Search Results for author: Massimo Piccardi

Found 30 papers, 12 papers with code

Pretrained Language Models and Backtranslation for English-Basque Biomedical Neural Machine Translation

no code implementations WMT (EMNLP) 2020 Inigo Jauregi Unanue, Massimo Piccardi

This paper describes the machine translation systems proposed by the University of Technology Sydney Natural Language Processing (UTS_NLP) team for the WMT20 English-Basque biomedical translation tasks.

Machine Translation NMT +1

Controlled Text Generation with Adversarial Learning

no code implementations INLG (ACL) 2020 Federico Betti, Giorgia Ramponi, Massimo Piccardi

In recent years, generative adversarial networks (GANs) have started to attain promising results also in natural language generation.

Sentence Text Generation

Improving Vietnamese-English Medical Machine Translation

no code implementations28 Mar 2024 Nhu Vo, Dat Quoc Nguyen, Dung D. Le, Massimo Piccardi, Wray Buntine

Machine translation for Vietnamese-English in the medical domain is still an under-explored research area.

Machine Translation Sentence +1

SumTra: A Differentiable Pipeline for Few-Shot Cross-Lingual Summarization

1 code implementation20 Mar 2024 Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi

In the present day, the predominant approach to this task is to take a performing, pretrained multilingual language model (LM) and fine-tune it for XLS on the language pairs of interest.

Language Modelling Translation

A Generative Adversarial Attack for Multilingual Text Classifiers

no code implementations16 Jan 2024 Tom Roth, Inigo Jauregi Unanue, Alsharif Abuadbba, Massimo Piccardi

Current adversarial attack algorithms, where an adversary changes a text to fool a victim model, have been repeatedly shown to be effective against text classifiers.

Adversarial Attack

T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification

1 code implementation8 Jun 2023 Inigo Jauregi Unanue, Gholamreza Haffari, Massimo Piccardi

Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer).

Cross-Lingual Transfer Language Modelling +3

Traffic incident duration prediction via a deep learning framework for text description encoding

1 code implementation19 Sep 2022 Artur Grigorev, Adriana-Simona Mihaita, Khaled Saleh, Massimo Piccardi

Predicting the traffic incident duration is a hard problem to solve due to the stochastic nature of incident occurrence in space and time, a lack of information at the beginning of a reported traffic disruption, and lack of advanced methods in transport engineering to derive insights from past accidents.

A Multi-Document Coverage Reward for RELAXed Multi-Document Summarization

1 code implementation ACL 2022 Jacob Parnell, Inigo Jauregi Unanue, Massimo Piccardi

Multi-document summarization (MDS) has made significant progress in recent years, in part facilitated by the availability of new, dedicated datasets and capacious language models.

Computational Efficiency Document Summarization +2

Learning Neural Textual Representations for Citation Recommendation

no code implementations8 Jul 2020 Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi

With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming.

Citation Recommendation Sentence

Regressing Word and Sentence Embeddings for Regularization of Neural Machine Translation

no code implementations30 Sep 2019 Inigo Jauregi Unanue, Ehsan Zare Borzeshi, Massimo Piccardi

This is a serious issue for low-resource language pairs and many specialized translation domains that are inherently limited in the amount of available supervised data.

Clustering Machine Translation +4

Cluster Labeling by Word Embeddings and WordNet's Hypernymy

no code implementations ALTA 2018 Hanieh Poostchi, Massimo Piccardi

Cluster labeling is the assignment of representative labels to clusters obtained from the organization of a document collection.

Clustering Descriptive +2

Recurrent neural networks with specialized word embeddings for health-domain named-entity recognition

1 code implementation29 Jun 2017 Inigo Jauregi Unanue, Ehsan Zare Borzeshi, Massimo Piccardi

Nevertheless, the embeddings need to be retrained over datasets that are adequate for the domain, in order to adequately cover the domain-specific vocabulary.

BIG-bench Machine Learning Clinical Concept Extraction +5

Bidirectional LSTM-CRF for Clinical Concept Extraction

1 code implementation25 Nov 2016 Raghavendra Chalapathy, Ehsan Zare Borzeshi, Massimo Piccardi

Automated extraction of concepts from patient clinical records is an essential facilitator of clinical research.

Clinical Concept Extraction Word Embeddings

Action recognition in still images by latent superpixel classification

no code implementations30 Jul 2015 Shaukat Abidi, Massimo Piccardi, Mary-Anne Williams

In the proposed approach, the action class is predicted by a structural model(learnt by Latent Structural SVM) based on measurements from the image superpixels and their latent classes.

Action Recognition In Still Images Classification +2

An Adaptive Online HDP-HMM for Segmentation and Classification of Sequential Data

no code implementations10 Mar 2015 Ava Bargi, Richard Yi Da Xu, Massimo Piccardi

This infinite adaptive online approach is capable of segmenting and classifying the sequential data over unlimited number of classes, while meeting the memory and delay constraints of streaming contexts.

General Classification

A non-parametric conditional factor regression model for high-dimensional input and response

no code implementations2 Jul 2013 Ava Bargi, Richard Yi Da Xu, Massimo Piccardi

In this paper, we propose a non-parametric conditional factor regression (NCFR)model for domains with high-dimensional input and response.

Dimensionality Reduction regression

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