no code implementations • LREC 2022 • Paula Carvalho, Bernardo Cunha, Raquel Santos, Fernando Batista, Ricardo Ribeiro
This paper introduces FIGHT, a dataset containing 63, 450 tweets, posted before and after the official declaration of Covid-19 as a pandemic by online users in Portugal.
no code implementations • 24 Jun 2022 • Luis Botelho, Luis Nunes, Ricardo Ribeiro, Rui J. Lopes
The current paper proposes a new set of concepts, axiom schemata and algorithms that allow the agent to learn new descriptions of an observed behaviour (e. g., perplexing actions), of its actor (e. g., undesired propositions or actions), and of its environment (e. g., incompatible propositions).
no code implementations • 7 Feb 2022 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
The development of artificial agents able to learn through dialog without domain restrictions has the potential to allow machines to learn how to perform tasks in a similar manner to humans and change how we relate to them.
no code implementations • 26 Jan 2021 • Gonçalo Cunha, Pedro Vicente, Alexandre Bernardino, Ricardo Ribeiro, Plínio Moreno
The results show cost-sensitive active learning has similar accuracy to the standard active learning approach, while reducing in about half the executed movement.
no code implementations • LREC 2020 • Eug{\'e}nio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Although this does not lead to a complete annotation according to the standard, the 347 dialogs provide a relevant amount of data that can be used in the development of automatic communicative function recognition approaches, which may lead to a wider adoption of the standard.
no code implementations • 7 Mar 2020 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
We explore the recognition of general-purpose communicative functions in the DialogBank, which is a reference set of dialogs annotated according to this standard.
no code implementations • 29 Jul 2019 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Concerning the single-label classification problem posed by the top level, we show that the conclusions drawn on English data also hold on Spanish data.
no code implementations • 20 Jun 2019 • Francisco Afonso Raposo, David Martins de Matos, Ricardo Ribeiro
We further show that joint modeling of several subjects increases the semantic richness of the learned latent vector spaces.
no code implementations • SEMEVAL 2019 • Eug{\'e}nio Ribeiro, V{\^a}nia Mendon{\c{c}}a, Ricardo Ribeiro, David Martins de Matos, Alberto Sardinha, Ana L{\'u}cia Santos, Lu{\'\i}sa Coheur
We approach all the subtasks by applying a graph clustering algorithm on contextualized embedding representations of the verbs and arguments.
no code implementations • 25 Mar 2019 • Francisco Afonso Raposo, David Martins de Matos, Ricardo Ribeiro
Music semantics is embodied, in the sense that meaning is biologically mediated by and grounded in the human body and brain.
no code implementations • 23 Jul 2018 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Recently, most approaches to the task explored different DNN architectures to combine the representations of the words in a segment and generate a segment representation that provides cues for intention.
no code implementations • 18 May 2018 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
In both cases, the experiments not only show that character-level tokenization leads to better performance than the typical word-level approaches, but also that both approaches are able to capture complementary information.
no code implementations • 14 Dec 2017 • Francisco Raposo, David Martins de Matos, Ricardo Ribeiro, Suhua Tang, Yi Yu
Modeling of music audio semantics has been previously tackled through learning of mappings from audio data to high-level tags or latent unsupervised spaces.
no code implementations • 18 Jan 2017 • Eugénio Ribeiro, Fernando Batista, Isabel Trancoso, José Lopes, Ricardo Ribeiro, David Martins de Matos
Identifying the level of expertise of its users is important for a system since it can lead to a better interaction through adaptation techniques.
no code implementations • 7 Dec 2016 • Francisco Raposo, David Martins de Matos, Ricardo Ribeiro
Our results suggest that relative entropy is a good predictor of summarization performance in the context of tasks relying on a bag-of-features model.
no code implementations • 5 Dec 2016 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
Furthermore, these are dialogs from a widely explored corpus for dialog related tasks.
no code implementations • 8 Jun 2016 • Jaime Ferreira, David Martins de Matos, Ricardo Ribeiro
We present xokde++, a state-of-the-art online kernel density estimation approach that maintains Gaussian mixture models input data streams.
no code implementations • LREC 2016 • Fern Batista, o, Pedro Curto, Isabel Trancoso, Alberto Abad, Jaime Ferreira, Eug{\'e}nio Ribeiro, Helena Moniz, David Martins de Matos, Ricardo Ribeiro
This paper presents SPA, a web-based Speech Analytics platform that integrates several speech processing modules and that makes it possible to use them through the web.
no code implementations • 12 Nov 2015 • Luis Botelho, Luis Nunes, Ricardo Ribeiro, Rui J. Lopes
The first-person or intrinsic meaning of an entity to a system is defined as its relation with the system's goals and capabilities, given the properties of the environment in which it operates.
no code implementations • 13 Aug 2015 • Paulo Figueiredo, Marta Aparício, David Martins de Matos, Ricardo Ribeiro
We explore methods for content selection and address the issue of coherence in the context of the generation of multimedia artifacts.
no code implementations • SEMEVAL 2015 • Luís Marujo, Ricardo Ribeiro, David Martins de Matos, João P. Neto, Anatole Gershman, Jaime Carbonell
The increasing amount of online content motivated the development of multi-document summarization methods.
no code implementations • 3 Jun 2015 • Marta Aparício, Paulo Figueiredo, Francisco Raposo, David Martins de Matos, Ricardo Ribeiro, Luís Marujo
We assess the performance of generic text summarization algorithms applied to films and documentaries, using the well-known behavior of summarization of news articles as reference.
no code implementations • 2 Jun 2015 • Eugénio Ribeiro, Ricardo Ribeiro, David Martins de Matos
We performed experiments on the widely explored Switchboard corpus, as well as on data annotated according to the recent ISO 24617-2 standard.
no code implementations • 31 Mar 2015 • António Lopes, David Martins de Matos, Vera Cabarrão, Ricardo Ribeiro, Helena Moniz, Isabel Trancoso, Ana Isabel Mata
Discourse markers are universal linguistic events subject to language variation.
no code implementations • 23 Mar 2015 • Francisco Raposo, Ricardo Ribeiro, David Martins de Matos
We evaluate the summarization process on binary and multiclass music genre classification tasks, by comparing the performance obtained using summarized datasets against the performances obtained using continuous segments (which is the traditional method used for addressing the previously mentioned time constraints) and full songs of the same original dataset.
no code implementations • 18 Jun 2014 • Francisco Raposo, Ricardo Ribeiro, David Martins de Matos
Several generic summarization algorithms were developed in the past and successfully applied in fields such as text and speech summarization.
no code implementations • 17 Jun 2014 • Pedro Girão Antunes, David Martins de Matos, Ricardo Ribeiro, Isabel Trancoso
In late 2011, Fado was elevated to the oral and intangible heritage of humanity by UNESCO.
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.
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.
no code implementations • 16 Jan 2014 • Ricardo Ribeiro, David Martins de Matos
In automatic summarization, centrality-as-relevance means that the most important content of an information source, or a collection of information sources, corresponds to the most central passages, considering a representation where such notion makes sense (graph, spatial, etc.).
no code implementations • 20 Jun 2013 • Luis Marujo, Ricardo Ribeiro, David Martins de Matos, João P. Neto, Anatole Gershman, Jaime Carbonell
Key phrases are often used to index the document or as features in further processing.