Search Results for author:
Found 26 papers, 4 papers with code
Strength in Numbers: Averaging and Clustering Effects in Mixture of Experts for Graph-Based Dependency Parsing
We review two features of mixture of experts (MoE) models which we call averaging and clustering effects in the context of graph-based dependency parsers learned in a supervised probabilistic framework.
Predicting Accurate Lagrangian Multipliers for Mixed Integer Linear Programs
Given any duals for these constraints, called Lagrangian Multipliers (LMs), it returns a bound on the optimal value of the MILP, and Lagrangian methods seek the LMs giving the best such bound.
Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Starting from a deep probabilistic generative model with attention, we measure the interaction between latent variables and realizations of syntactic roles and show that it is possible to obtain, without supervision, representations of sentences where different syntactic roles correspond to clearly identified different latent variables.
Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
In the attention of Transformers, keys handle information selection while values specify what information is conveyed.
AraBART: a Pretrained Arabic Sequence-to-Sequence Model for Abstractive Summarization
Like most natural language understanding and generation tasks, state-of-the-art models for summarization are transformer-based sequence-to-sequence architectures that are pretrained on large corpora.
Abstractive Text Summarization
Natural Language Understanding
Challenging the Semi-Supervised VAE Framework for Text Classification
We compare the simplified versions to standard SSVAEs on 4 text classification tasks.
Disentangling semantics in language through VAEs and a certain architectural choice
We present an unsupervised method to obtain disentangled representations of sentences that single out semantic content.
Multitask Easy-First Dependency Parsing: Exploiting Complementarities of Different Dependency Representations
In this paper we present a parsing model for projective dependency trees which takes advantage of the existence of complementary dependency annotations which is the case in Arabic, with the availability of CATiB and UD treebanks.
Calcul de similarit\'e entre phrases : quelles mesures et quels descripteurs ? (Sentence Similarity : a study on similarity metrics with words and character strings )
Dans notre travail nous nous sommes int{\'e}ress{\'e} {\`a} deux questions : celle du choix de la mesure du similarit{\'e} d{'}une part et celle du choix des op{\'e}randes sur lesquelles se porte la mesure de similarit{\'e}.
Representation Learning and Dynamic Programming for Arc-Hybrid Parsing
We present a new method for transition-based parsing where a solution is a pair made of a dependency tree and a derivation graph describing the construction of the former.
Indexation et appariements de documents cliniques pour le Deft 2019 (Indexing and pairing texts of the medical domain )
Pour la ta{\^c}he d{'}indexation nous avons test{\'e} deux m{\'e}thodes, une fond{\'e}e sur l{'}appariemetn pr{\'e}alable des documents du jeu de tset avec les documents du jeu d{'}entra{\^\i}nement et une autre m{\'e}thode fond{\'e}e sur l{'}annotation terminologique.
Mod\`eles en Caract\`eres pour la D\'etection de Polarit\'e dans les Tweets (Character-level Models for Polarity Detection in Tweets )
Notre premi{\`e}re m{\'e}thode est fond{\'e}e sur des lexiques (mots et emojis), les n-grammes de caract{\`e}res et un classificateur {\`a} vaste marge (ou SVM).
Efficient Discontinuous Phrase-Structure Parsing via the Generalized Maximum Spanning Arborescence
We present a new method for the joint task of tagging and non-projective dependency parsing.
