Search Results for author: Jean-Philippe Bernardy

Found 35 papers, 5 papers with code

A Neural Model for Compositional Word Embeddings and Sentence Processing

no code implementations CMCL (ACL) 2022 Shalom Lappin, Jean-Philippe Bernardy

We propose a new neural model for word embeddings, which uses Unitary Matrices as the primary device for encoding lexical information.

Word Embeddings

Applied Temporal Analysis: A Complete Run of the FraCaS Test Suite

no code implementations IWCS (ACL) 2021 Jean-Philippe Bernardy, Stergios Chatzikyriakidis

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.

From compositional semantics to Bayesian pragmatics via logical inference

no code implementations ACL (NALOMA, IWCS) 2021 Julian Grove, Jean-Philippe Bernardy, Stergios Chatzikyriakidis

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.

How does Punctuation Affect Neural Models in Natural Language Inference

no code implementations PaM 2020 Adam Ek, Jean-Philippe Bernardy, Stergios Chatzikyriakidis

Natural Language Inference models have reached almost human-level performance but their generalisation capabilities have not been yet fully characterized.

Natural Language Inference

Training Strategies for Neural Multilingual Morphological Inflection

no code implementations ACL (SIGMORPHON) 2021 Adam Ek, Jean-Philippe Bernardy

This paper presents the submission of team GUCLASP to SIGMORPHON 2021 Shared Task on Generalization in Morphological Inflection Generation.

Morphological Inflection

Why Should I Turn Left? Towards Active Explainability for Spoken Dialogue Systems.

no code implementations ReInAct 2021 Vladislav Maraev, Ellen Breitholtz, Christine Howes, Jean-Philippe Bernardy

In this paper we argue that to make dialogue systems able to actively explain their decisions they can make use of enthymematic reasoning.

Spoken Dialogue Systems

Semantic Classification and Learning Using a Linear Tranformation Model in a Probabilistic Type Theory with Records

no code implementations ReInAct 2021 Staffan Larsson, Jean-Philippe Bernardy

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.

Bayesian Inference Classification

Composing Byte-Pair Encodings for Morphological Sequence Classification

1 code implementation UDW (COLING) 2020 Adam Ek, Jean-Philippe Bernardy

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.

Classification Language Modelling

Two experiments for embedding Wordnet hierarchy into vector spaces

no code implementations GWC 2019 Jean-Philippe Bernardy, Aleksandre Maskharashvili

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.

A Wide-Coverage Symbolic Natural Language Inference System

no code implementations WS (NoDaLiDa) 2019 Stergios Chatzikyriakidis, Jean-Philippe Bernardy

We present a system for Natural Language Inference which uses a dynamic semantics converter from abstract syntax trees to Coq types.

Natural Language Inference

Language Modeling with Syntactic and Semantic Representation for Sentence Acceptability Predictions

1 code implementation WS (NoDaLiDa) 2019 Adam Ek, Jean-Philippe Bernardy, Shalom Lappin

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.

Language Modelling

UniMorph 4.0: Universal Morphology

no code implementations7 May 2022 Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieraś, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina J. Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Lane, Mohit Raj, Matt Coler, Jaime Rafael Montoya Samame, Delio Siticonatzi Camaiteri, Benoît Sagot, Esaú Zumaeta Rojas, Didier López Francis, Arturo Oncevay, Juan López Bautista, Gema Celeste Silva Villegas, Lucas Torroba Hennigen, Adam Ek, David Guriel, Peter Dirix, Jean-Philippe Bernardy, Andrey Scherbakov, Aziyana Bayyr-ool, Antonios Anastasopoulos, Roberto Zariquiey, Karina Sheifer, Sofya Ganieva, Hilaria Cruz, Ritván Karahóǧa, Stella Markantonatou, George Pavlidis, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Candy Angulo, Jatayu Baxi, Andrew Krizhanovsky, Natalia Krizhanovskaya, Elizabeth Salesky, Clara Vania, Sardana Ivanova, Jennifer White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan North Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo M. Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Prud'hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya D. McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova

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.

Morphological Inflection

Evaluating Linear Functions to Symmetric Monoidal Categories

no code implementations10 Mar 2021 Jean-Philippe Bernardy, Arnaud Spiwack

The Arrow abstraction is an approximation, but we argue that it does not capture the right properties.

Programming Languages

Linear Constraints

no code implementations10 Mar 2021 Jean-Philippe Bernardy, Richard Eisenberg, Csongor Kiss, Arnaud Spiwack, Nicolas Wu

A linear argument must be consumed exactly once in the body of its function.

Programming Languages

FraCaS: Temporal Analysis

no code implementations19 Dec 2020 Jean-Philippe Bernardy, Stergios Chatzikyriakidis

In this paper, we propose an implementation of temporal semantics which is suitable for inference problems.

How Much of Enhanced UD Is Contained in UD?

no code implementations WS 2020 Adam Ek, Jean-Philippe Bernardy

This algorithm can transform gold UD trees to EUD graphs with an ELAS score of 81. 55 and a EULAS score of 96. 70.

Dynamic IFC Theorems for Free!

1 code implementation10 May 2020 Maximilian Algehed, Jean-Philippe Bernardy, Catalin Hritcu

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

Improving the Precision of Natural Textual Entailment Problem Datasets

no code implementations LREC 2020 Jean-Philippe Bernardy, Stergios Chatzikyriakidis

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.

Natural Language Inference

Identifying Sentiments in Algerian Code-switched User-generated Comments

no code implementations LREC 2020 Wafia Adouane, Samia Touileb, Jean-Philippe Bernardy

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.

Sentiment Analysis

When is Multi-task Learning Beneficial for Low-Resource Noisy Code-switched User-generated Algerian Texts?

no code implementations LREC 2020 Wafia Adouane, Jean-Philippe Bernardy

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.

Data Augmentation Multi-Task Learning +2

Normalising Non-standardised Orthography in Algerian Code-switched User-generated Data

no code implementations WS 2019 Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik

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.

Semantic Textual Similarity Spelling Correction

Neural Models for Detecting Binary Semantic Textual Similarity for Algerian and MSA

no code implementations WS 2019 Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik

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.

Semantic Textual Similarity

Mapping the hyponymy relation of wordnet onto vector Spaces

no code implementations ICLR 2019 Jean-Philippe Bernardy, Aleksandre Maskharashvili

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.

A Compositional Bayesian Semantics for Natural Language

no code implementations COLING 2018 Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin

We propose a compositional Bayesian semantics that interprets declarative sentences in a natural language by assigning them probability conditions.

Improving Neural Network Performance by Injecting Background Knowledge: Detecting Code-switching and Borrowing in Algerian texts

no code implementations WS 2018 Wafia Adouane, Jean-Philippe Bernardy, Simon Dobnik

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.

Word Embeddings

The Influence of Context on Sentence Acceptability Judgements

1 code implementation ACL 2018 Jean-Philippe Bernardy, Shalom Lappin, Jey Han Lau

We investigate the influence that document context exerts on human acceptability judgements for English sentences, via two sets of experiments.

Language Modelling Machine Translation +1

A Comparison of Character Neural Language Model and Bootstrapping for Language Identification in Multilingual Noisy Texts

no code implementations WS 2018 Wafia Adouane, Simon Dobnik, Jean-Philippe Bernardy, Nasredine Semmar

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.

Language Identification Language Modelling +1

Modelling prosodic structure using Artificial Neural Networks

no code implementations13 Jun 2017 Jean-Philippe Bernardy, Charalambos Themistocleous

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 Classification +1

Cannot find the paper you are looking for? You can Submit a new open access paper.