Search Results for author: Bruno Martins

Found 25 papers, 9 papers with code

Dense Template Retrieval for Customer Support

no code implementations COLING 2022 Tiago Mesquita, Bruno Martins, Mariana Almeida

Templated answers are used extensively in customer support scenarios, providing an efficient way to cover a plethora of topics, with an easily maintainable collection of templates.


Stress Testing BERT Anaphora Resolution Models for Reaction Extraction in Chemical Patents

no code implementations23 Jun 2023 Chieling Yueh, Evangelos Kanoulas, Bruno Martins, Camilo Thorne, Saber Akhondi

The high volume of published chemical patents and the importance of a timely acquisition of their information gives rise to automating information extraction from chemical patents.

LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting

1 code implementation31 May 2023 Rita Ramos, Bruno Martins, Desmond Elliott

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process.

Image Captioning Language Modelling +1

Retrieval-augmented Image Captioning

1 code implementation16 Feb 2023 Rita Ramos, Desmond Elliott, Bruno Martins

The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions.

Image Captioning Retrieval +1

GeoAI at ACM SIGSPATIAL: The New Frontier of Geospatial Artificial Intelligence Research

no code implementations20 Oct 2022 Dalton Lunga, Yingjie Hu, Shawn Newsam, Song Gao, Bruno Martins, Lexie Yang, Xueqing Deng

Geospatial Artificial Intelligence (GeoAI) is an interdisciplinary field enjoying tremendous adoption.

SmallCap: Lightweight Image Captioning Prompted with Retrieval Augmentation

1 code implementation CVPR 2023 Rita Ramos, Bruno Martins, Desmond Elliott, Yova Kementchedjhieva

Recent advances in image captioning have focused on scaling the data and model size, substantially increasing the cost of pre-training and finetuning.

Image Captioning Retrieval

Optimization of Artificial Neural Networks models applied to the identification of images of asteroids' resonant arguments

1 code implementation28 Jul 2022 Valerio Carruba, Safwan Aljbaae, Gabriel Caritá, Rita Cassia Domingos, Bruno Martins

Since the population of asteroids affected by these resonances is, in some cases, of the order of several thousand, this has become a taxing task for a human observer.

Data Augmentation

State of the Art in Artificial Intelligence applied to the Legal Domain

no code implementations10 Mar 2022 João Dias, Pedro A. Santos, Nuno Cordeiro, Ana Antunes, Bruno Martins, Jorge Baptista, Carlos Gonçalves

While Artificial Intelligence applied to the legal domain is a topic with origins in the last century, recent advances in Artificial Intelligence are posed to revolutionize it.

Question rewriting? Assessing its importance for conversational question answering

1 code implementation22 Jan 2022 Gonçalo Raposo, Rui Ribeiro, Bruno Martins, Luísa Coheur

In conversational question answering, systems must correctly interpret the interconnected interactions and generate knowledgeable answers, which may require the retrieval of relevant information from a background repository.

Question Rewriting Retrieval

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 Retrieval +2

Assessing the Benefits of Model Ensembles in Neural Re-Ranking for Passage Retrieval

no code implementations21 Jan 2021 Luís Borges, Bruno Martins, Jamie Callan

Our work aimed at experimentally assessing the benefits of model ensembling within the context of neural methods for passage reranking.

Learning-To-Rank Passage Retrieval +2

Combining Similarity Features and Deep Representation Learning for Stance Detection in the Context of Checking Fake News

3 code implementations2 Nov 2018 Luís Borges, Bruno Martins, Pável Calado

Specifically, we use bi-directional Recurrent Neural Networks, together with max-pooling over the temporal/sequential dimension and neural attention, for representing (i) the headline, (ii) the first two sentences of the news article, and (iii) the entire news article.

Document Classification General Classification +3

Using Rank Aggregation for Expert Search in Academic Digital Libraries

no code implementations21 Jan 2015 Catarina Moreira, Bruno Martins, Pável Calado

The task of expert finding has been getting increasing attention in information retrieval literature.

Information Retrieval Retrieval

Learning to Rank Academic Experts in the DBLP Dataset

no code implementations21 Jan 2015 Catarina Moreira, Bruno Martins, Pável Calado

More specifically, this article explores the use of supervised learning to rank methods, as well as rank aggregation approaches, for combing all of the estimators of expertise.

Information Retrieval Learning-To-Rank +1

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