Search Results for author:
Found 173 papers, 4 papers with code
SIMPLEX-PB 2.0: A Reliable Dataset for Lexical Simplification in Brazilian Portuguese
Most research on Lexical Simplification (LS) addresses non-native speakers of English, since they are numerous and easy to recruit.
Findings of the Fourth Workshop on Neural Generation and Translation
We describe the finding of the Fourth Workshop on Neural Generation and Translation, held in concert with the annual conference of the Association for Computational Linguistics (ACL 2020).
Integrating Ethics into the NLP Curriculum
To raise awareness among future NLP practitioners and prevent inertia in the field, we need to place ethics in the curriculum for all NLP students{---}not as an elective, but as a core part of their education.
Participation d'EDF R\&D \`a DEFT 2020 (This paper describes the participation of EDF R\&D at DEFT 2020 evaluation campaign)
Ce papier d{\'e}crit la participation d{'}EDF R{\&}D {\`a} la campagne d{'}{\'e}valuation DEFT 2020.
Segmentation de texte non-supervis\'ee pour la d\'etection de th\'ematiques \`a l'aide de plongements lexicaux (Unsupervised text segmentation for topic detection using embeddings )
Parmi les approches neuronales utilis{\'e}es, nous nous int{\'e}ressons tout particuli{\`e}rement {\`a} celles qui utilisent des plongements lexicaux pour repr{\'e}senter des phrases et d{\'e}finir des segments th{\'e}matiques.
Architecture of a Scalable, Secure and Resilient Translation Platform for Multilingual News Media
A growth in news sources makes this increasingly challenging and time-consuming but MT can help automate some aspects of this process.
PATE: A Corpus of Temporal Expressions for the In-car Voice Assistant Domain
The recognition and automatic annotation of temporal expressions (e. g. {``}Add an event for tomorrow evening at eight to my calendar{''}) is a key module for AI voice assistants, in order to allow them to interact with apps (for example, a calendar app).
Offensive Language Detection Using Brown Clustering
In this study, we investigate the use of Brown clustering for offensive language detection.
Building a Universal Dependencies Treebank for Occitan
This paper outlines the ongoing effort of creating the first treebank for Occitan, a low-ressourced regional language spoken mainly in the south of France.
Terminology in Written Medical Reports: A Proposal of Text Enrichment to Favour its Comprehension by the Patient
In this paper we focus on the patient{'}s lack of comprehension of medical reports.
Evaluating Sentence Segmentation in Different Datasets of Neuropsychological Language Tests in Brazilian Portuguese
Automatic analysis of connected speech by natural language processing techniques is a promising direction for diagnosing cognitive impairments.
Towards the First Dyslexic Font in Russian
However, often the text design process is focused on the font size, but not on its type; which might be crucial especially for the people with reading disabilities.
Automatic Detection of Offensive Language in Social Media: Defining Linguistic Criteria to build a Mexican Spanish Dataset
For this purpose, a Mexican Spanish Twitter corpus was compiled and analyzed.
Multiword Expression aware Neural Machine Translation
Multiword Expressions (MWEs) are a frequently occurring phenomenon found in all natural languages that is of great importance to linguistic theory, natural language processing applications, and machine translation systems.
HBCP Corpus: A New Resource for the Analysis of Behavioural Change Intervention Reports
Due to the fast pace at which research reports in behaviour change are published, researchers, consultants and policymakers would benefit from more automatic ways to process these reports.
Investigating Multilingual Abusive Language Detection: A Cautionary Tale
Based on our findings, we can conclude that a multilingual optimization of classifiers is not possible even in settings where comparable data sets are used.
Reading KITTY: Pitch Range as an Indicator of Reading Skill
While affective outcomes are generally positive for the use of eBooks and computer-based reading tutors in teaching children to read, learning outcomes are often poorer (Korat and Shamir, 2004).
Participation d'EDF R\&D \`a DEFT 2019 : des vecteurs et des r\`egles ! (EDF R\&D submission to DEFT 2019 )
Les m{\'e}thodes propos{\'e}es sont facilement transposables {\`a} d{'}autres t{\^a}ches d{'}indexation et de d{\'e}tection de similarit{\'e} qui peuvent int{\'e}resser plusieurs entit{\'e}s du groupe EDF.
