no code implementations • ACL 2016 • Teng Long, Ryan Lowe, Jackie Chi Kit Cheung, Doina Precup
Recent work in learning vector-space embeddings for multi-relational data has focused on combining relational information derived from knowledge bases with distributional information derived from large text corpora.
no code implementations • COLING 2016 • Victor Chenal, Jackie Chi Kit Cheung
We examine the task of aggregation in the context of text-to-text generation.
no code implementations • COLING 2016 • Jad Kabbara, Yulan Feng, Jackie Chi Kit Cheung
We examine the potential of recurrent neural networks for handling pragmatic inferences involving complex contextual cues for the task of article usage prediction.
no code implementations • WS 2017 • Michael Noseworthy, Jackie Chi Kit Cheung, Joelle Pineau
We then propose a turn-based hierarchical neural network model that can be used to predict success without requiring a structured goal definition.
no code implementations • EMNLP 2017 • Teng Long, Emmanuel Bengio, Ryan Lowe, Jackie Chi Kit Cheung, Doina Precup
Humans interpret texts with respect to some background information, or world knowledge, and we would like to develop automatic reading comprehension systems that can do the same.
no code implementations • WS 2018 • Stanisław Jastrzębski, Dzmitry Bahdanau, Seyedarian Hosseini, Michael Noukhovitch, Yoshua Bengio, Jackie Chi Kit Cheung
Commonsense knowledge bases such as ConceptNet represent knowledge in the form of relational triples.
1 code implementation • SEMEVAL 2018 • Kian Kenyon-Dean, Jackie Chi Kit Cheung, Doina Precup
This work provides insight and motivating results for a new general approach to solving coreference and clustering problems with representation learning.
no code implementations • SEMEVAL 2018 • Laura Kallmeyer, Behrang Qasemizadeh, Jackie Chi Kit Cheung
We present a method for unsupervised lexical frame acquisition at the syntax{--}semantics interface.
no code implementations • NAACL 2018 • Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
We introduce an automatic system that performs well on two common-sense reasoning tasks, the Winograd Schema Challenge (WSC) and the Choice of Plausible Alternatives (COPA).
no code implementations • 11 Jun 2018 • Andre Cianflone, Yulan Feng, Jad Kabbara, Jackie Chi Kit Cheung
We introduce the task of predicting adverbial presupposition triggers such as also and again.
no code implementations • ACL 2018 • Andre Cianflone, Yulan Feng, Jad Kabbara, Jackie Chi Kit Cheung
We introduce the novel task of predicting adverbial presupposition triggers, which is useful for natural language generation tasks such as summarization and dialogue systems.
1 code implementation • EMNLP 2018 • Yue Dong, Yikang Shen, Eric Crawford, Herke van Hoof, Jackie Chi Kit Cheung
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels.
Ranked #10 on Extractive Text Summarization on CNN / Daily Mail
1 code implementation • EMNLP 2018 • Koustuv Sinha, Yue Dong, Jackie Chi Kit Cheung, Derek Ruths
Deep neural networks have been displaying superior performance over traditional supervised classifiers in text classification.
no code implementations • EMNLP 2018 • Ali Emami, Noelia De La Cruz, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
We introduce an automatic system that achieves state-of-the-art results on the Winograd Schema Challenge (WSC), a common sense reasoning task that requires diverse, complex forms of inference and knowledge.
Ranked #65 on Coreference Resolution on Winograd Schema Challenge
1 code implementation • ACL 2019 • Ali Emami, Paul Trichelair, Adam Trischler, Kaheer Suleman, Hannes Schulz, Jackie Chi Kit Cheung
To explain this performance gap, we show empirically that state-of-the art models often fail to capture context, instead relying on the gender or number of candidate antecedents to make a decision.
1 code implementation • IJCNLP 2019 • Paul Trichelair, Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
Recent studies have significantly improved the state-of-the-art on common-sense reasoning (CSR) benchmarks like the Winograd Schema Challenge (WSC) and SWAG.
