Saturnino Luz


2021

pdf bib
TeMoTopic: Temporal Mosaic Visualisation of Topic Distribution, Keywords, and Context
Shane Sheehan | Saturnino Luz | Masood Masoodian
Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation

In this paper we present TeMoTopic, a visualization component for temporal exploration of topics in text corpora. TeMoTopic uses the temporal mosaic metaphor to present topics as a timeline of stacked bars along with related keywords for each topic. The visualization serves as an overview of the temporal distribution of topics, along with the keyword contents of the topics, which collectively support detail-on-demand interactions with the source text of the corpora. Through these interactions and the use of keyword highlighting, the content related to each topic and its change over time can be explored.

pdf bib
Exploring Neural Language Models via Analysis of Local and Global Self-Attention Spaces
Blaž Škrlj | Shane Sheehan | Nika Eržen | Marko Robnik-Šikonja | Saturnino Luz | Senja Pollak
Proceedings of the EACL Hackashop on News Media Content Analysis and Automated Report Generation

Large pretrained language models using the transformer neural network architecture are becoming a dominant methodology for many natural language processing tasks, such as question answering, text classification, word sense disambiguation, text completion and machine translation. Commonly comprising hundreds of millions of parameters, these models offer state-of-the-art performance, but at the expense of interpretability. The attention mechanism is the main component of transformer networks. We present AttViz, a method for exploration of self-attention in transformer networks, which can help in explanation and debugging of the trained models by showing associations between text tokens in an input sequence. We show that existing deep learning pipelines can be explored with AttViz, which offers novel visualizations of the attention heads and their aggregations. We implemented the proposed methods in an online toolkit and an offline library. Using examples from news analysis, we demonstrate how AttViz can be used to inspect and potentially better understand what a model has learned.

2018

pdf bib
The Metalogue Debate Trainee Corpus: Data Collection and Annotations
Volha Petukhova | Andrei Malchanau | Youssef Oualil | Dietrich Klakow | Saturnino Luz | Fasih Haider | Nick Campbell | Dimitris Koryzis | Dimitris Spiliotopoulos | Pierre Albert | Nicklas Linz | Jan Alexandersson
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

pdf bib
Speech Rate Calculations with Short Utterances: A Study from a Speech-to-Speech, Machine Translation Mediated Map Task
Akira Hayakawa | Carl Vogel | Saturnino Luz | Nick Campbell
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)

2016

pdf bib
The ILMT-s2s Corpus ― A Multimodal Interlingual Map Task Corpus
Akira Hayakawa | Saturnino Luz | Loredana Cerrato | Nick Campbell
Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16)

This paper presents the multimodal Interlingual Map Task Corpus (ILMT-s2s corpus) collected at Trinity College Dublin, and discuss some of the issues related to the collection and analysis of the data. The corpus design is inspired by the HCRC Map Task Corpus which was initially designed to support the investigation of linguistic phenomena, and has been the focus of a variety of studies of communicative behaviour. The simplicity of the task, and the complexity of phenomena it can elicit, make the map task an ideal object of study. Although there are studies that used replications of the map task to investigate communication in computer mediated tasks, this ILMT-s2s corpus is, to the best of our knowledge, the first investigation of communicative behaviour in the presence of three additional “filters”: Automatic Speech Recognition (ASR), Machine Translation (MT) and Text To Speech (TTS) synthesis, where the instruction giver and the instruction follower speak different languages. This paper details the data collection setup and completed annotation of the ILMT-s2s corpus, and outlines preliminary results obtained from the data.

2013

pdf bib
WebWOZ: A Platform for Designing and Conducting Web-based Wizard of Oz Experiments
Stephan Schlögl | Saturnino Luz | Gavin Doherty
Proceedings of the SIGDIAL 2013 Conference

2011

pdf bib
A Cross-Linguistic Study on the Production of Multimodal Referring Expressions in Dialogue
Ielka van der Sluis | Saturnino Luz
Proceedings of the 13th European Workshop on Natural Language Generation

pdf bib
Production of Demonstratives in Dutch, English and Portuguese Dialogues
Saturnino Luz | Ielka van der Sluis
Proceedings of the 13th European Workshop on Natural Language Generation

pdf bib
Speaker alignment in synthesised, machine translation communication
Anne H. Schneider | Saturnino Luz
Proceedings of the 8th International Workshop on Spoken Language Translation: Papers

The effect of mistranslations on the verbal behaviour of users of speech-to-speech translation is investigated through a question answering experiment in which users were presented with machine translated questions through synthesized speech. Results show that people are likely to align their verbal behaviour to the output of a system that combines machine translation, speech recognition and speech synthesis in an interactive dialogue context, even when the system produces erroneous output. The alignment phenomenon has been previously considered by dialogue system designers from the perspective of the benefits it might bring to the interaction (e.g. by making the user more likely to employ terms contained in the system’s vocabulary). In contrast, our results reveal that in speech-to-speech translation systems alignment can in fact be detrimental to the interaction (e.g. by priming the user to align with non-existing lexical items produced by mistranslation). The implications of these findings are discussed with respect to the design of such systems.

2010

pdf bib
Assessing the effectiveness of conversational features for dialogue segmentation in medical team meetings and in the AMI corpus
Saturnino Luz | Jing Su
Proceedings of the SIGDIAL 2010 Conference

pdf bib
Comparing intrinsic and extrinsic evaluation of MT output in a dialogue system
Anne H. Schneider | Ielka van der Sluis | Saturnino Luz
Proceedings of the 7th International Workshop on Spoken Language Translation: Papers

pdf bib
Translation practice in the workplace and Machine Translation
Nikiforos Karamanis | Saturnino Luz | Gavin Doherty
Proceedings of the 14th Annual conference of the European Association for Machine Translation

2009

pdf bib
Exploring Multilingual Semantic Role Labeling
Baoli Li | Martin Emms | Saturnino Luz | Carl Vogel
Proceedings of the Thirteenth Conference on Computational Natural Language Learning (CoNLL 2009): Shared Task

2006

pdf bib
Gathering a corpus of multimodal computer-mediated meetings
Saturnino Luz | Matt-Mouley Bouamrane | Masood Masoodian
Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)

In this paper we describe the gathering of a corpus of synchronised speech and text interaction over the network. The data collection scenarios characterise audio meetings with a significant textual component. Unlike existing meeting corpora, the corpus described in this paper emphasises temporal relationships between speech and text media streams. This is achieved through detailed logging and timestamping of text editing operations, actions on shared user interface widgets and gesturing, as well as generation of speech activity profiles. A set of tools has been developed specifically for these purposes which can be used as a data collection platform for the development of meeting browsers. The data gathered to date consists of nearly 30 hours of recorded audio and time stamped editing operations and gestures.

2000

pdf bib
A Software Toolkit for Sharing and Accessing Corpora Over the Internet
Saturnino Luz
Proceedings of the Second International Conference on Language Resources and Evaluation (LREC’00)