most citedRobust Semantic Parsing with Adversarial Learning for Domain Generalization

4 citations · 10 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL20193 cited

Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning

Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet

This paper presents a new semantic frame parsing model, based on Berkeley FrameNet, adapted to process spoken documents in order to perform information extraction from broadcast co…

cs.CL20191 cited

MaskParse@Deskin at SemEval-2019 Task 1: Cross-lingual UCCA Semantic Parsing using Recursive Masked Sequence Tagging

Gabriel Marzinotto, Johannes Heinecke, Geraldine Damnati

This paper describes our recursive system for SemEval-2019 \textit{ Task 1: Cross-lingual Semantic Parsing with UCCA}. Each recursive step consists of two parts. We first perform s…

cs.CL20194 cited

Robust Semantic Parsing with Adversarial Learning for Domain Generalization

Gabriel Marzinotto, Geraldine Damnati, Frédéric Béchet +1

This paper addresses the issue of generalization for Semantic Parsing in an adversarial framework. Building models that are more robust to inter-document variability is crucial for…

cs.AI2019

Spoken Conversational Search for General Knowledge

Lina M. Rojas-Barahona, Pascal Bellec, Benoit Besset +8

We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. The dialogue component does not only…

cs.CL20182 cited

Sources of Complexity in Semantic Frame Parsing for Information Extraction

Gabriel Marzinotto, Frédéric Béchet, Géraldine Damnati +1

This paper describes a Semantic Frame parsing System based on sequence labeling methods, precisely BiLSTM models with highway connections, for performing information extraction on…

cs.CL2018

FrameNet automatic analysis : a study on a French corpus of encyclopedic texts

Gabriel Marzinotto, Géraldine Damnati, Frederic Bechet

This article presents an automatic frame analysis system evaluated on a corpus of French encyclopedic history texts annotated according to the FrameNet formalism. The chosen approa…