Papers by Leila Kosseim

5 papers
Cooking Up a Neural-based Model for Recipe Classification (2020.lrec-1)

Copied to clipboard

Challenge: a dataset of cooking recipes in French is highly imbalanced due to collaborative nature of the dataset . authors propose a neural-based model to address the first task of the DEFT 2013 shared task .
Approach: They propose a neural-based model to address the first task of the DEFT 2013 shared task . they use state-of-the-art embedding approaches and deep architectures to address imbalanced dataset .
Outcome: The proposed model outperforms models that use only pretrained embeddings in micro and macro F1 scores.
The Concordia NLG Surface Realizer at SRST 2019 (D19-63)

Copied to clipboard

Challenge: The goal of Natural Language Generation (NLG) is to produce natural texts given structured data.
Approach: They propose a model for the shallow track of the 2019 NLG Surface Realization Shared Task . they divided the problem into two sub-problems: reordering and inflecting .
Outcome: The proposed model reconstructs sentences whose word order and word inflections were removed.
On the Creation of a Corpus for Coherence Evaluation of Discursive Units (2020.lrec-1)

Copied to clipboard

Challenge: Most corpora for textual coherence evaluation are composed of randomly shuffled sentences that focus on sentence ordering.
Approach: They propose to use a variety of corruption strategies to build a corpus of incoherent pairs of sentences by swapping their discourse connective or a discourse argument.
Outcome: The proposed corpus is constructed from discourse argument pairs from the Penn Discourse Tree Bank and is compared with existing corpus models.
Attention for Implicit Discourse Relation Recognition (L18-1)

Copied to clipboard

Challenge: Existing approaches to implicit discourse relation recognition reach F1 scores of 9.95% to 37.67% . a neural network exploits the strong correlation between pairs of words that implicitly signal a discourse relation.
Approach: They propose a neural network which exploits strong correlation between pairs of words . they use an encoder-decoder model with attention to detect a latent discourse relation .
Outcome: The proposed model outperforms state-of-the-art models on fine-grained classification and fine-granular classification while computing parameters without pooling and fully connected layers.
TIMBERT: Toponym Identifier For The Medical Domain Based on BERT (2020.coling-main)

Copied to clipboard

Challenge: Phylogeographers have long linked the geographical spread of viruses to the growth in global tourism and international trade of goods.
Approach: They propose to automate the process of place name detection in the medical domain by learning the mapping from an input sentence to the associated sentence labeled with toponyms.
Outcome: The proposed model achieves an F1 score of 90.85%, compared to the state-of-the-art of 89.13%.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations