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.
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.
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.
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.
no code implementations • ACL (SIGMORPHON) 2021 • Tiago Pimentel, Maria Ryskina, Sabrina J. Mielke, Shijie Wu, Eleanor Chodroff, Brian Leonard, Garrett Nicolai, Yustinus Ghanggo Ate, Salam Khalifa, Nizar Habash, Charbel El-Khaissi, Omer Goldman, Michael Gasser, William Lane, Matt Coler, Arturo Oncevay, Jaime Rafael Montoya Samame, Gema Celeste Silva Villegas, Adam Ek, Jean-Philippe Bernardy, Andrey Shcherbakov, Aziyana Bayyr-ool, Karina Sheifer, Sofya Ganieva, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Andrew Krizhanovsky, Natalia Krizhanovsky, Clara Vania, Sardana Ivanova, Aelita Salchak, Christopher Straughn, Zoey Liu, Jonathan North Washington, Duygu Ataman, Witold Kieraś, Marcin Woliński, Totok Suhardijanto, Niklas Stoehr, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo M. Ponti, Grant Aiton, Richard J. Hatcher, Emily Prud'hommeaux, Ritesh Kumar, Mans Hulden, Botond Barta, Dorina Lakatos, Gábor Szolnok, Judit Ács, Mohit Raj, David Yarowsky, Ryan Cotterell, Ben Ambridge, Ekaterina Vylomova
This year's iteration of the SIGMORPHON Shared Task on morphological reinflection focuses on typological diversity and cross-lingual variation of morphosyntactic features.
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.
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.
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.
no code implementations • WS (NoDaLiDa) 2019 • Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin, Aleksandre Maskharashvili
In this way we construct a model, by specifying boxes for the predicates.
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.
1 code implementation • DCLRL (LREC) 2022 • Eirini Amanaki, Jean-Philippe Bernardy, Stergios Chatzikyriakidis, Robin Cooper, Simon Dobnik, Aram Karimi, Adam Ek, Eirini Chrysovalantou Giannikouri, Vasiliki Katsouli, Ilias Kolokousis, Eirini Chrysovalantou Mamatzaki, Dimitrios Papadakis, Olga Petrova, Erofili Psaltaki, Charikleia Soupiona, Effrosyni Skoulataki, Christina Stefanidou
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.
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.
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.
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.
no code implementations • EMNLP (LAW, DMR) 2021 • Adam Ek, Jean-Philippe Bernardy, Stergios Chatzikyriakidis
In this paper we investigate the possibility of extracting predicate-argument relations from UD trees (and enhanced UD graphs).
1 code implementation • 3 Feb 2024 • Konstantinos Kogkalidis, Orestis Melkonian, Jean-Philippe Bernardy
Agda is a dependently-typed programming language and a proof assistant, pivotal in proof formalization and programming language theory.
1 code implementation • 26 Dec 2023 • Konstantinos Kogkalidis, Jean-Philippe Bernardy, Vikas Garg
We introduce a novel positional encoding strategy for Transformer-style models, addressing the shortcomings of existing, often ad hoc, approaches.
no code implementations • 11 Aug 2022 • Jean-Philippe Bernardy, Shalom Lappin
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.
no code implementations • LREC 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.
no code implementations • 10 Mar 2021 • Jean-Philippe Bernardy, Richard Eisenberg, Csongor Kiss, Arnaud Spiwack, Nicolas Wu
A linear parameter must be consumed exactly once in the body of its function.
Programming Languages
no code implementations • 10 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
no code implementations • 19 Dec 2020 • Jean-Philippe Bernardy, Stergios Chatzikyriakidis
In this paper, we propose an implementation of temporal semantics which is suitable for inference problems.
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.
1 code implementation • 10 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
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.
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.
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.
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.
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.
1 code implementation • SEMEVAL 2019 • Jean-Philippe Bernardy, Rasmus Blanck, Stergios Chatzikyriakidis, Shalom Lappin, Aleks Maskharashvili, re
We present BIS, a Bayesian Inference Semantics, for probabilistic reasoning in natural language.
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.
no code implementations • 14 Dec 2018 • Jean-Philippe Bernardy, Stergios Chatzikyriakidis
In this paper, we present a new corpus of entailment problems.
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.
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.
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.
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.
no code implementations • 13 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 Automatic Speech Recognition (ASR) +3