Оқыту уақыты
Related Papers
On the Use of Tied-Mixture Distributions
Tied-mixture (or semi-continuous) distributions are an im- portant tool for acoustic modeling, used in many high- performance speech recognition systems today. This paper provides a survey of the work in …...
Top Accuracy and Fast Dependency Parsing is not a Contradiction
In addition to a high accuracy, short pars- ing and training times are the most impor- tant properties of a parser. However, pars- ing and training times are still relatively …...
Automatic Feature Selection for Agenda-Based Dependency Parsing
In this paper we present an in-depth study on automatic feature selection for beam-search depen- dency parsers. The search strategy is inherited from the one implemented in MaltOptimizer, but searches …...
Combining techniques from different NN-based language models for machine translation
AbstractThis paper presents two improvements of language models based on Restricted Boltzmann Machine (RBM) for large machine translation tasks. In contrast to other continuous space approach, RBM based models can …...
Comparison of scheduling methods for the learning rate of neural network language models (Modèles de langue neuronaux: une comparaison de plusieurs stratégies d’apprentissage) [in French]
. If neural networks play an increasingly important role in natural language processing, training issues still hinder their dissemination in the community. This paper studies different learning strategies for neural …...
Competence-based Curriculum Learning for Neural Machine Translation
AbstractCurrent state-of-the-art NMT systems use large neural networks that are not only slow to train, but also often require many heuristics and optimization tricks, such as specialized learning rate schedules …...
SoftRegex: Generating Regex from Natural Language Descriptions using Softened Regex Equivalence
AbstractWe continue the study of generating se-mantically correct regular expressions from natural language descriptions (NL). The current state-of-the-art model SemRegex produces regular expressions from NLs by rewarding the reinforced learning …...
Autoregressive Reasoning over Chains of Facts with Transformers
AbstractThis paper proposes an iterative inference algorithm for multi-hop explanation regeneration, that retrieves relevant factual evidence in the form of text snippets, given a natural language question and its answer. …...
Class-based LSTM Russian Language Model with Linguistic Information
AbstractIn the paper, we present class-based LSTM Russian language models (LMs) with classes generated with the use of both word frequency and linguistic information data, obtained with the help of …...
Do It Once: An Embarrassingly Simple Joint Matching Approach to Response Selection
Existing matching models for response selec- tion adopt the independent matching (IM) ap- proach. To complete a prediction, they have to perform N independent matches, where N is the number …...
Scaling Within Document Coreference to Long Texts
State of the art end-to-end coreference reso- lution models use expensive span representa- tions and antecedent prediction mechanisms. These approaches are expensive both in terms of their memory requirements as …...
FastClass: A Time-Efficient Approach to Weakly-Supervised Text Classification
AbstractWeakly-supervised text classification aims to train a classifier using only class descriptions and unlabeled data. Recent research shows that keyword-driven methods can achieve state-of-the-art performance on various tasks. However, these …...
Sparsifying Transformer Models with Trainable Representation Pooling
AbstractWe propose a novel method to sparsify attention in the Transformer model by learning to select the most-informative token representations during the training process, thus focusing on the task-specific parts …...