Search Results for author:
Found 36 papers, 1 papers with code
TALEP at CMCL 2021 Shared Task: Non Linear Combination of Low and High-Level Features for Predicting Eye-Tracking Data
In this paper we describe our contribution to the CMCL 2021 Shared Task, which consists in predicting 5 different eye tracking variables from English tokenized text.
Transfer Learning and Masked Generation for Answer Verbalization
In general, QA systems query a Knowledge Base (KB) to detect and extract the raw answers as final prediction.
The Reading Machine: A Versatile Framework for Studying Incremental Parsing Strategies
The Reading Machine, is a parsing framework that takes as input raw text and performs six standard nlp tasks: tokenization, pos tagging, morphological analysis, lemmatization, dependency parsing and sentence segmentation.
WikiFactDiff: A Large, Realistic, and Temporally Adaptable Dataset for Atomic Factual Knowledge Update in Causal Language Models
To study this task, we present WikiFactDiff, a dataset that describes the evolution of factual knowledge between two dates as a collection of simple facts divided into three categories: new, obsolete, and static.
Investigating the Effect of Relative Positional Embeddings on AMR-to-Text Generation with Structural Adapters
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs).
Dependency Parsing with Backtracking using Deep Reinforcement Learning
Greedy algorithms for NLP such as transition based parsing are prone to error propagation.
SLICE: Supersense-based Lightweight Interpretable Contextual Embeddings
Contextualised embeddings such as BERT have become de facto state-of-the-art references in many NLP applications, thanks to their impressive performances.
CALOR-QUEST : generating a training corpus for Machine Reading Comprehension models from shallow semantic annotations
Machine reading comprehension is a task related to Question-Answering where questions are not generic in scope but are related to a particular document.
Genetic Neural Architecture Search for automatic assessment of human sperm images
Every individual of the genetic algorithm is a convolutional neural network trained to predict morphological deformities in different segments of human sperm (head, vacuole, and acrosome), and its fitness is calculated by a novel proposed method named GeNAS-WF especially designed for noisy, low resolution, and imbalanced datasets.
CALOR-QUEST : un corpus d'entra\^\inement et d'\'evaluation pour la compr\'ehension automatique de textes (Machine reading comprehension is a task related to Question-Answering where questions are not generic in scope but are related to a particular document)
Le but de cette {\'e}tude est de permettre le d{\'e}veloppement de telles ressources pour d{'}autres langues {\`a} moindre co{\^u}t en proposant une m{\'e}thode g{\'e}n{\'e}rant de mani{\`e}re semi-automatique des questions {\`a} partir d{'}une analyse s{\'e}mantique d{'}un grand corpus.
Typological Features for Multilingual Delexicalised Dependency Parsing
The existence of universal models to describe the syntax of languages has been debated for decades.
Sources of Complexity in Semantic Frame Parsing for Information Extraction
This paper describes a Semantic Frame parsing System based on sequence labeling methods, precisely BiLSTM models with highway connections, for performing information extraction on a corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism.
Semantic Frame Parsing for Information Extraction : the CALOR corpus
This paper presents a publicly available corpus of French encyclopedic history texts annotated according to the Berkeley FrameNet formalism.
Annotation en Actes de Dialogue pour les Conversations d'Assistance en Ligne (Dialog Acts Annotations for Online Chats)
Les conversations techniques en ligne sont un type de productions linguistiques qui par de nombreux aspects se d{\'e}marquent des objets plus usuellement {\'e}tudi{\'e}s en traitement automatique des langues : il s{'}agit de dialogues {\'e}crits entre deux locuteurs qui servent de support {\`a} la r{\'e}solution coop{\'e}rative des probl{\`e}mes des usagers.
Correction automatique d'attachements pr\'epositionnels par utilisation de traits visuels (PP-attachement resolution using visual features)
La d{\'e}sambigu{\"\i}sation des rattachements pr{\'e}positionnels est une t{\^a}che syntaxique qui demande des connaissances s{\'e}mantiques, pouvant {\^e}tre extraites d{'}une image associ{\'e}e au texte trait{\'e}.
TAG Parsing with Neural Networks and Vector Representations of Supertags
We present supertagging-based models for Tree Adjoining Grammar parsing that use neural network architectures and dense vector representation of supertags (elementary trees) to achieve state-of-the-art performance in unlabeled and labeled attachment scores.
Correcting prepositional phrase attachments using multimodal corpora
PP-attachments are an important source of errors in parsing natural language.
Deeper syntax for better semantic parsing
Syntax plays an important role in the task of predicting the semantic structure of a sentence.
DeQue: A Lexicon of Complex Prepositions and Conjunctions in French
We introduce DeQue, a lexicon covering French complex prepositions (CPRE) like {``}{\`a} partir de{''} (from) and complex conjunctions (CCONJ) like {``}bien que{''} (although).
Automatically enriching spoken corpora with syntactic information for linguistic studies
Syntactic parsing of speech transcriptions faces the problem of the presence of disfluencies that break the syntactic structure of the utterances.
Syntactic annotation of spontaneous speech: application to call-center conversation data
This paper describes the syntactic annotation process of the DECODA corpus.
