Search Results for author:
Found 39 papers, 8 papers with code
Modelling prosodic structure using Artificial Neural Networks
The ability to accurately perceive whether a speaker is asking a question or is making a statement is crucial for any successful interaction.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
A Comparison of Character Neural Language Model and Bootstrapping for Language Identification in Multilingual Noisy Texts
This paper seeks to examine the effect of including background knowledge in the form of character pre-trained neural language model (LM), and data bootstrapping to overcome the problem of unbalanced limited resources.
Improving Neural Network Performance by Injecting Background Knowledge: Detecting Code-switching and Borrowing in Algerian texts
We explore the effect of injecting background knowledge to different deep neural network (DNN) configurations in order to mitigate the problem of the scarcity of annotated data when applying these models on datasets of low-resourced languages.
The Influence of Context on Sentence Acceptability Judgements
We investigate the influence that document context exerts on human acceptability judgements for English sentences, via two sets of experiments.
A Compositional Bayesian Semantics for Natural Language
We propose a compositional Bayesian semantics that interprets declarative sentences in a natural language by assigning them probability conditions.
A corpus of precise natural textual entailment problems
In this paper, we present a new corpus of entailment problems.
Mapping the hyponymy relation of wordnet onto vector Spaces
The first one leverages an existing mapping of words to feature vectors (fasttext), and attempts to classify such vectors as within or outside of each class.
Bayesian Inference Semantics: A Modelling System and A Test Suite
We present BIS, a Bayesian Inference Semantics, for probabilistic reasoning in natural language.
Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA
We explore the extent to which neural networks can learn to identify semantically equivalent sentences from a small variable dataset using an end-to-end training.
Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data
We work with Algerian, an under-resourced non-standardised Arabic variety, for which we compile a new parallel corpus consisting of user-generated textual data matched with normalised and corrected human annotations following data-driven and our linguistically motivated standard.
Improving the Precision of Natural Textual Entailment Problem Datasets
In this paper, we propose a method to modify natural textual entailment problem datasets so that they better reflect a more precise notion of entailment.
Identifying Sentiments in Algerian Code-switched User-generated Comments
We present in this paper our work on Algerian language, an under-resourced North African colloquial Arabic variety, for which we built a comparably large corpus of more than 36, 000 code-switched user-generated comments annotated for sentiments.
When is Multi-task Learning Beneficial for Low-Resource Noisy Code-switched User-generated Algerian Texts?
Our empirical results show that multi-task learning is beneficial for some tasks in particular settings, and that the effect of each task on another, the order of the tasks, and the size of the training data of the task with more data do matter.
Dynamic IFC Theorems for Free!
We show that noninterference and transparency, the key soundness theorems for dynamic IFC libraries, can be obtained "for free", as direct consequences of the more general parametricity theorem of type abstraction.
Programming Languages Cryptography and Security Logic in Computer Science
How Much of Enhanced UD Is Contained in UD?
This algorithm can transform gold UD trees to EUD graphs with an ELAS score of 81. 55 and a EULAS score of 96. 70.
FraCaS: Temporal Analysis
In this paper, we propose an implementation of temporal semantics which is suitable for inference problems.
Linearly Qualified Types: Generic inference for capabilities and uniqueness
A linear parameter must be consumed exactly once in the body of its function.
Programming Languages
Evaluating Linear Functions to Symmetric Monoidal Categories
The Arrow abstraction is an approximation, but we argue that it does not capture the right properties.
Programming Languages
UniMorph 4.0: Universal Morphology
The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema.
Assessing the Unitary RNN as an End-to-End Compositional Model of Syntax
We show that both an LSTM and a unitary-evolution recurrent neural network (URN) can achieve encouraging accuracy on two types of syntactic patterns: context-free long distance agreement, and mildly context-sensitive cross serial dependencies.
Algebraic Positional Encodings
We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches.
Learning Structure-Aware Representations of Dependent Types
Agda is a dependently-typed programming language and a proof assistant, pivotal in proof formalization and programming language theory.
Two experiments for embedding Wordnet hierarchy into vector spaces
The first one leverages an existing mapping of words to feature vectors (fastText), and attempts to classify such vectors as within or outside of each class.
Composing Byte-Pair Encodings for Morphological Sequence Classification
Byte-pair encodings is a method for splitting a word into sub-word tokens, a language model then assigns contextual representations separately to each of these tokens.
From compositional semantics to Bayesian pragmatics via logical inference
Formal semantics in the Montagovian tradition provides precise meaning characterisations, but usually without a formal theory of the pragmatics of contextual parameters and their sensitivity to background knowledge.
Applied Temporal Analysis: A Complete Run of the FraCaS Test Suite
In this paper, we propose an implementation of temporal semantics that translates syntax trees to logical formulas, suitable for consumption by the Coq proof assistant.
Can predicate-argument relationships be extracted from UD trees?
In this paper we investigate the possibility of extracting predicate-argument relations from UD trees (and enhanced UD graphs).
How does Punctuation Affect Neural Models in Natural Language Inference
Natural Language Inference models have reached almost human-level performance but their generalisation capabilities have not been yet fully characterized.
A Neural Model for Compositional Word Embeddings and Sentence Processing
We propose a new neural model for word embeddings, which uses Unitary Matrices as the primary device for encoding lexical information.
Fine-grained Entailment: Resources for Greek NLI and Precise Entailment
First, we extend the Greek version of the FraCaS test suite to include examples where the inference is directly linked to the syntactic/morphological properties of Greek.
Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions
Our experiments also show that neither syntactic nor semantic tags improve the performance of LSTM language models on the task of predicting sentence acceptability judgments.
A Wide-Coverage Symbolic Natural Language Inference System
We present a system for Natural Language Inference which uses a dynamic semantics converter from abstract syntax trees to Coq types.
Predicates as Boxes in Bayesian Semantics for Natural Language
In this way we construct a model, by specifying boxes for the predicates.
Semantic Classification and Learning Using a Linear Tranformation Model in a Probabilistic Type Theory with Records
Starting from an existing account of semantic classification and learning from interaction formulated in a Probabilistic Type Theory with Records, encompassing Bayesian inference and learning with a frequentist flavour, we observe some problems with this account and provide an alternative account of classification learning that addresses the observed problems.
Why Should I Turn Left? Towards Active Explainability for Spoken Dialogue Systems.
In this paper we argue that to make dialogue systems able to actively explain their decisions they can make use of enthymematic reasoning.
SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages
This year's iteration of the SIGMORPHON Shared Task on morphological reinflection focuses on typological diversity and cross-lingual variation of morphosyntactic features.
Training Strategies for Neural Multilingual Morphological Inflection
This paper presents the submission of team GUCLASP to SIGMORPHON 2021 Shared Task on Generalization in Morphological Inflection Generation.