Ranked #36 on Coreference Resolution on Winograd Schema Challenge
no code implementations • 21 Nov 2018 • Pengfei Liu, Shuaichen Chang, Xuanjing Huang, Jian Tang, Jackie Chi Kit Cheung
Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention.
no code implementations • 26 Nov 2018 • Pengfei Liu, Jie Fu, Yue Dong, Xipeng Qiu, Jackie Chi Kit Cheung
We present two architectures for multi-task learning with neural sequence models.
1 code implementation • 18 Dec 2018 • Kian Kenyon-Dean, Andre Cianflone, Lucas Page-Caccia, Guillaume Rabusseau, Jackie Chi Kit Cheung, Doina Precup
The standard loss function used to train neural network classifiers, categorical cross-entropy (CCE), seeks to maximize accuracy on the training data; building useful representations is not a necessary byproduct of this objective.
1 code implementation • ICML 2020 • Peng Xu, Jackie Chi Kit Cheung, Yanshuai Cao
The variational autoencoder (VAE) can learn the manifold of natural images on certain datasets, as evidenced by meaningful interpolating or extrapolating in the continuous latent space.
1 code implementation • ACL 2019 • Peng Xu, Hamidreza Saghir, Jin Sung Kang, Teng Long, Avishek Joey Bose, Yanshuai Cao, Jackie Chi Kit Cheung
Coherence is an important aspect of text quality and is crucial for ensuring its readability.
no code implementations • NAACL 2019 • Krtin Kumar, Jackie Chi Kit Cheung
Neural abstractive summarizers generate summary texts using a language model conditioned on the input source text, and have recently achieved high ROUGE scores on benchmark summarization datasets.
1 code implementation • ACL 2019 • Yue Dong, Zichao Li, Mehdi Rezagholizadeh, Jackie Chi Kit Cheung
We present the first sentence simplification model that learns explicit edit operations (ADD, DELETE, and KEEP) via a neural programmer-interpreter approach.
Ranked #2 on Text Simplification on PWKP / WikiSmall (SARI metric)
1 code implementation • IJCNLP 2019 • Meng Cao, Jackie Chi Kit Cheung
Referring Expression Generation (REG) is the task of generating contextually appropriate references to entities.
no code implementations • IJCNLP 2019 • Matt Grenander, Yue Dong, Jackie Chi Kit Cheung, Annie Louis
Sentence position is a strong feature for news summarization, since the lead often (but not always) summarizes the key points of the article.
no code implementations • 10 Nov 2019 • Teng Long, Yanshuai Cao, Jackie Chi Kit Cheung
Variational autoencoders (VAEs) hold great potential for modelling text, as they could in theory separate high-level semantic and syntactic properties from local regularities of natural language.
no code implementations • WS 2019 • Ian Porada, Kaheer Suleman, Jackie Chi Kit Cheung
Previous work has focused specifically on modeling physical plausibility and shown that distributional methods fail when tested in a supervised setting.
no code implementations • 29 Nov 2019 • Edward Newell, Kian Kenyon-Dean, Jackie Chi Kit Cheung
Uncontextualized word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications.
no code implementations • EMNLP 2020 • Yue Dong, Shuohang Wang, Zhe Gan, Yu Cheng, Jackie Chi Kit Cheung, Jingjing Liu
Pre-trained neural abstractive summarization systems have dominated extractive strategies on news summarization performance, at least in terms of ROUGE.
1 code implementation • EMNLP 2020 • Jiapeng Wu, Meng Cao, Jackie Chi Kit Cheung, William L. Hamilton
Our analysis also reveals important sources of variability both within and across TKG datasets, and we introduce several simple but strong baselines that outperform the prior state of the art in certain settings.
1 code implementation • EMNLP 2020 • Meng Cao, Yue Dong, Jiapeng Wu, Jackie Chi Kit Cheung
Experimental results show that our model is able to correct factual errors in summaries generated by other neural summarization models and outperforms previous models on factual consistency evaluation on the CNN/DailyMail dataset.
