Jackie Cheung

Ines Arous

Collaborateur·rice alumni - McGill

Doctorat - McGill

Collaborateur·rice de recherche

Nadhem Benhadjali

Collaborateur·rice de recherche

Meng (Caden) Cao

Collaborateur·rice alumni - McGill

Doctorat - McGill

Doctorat - McGill

Superviseur⋅e principal⋅e :

Maîtrise recherche - McGill

Nelson Filipe Costa

Collaborateur·rice de recherche - Concordia University

Maxime Darrin

Doctorat - McGill

Co-superviseur⋅e :

Doctorat - McGill

Aylin Erman

Doctorat - McGill

Co-superviseur⋅e :

Dan Poenaru

Ori Ernst

Collaborateur·rice alumni - McGill

Maîtrise recherche - McGill

Jie Gao

Collaborateur·rice de recherche - McGill University

Co-superviseur⋅e :

Nikki Lobczowski

Langlois Henri

Maîtrise recherche - Paris-Saclay University

Superviseur⋅e principal⋅e :

Pablo Piantanida

Fanny JOURDAN

Postdoctorat - École de technologie suprérieure

Superviseur⋅e principal⋅e :

Pablo Piantanida

Zichao Li

Doctorat - McGill

Superviseur⋅e principal⋅e :

Siva Reddy

Caleb Moses

Doctorat - McGill

Ian Porada

Doctorat - McGill

Sihan Qin

Baccalauréat - McGill

Michael Runningwolf

Doctorat - McGill

Sina Salmannia

Baccalauréat - McGill

Cesare Spinoso-Di Piano

Doctorat - McGill

Sihui Wei

Baccalauréat - McGill

Michael Yu

Collaborateur·rice de recherche - McGill University

Co-superviseur⋅e :

Nikki Lobczowski

Xiyuan Zou

Maîtrise recherche - McGill

Publications

Optimizing Deeper Transformers on Small Datasets

Peng Xu

Dhruv Kumar

Wei Yang

Wenjie Zi

Keyi Tang

Chenyang Huang

S. Prince

Yanshuai Cao

It is a common belief that training deep transformers from scratch requires large datasets. Consequently, for small datasets, people usually… (voir plus) use shallow and simple additional layers on top of pre-trained models during fine-tuning. This work shows that this does not always need to be the case: with proper initialization and optimization, the benefits of very deep transformers can carry over to challenging tasks with small datasets, including Text-to-SQL semantic parsing and logical reading comprehension. In particular, we successfully train 48 layers of transformers, comprising 24 fine-tuned layers from pre-trained RoBERTa and 24 relation-aware layers trained from scratch. With fewer training steps and no task-specific pre-training, we obtain the state of the art performance on the challenging cross-domain Text-to-SQL parsing benchmark Spider. We achieve this by deriving a novel Data dependent Transformer Fixed-update initialization scheme (DT-Fixup), inspired by the prior T-Fixup work. Further error analysis shows that increasing depth can help improve generalization on small datasets for hard cases that require reasoning and structural understanding.

2021-08-01

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (publié)

TIE: A Framework for Embedding-based Incremental Temporal Knowledge Graph Completion

Jiapeng Wu

Yingxue Zhang

Reasoning in a temporal knowledge graph (TKG) is a critical task for information retrieval and semantic search. It is particularly challengi… (voir plus)ng when the TKG is updated frequently. The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge. Recent work approaches TKG completion (TKGC) by augmenting the encoder-decoder framework with a time-aware encoding function. However, naively fine-tuning the model at every time step using these methods does not address the problems of 1) catastrophic forgetting, 2) the model's inability to identify the change of facts (e.g., the change of the political affiliation and end of a marriage), and 3) the lack of training efficiency. To address these challenges, we present the Time-aware Incremental Embedding (TIE) framework, which combines TKG representation learning, experience replay, and temporal regularization. We introduce a set of metrics that characterizes the intransigence of the model and propose a constraint that associates the deleted facts with negative labels. Experimental results on Wikidata12k and YAGO11k datasets demonstrate that the proposed TIE framework reduces training time by about ten times and improves on the proposed metrics compared to vanilla full-batch training. It comes without a significant loss in performance for any traditional measures. Extensive ablation studies reveal performance trade-offs among different evaluation metrics, which is essential for decision-making around real-world TKG applications.

2021-07-11

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval (publié)

Modeling Event Plausibility with Consistent Conceptual Abstraction

Ian Porada

Kaheer Suleman

Adam Trischler

2021-06-01

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (publié)

Deep Discourse Analysis for Generating Personalized Feedback in Intelligent Tutor Systems

Matt Grenander

Robert Belfer

Ekaterina Kochmar

Iulian V. Serban

Franccois St-Hilaire

We explore creating automated, personalized feedback in an intelligent tutoring system (ITS). Our goal is to pinpoint correct and incorrect … (voir plus)concepts in student answers in order to achieve better student learning gains. Although automatic methods for providing personalized feedback exist, they do not explicitly inform students about which concepts in their answers are correct or incorrect. Our approach involves decomposing students answers using neural discourse segmentation and classification techniques. This decomposition yields a relational graph over all discourse units covered by the reference solutions and student answers. We use this inferred relational graph structure and a neural classifier to match student answers with reference solutions and generate personalized feedback. Although the process is completely automated and data-driven, the personalized feedback generated is highly contextual, domain-aware and effectively targets each student's misconceptions and knowledge gaps. We test our method in a dialogue-based ITS and demonstrate that our approach results in high-quality feedback and significantly improved student learning gains.

