Search Results for author: Helena Moniz

Found 20 papers, 4 papers with code

QUARTZ: Quality-Aware Machine Translation

no code implementations EAMT 2022 José G.C. de Souza, Ricardo Rei, Ana C. Farinha, Helena Moniz, André F. T. Martins

This paper presents QUARTZ, QUality-AwaRe machine Translation, a project led by Unbabel which aims at developing machine translation systems that are more robust and produce fewer critical errors.

Machine Translation Translation

Multi3Generation: Multitask, Multilingual, Multimodal Language Generation

no code implementations EAMT 2022 Anabela Barreiro, José GC de Souza, Albert Gatt, Mehul Bhatt, Elena Lloret, Aykut Erdem, Dimitra Gkatzia, Helena Moniz, Irene Russo, Fabio Kepler, Iacer Calixto, Marcin Paprzycki, François Portet, Isabelle Augenstein, Mirela Alhasani

This paper presents the Multitask, Multilingual, Multimodal Language Generation COST Action – Multi3Generation (CA18231), an interdisciplinary network of research groups working on different aspects of language generation.

Text Generation

Agent and User-Generated Content and its Impact on Customer Support MT

no code implementations EAMT 2022 Madalena Gonçalves, Marianna Buchicchio, Craig Stewart, Helena Moniz, Alon Lavie

This paper illustrates a new evaluation framework developed at Unbabel for measuring the quality of source language text and its effect on both Machine Translation (MT) and Human Post-Edition (PE) performed by non-professional post-editors.

Machine Translation Translation

Project MAIA: Multilingual AI Agent Assistant

no code implementations EAMT 2020 André F. T. Martins, Joao Graca, Paulo Dimas, Helena Moniz, Graham Neubig

This paper presents the Multilingual Artificial Intelligence Agent Assistant (MAIA), a project led by Unbabel with the collaboration of CMU, INESC-ID and IT Lisbon.

AI Agent BIG-bench Machine Learning +1

ConText at WASSA 2024 Empathy and Personality Shared Task: History-Dependent Embedding Utterance Representations for Empathy and Emotion Prediction in Conversations

no code implementations4 Jul 2024 Patrícia Pereira, Helena Moniz, Joao Paulo Carvalho

In our submissions, we model empathy, emotion polarity and emotion intensity of each utterance in a conversation by feeding the utterance to be classified together with its conversational context, i. e., a certain number of previous conversational turns, as input to an encoder Pre-trained Language Model, to which we append a regression head for prediction.

Language Modelling

Fuzzy Fingerprinting Transformer Language-Models for Emotion Recognition in Conversations

no code implementations8 Sep 2023 Patrícia Pereira, Rui Ribeiro, Helena Moniz, Luisa Coheur, Joao Paulo Carvalho

Fuzzy Fingerprints have been successfully used as an interpretable text classification technique, but, like most other techniques, have been largely surpassed in performance by Large Pre-trained Language Models, such as BERT or RoBERTa.

Emotion Recognition text-classification +1

Simple LLM Prompting is State-of-the-Art for Robust and Multilingual Dialogue Evaluation

1 code implementation31 Aug 2023 John Mendonça, Patrícia Pereira, Helena Moniz, João Paulo Carvalho, Alon Lavie, Isabel Trancoso

Despite significant research effort in the development of automatic dialogue evaluation metrics, little thought is given to evaluating dialogues other than in English.

Dialogue Evaluation

Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations

1 code implementation17 Apr 2023 Patrícia Pereira, Helena Moniz, Isabel Dias, Joao Paulo Carvalho

The usual approach to model the conversational context has been to produce context-independent representations of each utterance and subsequently perform contextual modeling of these.

 Ranked #1 on Emotion Recognition in Conversation on EmoWoz (Macro F1 metric)

Classification Emotion Recognition in Conversation

A Simple Feature Method for Prosody Rhythm Comparison

no code implementations20 Dec 2022 Mariana Julião, Alberto Abad, Helena Moniz

Of all components of Prosody, Rhythm has been regarded as the hardest to address, as it is utterly linked to Pitch and Intensity.

Clustering Sentence

Deep Emotion Recognition in Textual Conversations: A Survey

no code implementations16 Nov 2022 Patrícia Pereira, Helena Moniz, Joao Paulo Carvalho

This is followed by descriptions of the most prominent works in ERC with explanations of the Deep Learning architectures employed.

Emotion Recognition in Conversation Text Classification

Retrieval Augmentation for Deep Neural Networks

1 code implementation25 Feb 2021 Rita Parada Ramos, Patrícia Pereira, Helena Moniz, Joao Paulo Carvalho, Bruno Martins

Despite the use of large training datasets, most models are trained by iterating over single input-output pairs, discarding the remaining examples for the current prediction.

Image Captioning Sentiment Analysis +1

OpenLogos Semantico-Syntactic Knowledge-Rich Bilingual Dictionaries

no code implementations LREC 2014 Anabela Barreiro, Fern Batista, o, Ricardo Ribeiro, Helena Moniz, Isabel Trancoso

This paper presents 3 sets of OpenLogos resources, namely the English-German, the English-French, and the English-Italian bilingual dictionaries.

Machine Translation Translation

Teenage and adult speech in school context: building and processing a corpus of European Portuguese

no code implementations LREC 2014 Ana Isabel Mata, Helena Moniz, Fern Batista, o, Julia Hirschberg

We present a corpus of European Portuguese spoken by teenagers and adults in school context, CPE-FACES, with an overview of the differential characteristics of high school oral presentations and the challenges this data poses to automatic speech processing.

Revising the annotation of a Broadcast News corpus: a linguistic approach

no code implementations LREC 2014 Vera Cabarr{\~a}o, Helena Moniz, Fern Batista, o, Ricardo Ribeiro, Nuno Mamede, Hugo Meinedo, Isabel Trancoso, Ana Isabel Mata, David Martins de Matos

This paper presents a linguistic revision process of a speech corpus of Portuguese broadcast news focusing on metadata annotation for rich transcription, and reports on the impact of the new data on the performance for several modules.

speech-recognition Speech Recognition

Prosodic, syntactic, semantic guidelines for topic structures across domains and corpora

no code implementations LREC 2014 Ana Isabel Mata, Helena Moniz, Telmo M{\'o}ia, Anabela Gon{\c{c}}alves, F{\'a}tima Silva, Fern Batista, o, In{\^e}s Duarte, F{\'a}tima Oliveira, Isabel Fal{\'e}

This paper presents the annotation guidelines applied to naturally occurring speech, aiming at an integrated account of contrast and parallel structures in European Portuguese.

Part-Of-Speech Tagging

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