In particular, they fail when compositional generalization is required. It is thus essential to develop parsers that exhibit better compositional abilities.

The representation of the semantic content is another concern when tackling semantic parsing. As different syntactic structures can be used to represent the same semantic content, one should focus on structures that can both accurately represent the semantic content and align well with natural language.

In that regard, this thesis relies on graph-based representations for semantic parsing and focuses on two tasks.

The first one deals with the training of graph-based semantic parsers. They need to learn a correspondence between the parts of the semantic graph and the natural language utterance. As this information is usually absent in the training data, we propose training algorithms that treat this correspondence as a latent variable.

The second task focuses on improving the compositional abilities of graph-based semantic parsers in two different settings. Note that in graph prediction, the traditional pipeline is to first predict the nodes and then the arcs of the graph. In the first setting, we assume that the graphs that must be predicted are trees and propose an optimization algorithm based on constraint smoothing and conditional gradient that allows to predict the entire graph jointly. In the second setting, we do not make any assumption regarding the nature of the semantic graphs. In that case, we propose to introduce an intermediate supertagging step in the inference pipeline that constrains the arc prediction step. In both settings, our contributions can be viewed as introducing additional local constraints to ensure the well-formedness the overall prediction. Experimentally, our contributions significantly improve the compositional abilities of graph-based semantic parsers and outperform comparable baselines on several datasets designed to evaluate compositional generalization.