Search Results for author:
Found 34 papers, 1 papers with code
Learning Web-based Procedures by Reasoning over Explanations and Demonstrations in Context
We explore learning web-based tasks from a human teacher through natural language explanations and a single demonstration.
Identification des probl\`emes d'annotation pour l'extraction de relations (Identification of annotation problem for the relation extraction)
L{'}annotation d{'}un corpus est une t{\^a}che difficile et laborieuse, notamment sur des textes de sp{\'e}cialit{\'e} comme les textes biom{\'e}dicaux.
\'Etude des facteurs affectant la compr\'ehensibilit\'e de documents multimodaux : une \'etude exp\'erimentale (Factors affecting the comprehensibility of multimodal documents : an experimental study )
La compr{\'e}hensibilit{\'e} de documents audiovisuels peut d{\'e}pendre de facteurs propres {\`a} l{'}auditeur/spectateur (ex.
Subjective Evaluation of Comprehensibility in Movie Interactions
Various research works have dealt with the comprehensibility of textual, audio, or audiovisual documents, and showed that factors related to text (e. g. linguistic complexity), sound (e. g. speech intelligibility), image (e. g. presence of visual context), or even to cognition and emotion can play a major role in the ability of humans to understand the semantic and pragmatic contents of a given document.
Cross-lingual Named Entity List Search via Transliteration
Out-of-vocabulary words are still a challenge in cross-lingual Natural Language Processing tasks, for which transliteration from source to target language or script is one of the solutions.
Humans Keep It One Hundred: an Overview of AI Journey
Artificial General Intelligence (AGI) is showing growing performance in numerous applications - beating human performance in Chess and Go, using knowledge bases and text sources to answer questions (SQuAD) and even pass human examination (Aristo project).
Commonsense inference in human-robot communication
Natural language communication between machines and humans are still constrained.
Query selection methods for automated corpora construction with a use case in food-drug interactions
In this paper, we address the problem of automatically constructing a relevant corpus of scientific articles about food-drug interactions.
De l'extraction des interactions m\'edicament-m\'edicament vers les interactions aliment-m\'edicament \`a partir de textes biom\'edicaux: Adaptation de domaine (From the extraction of drug-drug interactions to the food-drug interactions in biomedical texts : domain adaptation)
Les interactions aliments-m{\'e}dicaments (FDI) se produisent lorsque des aliments et des m{\'e}dicaments sont pris simultan{\'e}ment et provoquent un effet inattendu.
Identification des cat\'egories de relations aliment-m\'edicament (Identification of categories of food-drug relations)
Les interactions aliment-m{\'e}dicament se produisent lorsque des aliments et des m{\'e}dicaments pris ensembles provoquent un effet inattendu.
Subcharacter Information in Japanese Embeddings: When Is It Worth It?
Languages with logographic writing systems present a difficulty for traditional character-level models.
Subword-level Composition Functions for Learning Word Embeddings
Subword-level information is crucial for capturing the meaning and morphology of words, especially for out-of-vocabulary entries.
Classification multi-label \`a grande dimension pour la d\'etection de concepts m\'edicaux (Large multi-label classification for medical concepts detection)
Dans ce papier, nous pr{\'e}sentons une m{\'e}thode pour associer de fa{\c{c}}on automatique des concepts {\`a} des images.
Extraction d'interactions entre aliment et m\'edicament : Etat de l'art et premiers r\'esultats (Extraction of food-drug interactions : State of the art and first results)
A partir de cet {\'e}tat de l{'}art, nous pr{\'e}sentons une m{\'e}thode bas{\'e}e sur un apprentissage supervis{\'e} et les r{\'e}sultats d{'}une premi{\`e}re s{\'e}rie d{'}exp{\'e}riences.
Investigating Different Syntactic Context Types and Context Representations for Learning Word Embeddings
The number of word embedding models is growing every year.
The (too Many) Problems of Analogical Reasoning with Word Vectors
This paper explores the possibilities of analogical reasoning with vector space models.
Interactive Relation Extraction in Main Memory Database Systems
We present INDREX-MM, a main memory database system for interactively executing two interwoven tasks, declarative relation extraction from text and their exploitation with SQL.
Word Embeddings, Analogies, and Machine Learning: Beyond king - man + woman = queen
Solving word analogies became one of the most popular benchmarks for word embeddings on the assumption that linear relations between word pairs (such as \textit{king}:\textit{man} :: \textit{woman}:\textit{queen}) are indicative of the quality of the embedding.
Modeling non-standard language
A specific language as used by different speakers and in different situations has a number of more or less distant varieties.
Improvements in Remote Cardiopulmonary Measurement Using a Five Band Digital Camera
Remote measurement of the blood volume pulse via photoplethysmography (PPG) using digital cameras and ambient light has great potential for healthcare and affective computing.
Building a multilingual parallel corpus for human users
We present the architecture and the current state of InterCorp, a multilingual parallel corpus centered around Czech, intended primarily for human users and consisting of written texts with a focus on fiction.
Annotating Story Timelines as Temporal Dependency Structures
We present an approach to annotating timelines in stories where events are linked together by temporal relations into a temporal dependency tree.
Building a learner corpus
The paper describes a corpus of texts produced by non-native speakers of Czech.
