16 citations · 59 across the 11 of their papers we have counts for
16 papers
Safer Together: Machine Learning Models Trained on Shared Accident Datasets Predict Construction Injuries Better than Company-Specific Models
Antoine J. -P. Tixier, Matthew R. Hallowell
In this study, we capitalized on a collective dataset repository of 57k accidents from 9 companies belonging to 3 domains and tested whether models trained on multiple datasets (ge…
FrugalScore: Learning Cheaper, Lighter and Faster Evaluation Metricsfor Automatic Text Generation
Moussa Kamal Eddine, Guokan Shang, Antoine J. -P. Tixier +1
Fast and reliable evaluation metrics are key to R&D progress. While traditional natural language generation metrics are fast, they are not very reliable. Conversely, new metrics ba…
BARThez: a Skilled Pretrained French Sequence-to-Sequence Model
Moussa Kamal Eddine, Antoine J. -P. Tixier, Michalis Vazirgiannis
Inductive transfer learning has taken the entire NLP field by storm, with models such as BERT and BART setting new state of the art on countless NLU tasks. However, most of the ava…
Speaker-change Aware CRF for Dialogue Act Classification
Guokan Shang, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis +1
Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the…
Unsupervised Word Polysemy Quantification with Multiresolution Grids of Contextual Embeddings
Christos Xypolopoulos, Antoine J. -P. Tixier, Michalis Vazirgiannis
The number of senses of a given word, or polysemy, is a very subjective notion, which varies widely across annotators and resources. We propose a novel method to estimate polysemy,…
Bidirectional Context-Aware Hierarchical Attention Network for Document Understanding
Jean-Baptiste Remy, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis
The Hierarchical Attention Network (HAN) has made great strides, but it suffers a major limitation: at level 1, each sentence is encoded in complete isolation. In this work, we pro…
Message Passing Attention Networks for Document Understanding
Giannis Nikolentzos, Antoine J. -P. Tixier, Michalis Vazirgiannis
Graph neural networks have recently emerged as a very effective framework for processing graph-structured data. These models have achieved state-of-the-art performance in many task…
AI-based Prediction of Independent Construction Safety Outcomes from Universal Attributes
Henrietta Baker, Matthew R. Hallowell, Antoine J. -P. Tixier
This paper significantly improves on, and finishes to validate, an approach proposed in previous research in which safety outcomes were predicted from attributes with machine learn…
Automatically Learning Construction Injury Precursors from Text
Henrietta Baker, Matthew R. Hallowell, Antoine J. -P. Tixier
In light of the increasing availability of digitally recorded safety reports in the construction industry, it is important to develop methods to exploit these data to improve our u…
Energy-based Self-attentive Learning of Abstractive Communities for Spoken Language Understanding
Guokan Shang, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis +1
Abstractive community detection is an important spoken language understanding task, whose goal is to group utterances in a conversation according to whether they can be jointly sum…
Notes on Deep Learning for NLP
Antoine J. -P. Tixier
My notes on Deep Learning for NLP.
Perturb and Combine to Identify Influential Spreaders in Real-World Networks
Antoine J. -P. Tixier, Maria-Evgenia G. Rossi, Fragkiskos D. Malliaros +2
Some of the most effective influential spreader detection algorithms are unstable to small perturbations of the network structure. Inspired by bagging in Machine Learning, we propo…
Unsupervised Abstractive Meeting Summarization with Multi-Sentence Compression and Budgeted Submodular Maximization
Guokan Shang, Wensi Ding, Zekun Zhang +4
We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the stren…
Kernel Graph Convolutional Neural Networks
Giannis Nikolentzos, Polykarpos Meladianos, Antoine Jean-Pierre Tixier +2
Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the featur…
Graph Classification with 2D Convolutional Neural Networks
Antoine Jean-Pierre Tixier, Giannis Nikolentzos, Polykarpos Meladianos +1
Graph learning is currently dominated by graph kernels, which, while powerful, suffer some significant limitations. Convolutional Neural Networks (CNNs) offer a very appealing alte…
Word Embeddings for the Construction Domain
Antoine J. -P. Tixier, Michalis Vazirgiannis, Matthew R. Hallowell
We introduce word vectors for the construction domain. Our vectors were obtained by running word2vec on an 11M-word corpus that we created from scratch by leveraging freely-accessi…