1 code implementation • COLING 2020 • Jingyi He, KC Tsiolis, Kian Kenyon-Dean, Jackie Chi Kit Cheung
Word embeddings are trained to predict word cooccurrence statistics, which leads them to possess different lexical properties (syntactic, semantic, etc.)
no code implementations • COLING 2020 • Ali Emami, Adam Trischler, Kaheer Suleman, Jackie Chi Kit Cheung
The Winograd Schema Challenge (WSC) and variants inspired by it have become important benchmarks for common-sense reasoning (CSR).
no code implementations • EMNLP 2020 • Kian Kenyon-Dean, Edward Newell, Jackie Chi Kit Cheung
Word embeddings are reliable feature representations of words used to obtain high quality results for various NLP applications.
1 code implementation • Joint Conference on Lexical and Computational Semantics 2020 • Abhilasha Ravichander, Eduard Hovy, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
In particular, we demonstrate through a simple consistency probe that the ability to correctly retrieve hypernyms in cloze tasks, as used in prior work, does not correspond to systematic knowledge in BERT.
1 code implementation • ACL 2021 • Peng Xu, Dhruv Kumar, Wei Yang, Wenjie Zi, Keyi Tang, Chenyang Huang, Jackie Chi Kit Cheung, Simon J. D. Prince, Yanshuai Cao
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.
no code implementations • Findings (ACL) 2021 • Yue Dong, Chandra Bhagavatula, Ximing Lu, Jena D. Hwang, Antoine Bosselut, Jackie Chi Kit Cheung, Yejin Choi
Despite considerable advancements with deep neural language models (LMs), neural text generation still suffers from degeneration: the generated text is repetitive, generic, self-contradictory, and often lacks commonsense.
1 code implementation • EACL 2021 • Yue Dong, Andrei Mircea, Jackie Chi Kit Cheung
We propose an unsupervised graph-based ranking model for extractive summarization of long scientific documents.
no code implementations • 17 Apr 2021 • Malik H. Altakrori, Jackie Chi Kit Cheung, Benjamin C. M. Fung
Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors.
no code implementations • ACL 2022 • Michaela Socolof, Jackie Chi Kit Cheung, Michael Wagner, Timothy J. O'Donnell
Second, the non-canonical meanings of words in an idiom are contingent on the presence of other words in the idiom.
1 code implementation • 17 Apr 2021 • Jiapeng Wu, Yishi Xu, Yingxue Zhang, Chen Ma, Mark Coates, Jackie Chi Kit Cheung
The model has to adapt to changes in the TKG for efficient training and inference while preserving its performance on historical knowledge.
1 code implementation • NAACL 2021 • Ian Porada, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
Understanding natural language requires common sense, one aspect of which is the ability to discern the plausibility of events.
no code implementations • ACL 2021 • Ali Emami, Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
A false contract is more likely to be rejected than a contract is, yet a false key is less likely than a key to open doors.
1 code implementation • ACL 2022 • Meng Cao, Yue Dong, Jackie Chi Kit Cheung
State-of-the-art abstractive summarization systems often generate \emph{hallucinations}; i. e., content that is not directly inferable from the source text.
Abstractive Text Summarization Reinforcement Learning (RL) +1
no code implementations • NAACL 2022 • Ian Porada, Alessandro Sordoni, Jackie Chi Kit Cheung
Transformer models pre-trained with a masked-language-modeling objective (e. g., BERT) encode commonsense knowledge as evidenced by behavioral probes; however, the extent to which this knowledge is acquired by systematic inference over the semantics of the pre-training corpora is an open question.
1 code implementation • Findings (ACL) 2022 • Kushal Arora, Layla El Asri, Hareesh Bahuleyan, Jackie Chi Kit Cheung
Current language generation models suffer from issues such as repetition, incoherence, and hallucinations.
no code implementations • 24 May 2022 • Yu Lu Liu, Rachel Bawden, Thomas Scialom, Benoît Sagot, Jackie Chi Kit Cheung
In text summarization and simplification, system outputs must be evaluated along multiple dimensions such as relevance, factual consistency, fluency, and grammaticality, and a wide range of possible outputs could be of high quality.