2021-05-18

Proceedings of the AAAI Conference on Artificial Intelligence (publié)

Characterizing Idioms: Conventionality and Contingency

Michaela Socolof

Michael Wagner

Timothy O'Donnell

Idioms are unlike most phrases in two important ways. First, words in an idiom have non-canonical meanings. Second, the non-canonical meanin… (voir plus)gs of words in an idiom are contingent on the presence of other words in the idiom. Linguistic theories differ on whether these properties depend on one another, as well as whether special theoretical machinery is needed to accommodate idioms. We define two measures that correspond to the properties above, and we show that idioms fall at the expected intersection of the two dimensions, but that the dimensions themselves are not correlated. Our results suggest that introducing special machinery to handle idioms may not be warranted.

2021-04-17

ArXiv (preprint)

Discourse-Aware Unsupervised Summarization for Long Scientific Documents

Andrei Mircea

2021-04-01

Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (publié)

ADEPT: An Adjective-Dependent Plausibility Task

Ali Emami

Ian Porada

Alexandra Olteanu

Kaheer Suleman

Adam Trischler

2021-01-01

Annual Meeting of the Association for Computational Linguistics (publié)

Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization

Meng Cao

State-of-the-art abstractive summarization systems often generate hallucinations ; i.e., content that is not directly inferable from the sou… (voir plus)rce text. Despite being assumed incorrect, many of the hallucinated contents are consistent with world knowledge (factual hallucinations). Including these factual hallucinations into a summary can be beneﬁcial in providing additional background information. In this work, we propose a novel detection approach that separates factual from non-factual hallucinations of entities. Our method is based on an entity’s prior and posterior probabilities according to pre-trained and ﬁnetuned masked language models, respectively. Empirical re-sults suggest that our method vastly outperforms three strong baselines in both accuracy and F1 scores and has a strong correlation with human judgements on factuality classiﬁcation tasks. Furthermore, our approach can provide insight into whether a particular hallucination is caused by the summarizer’s pre-training or ﬁne-tuning step. 1

2021-01-01

arXiv.org (prépublication)

dblp.uni-trier.de

Inspecting the Factuality of Hallucinated Entities in Abstractive Summarization

Meng Cao

2021-01-01

arXiv.org (preprint)

dblp.uni-trier.de

On-the-Fly Attention Modularization for Neural Generation

Chandra Bhagavatula

Ximing Lu

Jena D. Hwang

Antoine Bosselut

Yejin Choi

Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from de generation: generated… (voir plus) text is repetitive, generic, self-inconsistent, and lacking commonsense. The empirical analyses on sentence-level attention patterns reveal that neural text degeneration may be associated with insufﬁcient learning of inductive biases by the attention mechanism. Our ﬁndings motivate on-the-ﬂy attention modularization, a simple but effective method for injecting inductive biases into attention computation during inference. The resulting text produced by the language model with attention modularization can yield enhanced diversity and commonsense reasoning while maintaining ﬂuency and coherence.

2021-01-01

arXiv.org (prépublication)

dblp.uni-trier.de

Post-Editing Extractive Summaries by Definiteness Prediction

Jad Kabbara

Extractive summarization has been the main-stay of automatic summarization for decades. Despite all the progress, extractive summarizers sti… (voir plus)ll suffer from shortcomings including coreference issues arising from extracting sentences away from their original context in the source document. This affects the coherence and readability of extractive summaries. In this work, we propose a lightweight postediting step for extractive summaries that centers around a single linguistic decision: the definiteness of noun phrases. We conduct human evaluation studies that show that human expert judges substantially prefer the output of our proposed system over the original summaries. Moreover, based on an automatic evaluation study, we provide evidence for our system’s ability to generate linguistic decisions that lead to improved extractive summaries. We also draw insights about how the automatic system is exploiting some local cues related to the writing style of the main article texts or summary texts to make the decisions, rather than reasoning about the contexts pragmatically.

2021-01-01

Conference on Empirical Methods in Natural Language Processing (publié)

Textual Time Travel: A Temporally Informed Approach to Theory of Mind

Akshatha Arodi

Natural language processing systems such as dialogue agents should be able to reason about other people’s beliefs, intentions and desires.… (voir plus) This capability, called theory of mind (ToM), is crucial, as it allows a model to predict and interpret the needs of users based on their mental states. A recent line of research evaluates the ToM capability of existing memoryaugmented neural models through questionanswering. These models perform poorly on false belief tasks where beliefs differ from reality, especially when the dataset contains distracting sentences. In this paper, we propose a new temporally informed approach for improving the ToM capability of memory-augmented neural models. Our model incorporates priors about the entities’ minds and tracks their mental states as they evolve over time through an extended passage. It then responds to queries through textual time travel—i.e., by accessing the stored memory of an earlier time step. We evaluate our model on ToM datasets and find that this approach improves performance, particularly by correcting the predicted mental states to match the false belief.

2021-01-01

Conference on Empirical Methods in Natural Language Processing (publié)