Transformation d'annotations en parties du discours et lemmes vers le format Universal Dependencies : \'etude de cas pour l'alsacien et l'occitan (Converting POS-tag and Lemma Annotations into the Universal Dependencies Format : A Case Study on Alsatian and Occitan )
Cet article pr{\'e}sente un retour d{'}exp{\'e}rience sur la transformation de corpus annot{\'e}s pour l{'}alsacien et l{'}occitan vers le format CONLL-U d{\'e}fini dans le projet Universal Dependencies.
Vers la traduction automatique d'adverbiaux temporels du fran\ccais vers la langue des signes fran\ccaise (Towards the automatic translation of temporal adverbials from French to French sign language)
Nous pr{\'e}sentons ici de premiers travaux abordant la question de r{\`e}gles de passage entre deux formalismes d{\'e}crivant la s{\'e}mantique d{'}adverbiaux temporels respectivement pour le fran{\c{c}}ais et pour la Langue des Signes Fran{\c{c}}aise (LSF).
A Crowdsourced Corpus of Multiple Judgments and Disagreement on Anaphoric Interpretation
The corpus, containing annotations for about 108, 000 markables, is one of the largest corpora for coreference for English, and one of the largest crowdsourced NLP corpora, but its main feature is the large number of judgments per markable: 20 on average, and over 2. 2M in total.
The importance of sharing patient-generated clinical speech and language data
Increased access to large datasets has driven progress in NLP.
Suicide Risk Assessment with Multi-level Dual-Context Language and BERT
Mental health predictive systems typically model language as if from a single context (e. g. Twitter posts, status updates, or forum posts) and often limited to a single level of analysis (e. g. either the message-level or user-level).
LIRMM-Advanse at SemEval-2019 Task 3: Attentive Conversation Modeling for Emotion Detection and Classification
This paper addresses the problem of modeling textual conversations and detecting emotions.
Coherence models in schizophrenia
Speech samples were obtained from healthy controls and patients with a diagnosis of schizophrenia or schizoaffective disorder and different severity of positive formal thought disorder.
Multilingual prediction of Alzheimer's disease through domain adaptation and concept-based language modelling
There is growing evidence that changes in speech and language may be early markers of dementia, but much of the previous NLP work in this area has been limited by the size of the available datasets.
INGEOTEC at SemEval-2019 Task 5 and Task 6: A Genetic Programming Approach for Text Classification
This paper describes our participation in HatEval and OffensEval challenges for English and Spanish languages.
Measuring English Readability for Vietnamese Speakers
This study introduces a first approximation to readability of English text for VL1, with suggestions for further improvements.
Readability of Twitter Tweets for Second Language Learners
Optimal language acquisition via reading requires the learners to read slightly above their current language skill level.
Multi-source synthetic treebank creation for improved cross-lingual dependency parsing
This paper describes a method of creating synthetic treebanks for cross-lingual dependency parsing using a combination of machine translation (including pivot translation), annotation projection and the spanning tree algorithm.
NLP-Cube: End-to-End Raw Text Processing With Neural Networks
We introduce NLP-Cube: an end-to-end Natural Language Processing framework, evaluated in CoNLL{'}s {``}Multilingual Parsing from Raw Text to Universal Dependencies 2018{''} Shared Task.
GBD-NER at PARSEME Shared Task 2018: Multi-Word Expression Detection Using Bidirectional Long-Short-Term Memory Networks and Graph-Based Decoding
This paper addresses the issue of multi-word expression (MWE) detection by employing a new decoding strategy inspired after graph-based parsing.
Gold Standard Annotations for Preposition and Verb Sense with Semantic Role Labels in Adult-Child Interactions
Inter-annotator agreement is given separately for prepositions and verbs, and for adult speech and child speech.
Anaphora Resolution with the ARRAU Corpus
The most distinctive feature of the corpus is the annotation of a wide range of anaphoric relations, including bridging references and discourse deixis in addition to identity (coreference).
Cross-corpus Native Language Identification via Statistical Embedding
In this paper, we approach the task of native language identification in a realistic cross-corpus scenario where a model is trained with available data and has to predict the native language from data of a different corpus.
Current and Future Psychological Health Prediction using Language and Socio-Demographics of Children for the CLPysch 2018 Shared Task
The goal of the shared task was to use childhood language as a marker for both current and future psychological health over individual lifetimes.
