Search Results for author: Peter Makarov

Found 15 papers, 2 papers with code

CLUZH at SIGMORPHON 2022 Shared Tasks on Morpheme Segmentation and Inflection Generation

no code implementations NAACL (SIGMORPHON) 2022 Silvan Wehrli, Simon Clematide, Peter Makarov

We report competitive results for morpheme segmentation (including sharing first place in part 2 of the challenge).

CLUZH at SIGMORPHON 2021 Shared Task on Multilingual Grapheme-to-Phoneme Conversion: Variations on a Baseline

no code implementations ACL (SIGMORPHON) 2021 Simon Clematide, Peter Makarov

This paper describes the submission by the team from the Department of Computational Linguistics, Zurich University, to the Multilingual Grapheme-to-Phoneme Conversion (G2P) Task 1 of the SIGMORPHON 2021 challenge in the low and medium settings.

Imitation Learning

Simple and Effective Multi-sentence TTS with Expressive and Coherent Prosody

no code implementations29 Jun 2022 Peter Makarov, Ammar Abbas, Mateusz Łajszczak, Arnaud Joly, Sri Karlapati, Alexis Moinet, Thomas Drugman, Penny Karanasou

In this paper, we examine simple extensions to a Transformer-based FastSpeech-like system, with the goal of improving prosody for multi-sentence TTS.

Language Modelling

CopyCat2: A Single Model for Multi-Speaker TTS and Many-to-Many Fine-Grained Prosody Transfer

no code implementations27 Jun 2022 Sri Karlapati, Penny Karanasou, Mateusz Lajszczak, Ammar Abbas, Alexis Moinet, Peter Makarov, Ray Li, Arent van Korlaar, Simon Slangen, Thomas Drugman

In this paper, we present CopyCat2 (CC2), a novel model capable of: a) synthesizing speech with different speaker identities, b) generating speech with expressive and contextually appropriate prosody, and c) transferring prosody at fine-grained level between any pair of seen speakers.

Multi-Scale Spectrogram Modelling for Neural Text-to-Speech

no code implementations29 Jun 2021 Ammar Abbas, Bajibabu Bollepalli, Alexis Moinet, Arnaud Joly, Penny Karanasou, Peter Makarov, Simon Slangens, Sri Karlapati, Thomas Drugman

We propose a novel Multi-Scale Spectrogram (MSS) modelling approach to synthesise speech with an improved coarse and fine-grained prosody.

Semi-supervised Contextual Historical Text Normalization

no code implementations ACL 2020 Peter Makarov, Simon Clematide

Historical text normalization, the task of mapping historical word forms to their modern counterparts, has recently attracted a lot of interest (Bollmann, 2019; Tang et al., 2018; Lusetti et al., 2018; Bollmann et al., 2018;Robertson and Goldwater, 2018; Bollmannet al., 2017; Korchagina, 2017).

Language Modelling

Imitation Learning for Neural Morphological String Transduction

1 code implementation EMNLP 2018 Peter Makarov, Simon Clematide

We employ imitation learning to train a neural transition-based string transducer for morphological tasks such as inflection generation and lemmatization.

Imitation Learning Lemmatization

Automated Acquisition of Patterns for Coding Political Event Data: Two Case Studies

no code implementations COLING 2018 Peter Makarov

We present a simple approach to the generation and labeling of extraction patterns for coding political event data, an important task in computational social science.

Neural Transition-based String Transduction for Limited-Resource Setting in Morphology

1 code implementation COLING 2018 Peter Makarov, Simon Clematide

We present a neural transition-based model that uses a simple set of edit actions (copy, delete, insert) for morphological transduction tasks such as inflection generation, lemmatization, and reinflection.

Lemmatization Machine Translation +1

Align and Copy: UZH at SIGMORPHON 2017 Shared Task for Morphological Reinflection

no code implementations CONLL 2017 Peter Makarov, Tatiana Ruzsics, Simon Clematide

The second approach is a neural state-transition system over a set of explicit edit actions, including a designated COPY action.

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