1 code implementation • 15 Dec 2022 • Akshatha Arodi, Martin Pömsl, Kaheer Suleman, Adam Trischler, Alexandra Olteanu, Jackie Chi Kit Cheung
In this work, we propose a test suite of coreference resolution subtasks that require reasoning over multiple facts.
1 code implementation • 16 Feb 2023 • Meng Cao, Yue Dong, Jingyi He, Jackie Chi Kit Cheung
State-of-the-art abstractive summarization systems frequently hallucinate content that is not supported by the source document, mainly due to noise in the training dataset.
1 code implementation • 27 Feb 2023 • Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung, Samira Shabanian
Other methods rely on rule-based or prompt-based token elimination, which are limited as they dismiss future tokens and the overall meaning of the complete discourse.
no code implementations • 16 Mar 2023 • Ian Porada, Alexandra Olteanu, Kaheer Suleman, Adam Trischler, Jackie Chi Kit Cheung
We investigate the extent to which errors of current coreference resolution models are associated with existing differences in operationalization across datasets (OntoNotes, PreCo, and Winogrande).
1 code implementation • 10 May 2023 • Rahul Aralikatte, Ziling Cheng, Sumanth Doddapaneni, Jackie Chi Kit Cheung
We present V\=arta, a large-scale multilingual dataset for headline generation in Indic languages.
no code implementations • 3 Nov 2023 • Meng Cao, Mehdi Fatemi, Jackie Chi Kit Cheung, Samira Shabanian
While large language models (LLMs) have achieved impressive performance in generating fluent and realistic text, controlling the generated text so that it exhibits properties such as safety, factuality, and non-toxicity remains challenging.
no code implementations • 18 Nov 2023 • Yu Lu Liu, Meng Cao, Su Lin Blodgett, Jackie Chi Kit Cheung, Alexandra Olteanu, Adam Trischler
We focus on how, which, and when responsible AI issues are covered, which relevant stakeholders are considered, and mismatches between stated and realized research goals.
no code implementations • 20 Jan 2024 • Yu Bai, Heyan Huang, Cesare Spinoso-Di Piano, Marc-Antoine Rondeau, Sanxing Chen, Yang Gao, Jackie Chi Kit Cheung
In-context learning (ICL) has become an effective solution for few-shot learning in natural language processing.
no code implementations • 29 Feb 2024 • Maxime Darrin, Philippe Formont, Jackie Chi Kit Cheung, Pablo Piantanida
Assessing the quality of summarizers poses significant challenges.
1 code implementation • 27 Mar 2024 • Lei Yu, Meng Cao, Jackie Chi Kit Cheung, Yue Dong
Our study investigates the mechanistic causes of hallucination, specifically non-factual ones where the LM incorrectly predicts object attributes in response to subject-relation queries.
1 code implementation • 31 Mar 2024 • Ian Porada, Xiyuan Zou, Jackie Chi Kit Cheung
When controlling for language model size, encoder-based CR models outperform more recent decoder-based models in terms of both accuracy and inference speed.
no code implementations • COLING 2022 • José Ángel González, Annie Louis, Jackie Chi Kit Cheung
In a text, entities mentioned earlier can be referred to in later discourse by a more general description.
no code implementations • Findings (EMNLP) 2021 • Akshatha Arodi, Jackie Chi Kit Cheung
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.
no code implementations • Findings (EMNLP) 2021 • Jad Kabbara, Jackie Chi Kit Cheung
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.
no code implementations • EMNLP 2020 • Cl{\'e}ment Jumel, Annie Louis, Jackie Chi Kit Cheung
Human-written texts contain frequent generalizations and semantic aggregation of content.
no code implementations • Findings (EMNLP) 2021 • Malik Altakrori, Jackie Chi Kit Cheung, Benjamin C. M. Fung
Authorship attribution is the problem of identifying the most plausible author of an anonymous text from a set of candidate authors.
no code implementations • COLING 2022 • Jad Kabbara, Jackie Chi Kit Cheung
Presuppositions are assumptions that are taken for granted by an utterance, and identifying them is key to a pragmatic interpretation of language.