EmoIntens Tracker at SemEval-2018 Task 1: Emotional Intensity Levels in \#Tweets
The „Affect in Tweets{''} task is centered on emotions categorization and evaluation matrix using multi-language tweets (English and Spanish).
Using Classifier Features to Determine Language Transfer on Morphemes
We focus on the use of English grammatical morphemes across four proficiency levels.
LIRMM@DEFT-2018 -- Mod\`ele de classification de la vectorisation des documents (LIRMM DEFT-2018 -- Document Vectorization Classification model )
Dans ce papier, nous d{\'e}crivons notre participation au d{\'e}fi d{'}analyse de texte DEFT 2018.
Towards Replicability in Parsing
We investigate parsing replicability across 7 languages (and 8 treebanks), showing that choices concerning the use of grammatical functions in parsing or evaluation, the influence of the rare word threshold, as well as choices in test sentences and evaluation script options have considerable and often unexpected effects on parsing accuracies.
Non-Deterministic Segmentation for Chinese Lattice Parsing
Parsing Chinese critically depends on correct word segmentation for the parser since incorrect segmentation inevitably causes incorrect parses.
Native Language Identification using Phonetic Algorithms
In this paper, we discuss the results of the IUCL system in the NLI Shared Task 2017.
Quantifying the Effects of Text Duplication on Semantic Models
Duplicate documents are a pervasive problem in text datasets and can have a strong effect on unsupervised models.
Similarity Based Genre Identification for POS Tagging Experts \& Dependency Parsing
The results show that the choice of similarity metric has an effect on results and that we can reach comparable accuracies to the joint topic modeling in POS tagging and dependency parsing, thus providing a viable and efficient approach to POS tagging and parsing a sentence by its genre expert.
\#WarTeam at SemEval-2017 Task 6: Using Neural Networks for Discovering Humorous Tweets
This paper presents the participation of {\#}WarTeam in Task 6 of SemEval2017 with a system classifying humor by comparing and ranking tweets.
The AI2 system at SemEval-2017 Task 10 (ScienceIE): semi-supervised end-to-end entity and relation extraction
This paper describes our submission for the ScienceIE shared task (SemEval- 2017 Task 10) on entity and relation extraction from scientific papers.
Enriching Complex Networks with Word Embeddings for Detecting Mild Cognitive Impairment from Speech Transcripts
The approach using linguistic features yielded higher accuracy if the transcriptions of the Cinderella dataset were manually revised.
D\'etection automatique de m\'etaphores dans des textes de G\'eographie : une \'etude prospective (Automatic detection of metaphors in Geographical research papers : a prospective study)
Cet article s{'}int{\`e}gre dans un projet collaboratif qui vise {\`a} r{\'e}aliser une analyse longitudinale de la production universitaire en G{\'e}ographie.
Pulling Out the Stops: Rethinking Stopword Removal for Topic Models
It is often assumed that topic models benefit from the use of a manually curated stopword list.
Investigating Diatopic Variation in a Historical Corpus
This paper investigates diatopic variation in a historical corpus of German.
Creating POS Tagging and Dependency Parsing Experts via Topic Modeling
Part of speech (POS) taggers and dependency parsers tend to work well on homogeneous datasets but their performance suffers on datasets containing data from different genres.
Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering
We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order.
Common Round: Application of Language Technologies to Large-Scale Web Debates
Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking.
The SUMMA Platform Prototype
We present the first prototype of the SUMMA Platform: an integrated platform for multilingual media monitoring.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
Combining Heterogeneous User Generated Data to Sense Well-being
In this paper we address a new problem of predicting affect and well-being scales in a real-world setting of heterogeneous, longitudinal and non-synchronous textual as well as non-linguistic data that can be harvested from on-line media and mobile phones.
Mise au point d'une m\'ethode d'annotation morphosyntaxique fine du serbe (Developping a method for detailed morphosyntactic tagging of Serbian)
Cet article pr{\'e}sente une exp{\'e}rience d{'}annotation morphosyntaxique fine du volet serbe du corpus parall{\`e}le ParCoLab (corpus serbe-fran{\c{c}}ais-anglais).
A Sequence Model Approach to Relation Extraction in Portuguese
The task of Relation Extraction from texts is one of the main challenges in the area of Information Extraction, considering the required linguistic knowledge and the sophistication of the language processing techniques employed.
Web Chat Conversations from Contact Centers: a Descriptive Study
In this article we propose a descriptive study of a chat conversations corpus from an assistance contact center.
The COPLE2 corpus: a learner corpus for Portuguese
We present the COPLE2 corpus, a learner corpus of Portuguese that includes written and spoken texts produced by learners of Portuguese as a second or foreign language.
Rule-based Automatic Multi-word Term Extraction and Lemmatization
In this paper we present a rule-based method for multi-word term extraction that relies on extensive lexical resources in the form of electronic dictionaries and finite-state transducers for modelling various syntactic structures of multi-word terms.
A Crowdsourced Database of Event Sequence Descriptions for the Acquisition of High-quality Script Knowledge
Scripts are standardized event sequences describing typical everyday activities, which play an important role in the computational modeling of cognitive abilities (in particular for natural language processing).
Summ-it++: an Enriched Version of the Summ-it Corpus
This paper presents Summ-it++, an enriched version the Summ-it corpus.
Detecting Implicit Expressions of Affect from Text using Semantic Knowledge on Common Concept Properties
Emotions are an important part of the human experience.
Relation- and Phrase-level Linking of FrameNet with Sar-graphs
Recent research shows the importance of linking linguistic knowledge resources for the creation of large-scale linguistic data.
Comparing Apples to Apple: The Effects of Stemmers on Topic Models
Rule-based stemmers such as the Porter stemmer are frequently used to preprocess English corpora for topic modeling.
Un syst\`eme expert fond\'e sur une analyse s\'emantique pour l'identification de menaces d'ordre biologique
Le projet europ{\'e}en TIER (Integrated strategy for CBRN {--} Chemical, Biological, Radiological and Nuclear {--} Threat Identification and Emergency Response) vise {\`a} int{\'e}grer une strat{\'e}gie compl{\`e}te et int{\'e}gr{\'e}e pour la r{\'e}ponse d{'}urgence dans un contexte de dangers biologiques, chimiques, radiologiques, nucl{\'e}aires, ou li{\'e}s aux explosifs, bas{\'e}e sur l{'}identification des menaces et d{'}{\'e}valuation des risques.
Classification d'entit\'es nomm\'ees de type film
Pour ce faire, nous combinons deux approches : nous partons d{'}un syst{\`e}me {\`a} base de r{\`e}gles, qui pr{\'e}sente une bonne pr{\'e}cision, que nous couplons avec un mod{\`e}le de langage permettant d{'}augmenter le rappel.
Entre \'ecrit et oral ? Analyse compar\'ee de conversations de type tchat et de conversations t\'el\'ephoniques dans un centre de contact client
L{'}{\'e}tude parall{\`e}le de transcriptions de conversations t{\'e}l{\'e}phoniques issues d{'}un centre d{'}appel dans le m{\^e}me domaine de l{'}assistance permet d{'}{\'e}tablir des comparaisons entre ces deux modes d{'}interaction.
Sprinter: Language Technologies for Interactive and Multimedia Language Learning
Modern language learning courses are no longer exclusively based on books or face-to-face lectures.
Discosuite - A parser test suite for German discontinuous structures
However, for the evaluation of parser performance concerning a particular phenomenon, a test suite of sentences is needed in which this phenomenon has been identified.
A Large Corpus of Product Reviews in Portuguese: Tackling Out-Of-Vocabulary Words
Web 2. 0 has allowed a never imagined communication boom.
Resource Creation and Evaluation for Multilingual Sentiment Analysis in Social Media Texts
We show that the use of machine translated data obtained similar results as the use of native-speaker translations of the same data.
TALC-sef A Manually-Revised POS-TAgged Literary Corpus in Serbian, English and French
In this paper, we present a parallel literary corpus for Serbian, English and French, the TALC-sef corpus.
SWIFT Aligner, A Multifunctional Tool for Parallel Corpora: Visualization, Word Alignment, and (Morpho)-Syntactic Cross-Language Transfer
It is well known that word aligned parallel corpora are valuable linguistic resources.
An evaluation of the role of statistical measures and frequency for MWE identification
We report on an experiment to evaluate the role of statistical association measures and frequency for the identification of MWE.
Generating a Lexicon of Errors in Portuguese to Support an Error Identification System for Spanish Native Learners
Aiming to inform a module of a system designed to support scientific written production of Spanish native speakers learning Portuguese, we developed an approach to automatically generate a lexicon of wrong words, reproducing language transfer errors made by such foreign learners.
