Publications

Post-Editing Extractive Summaries by Definiteness Prediction
Jad Kabbara
Jackie Chi Kit Cheung
Extractive summarization has been the mainstay of automatic summarization for decades. Despite all the progress, extractive summarizers stil… (voir plus)l 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 post-editing 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.
2021-10-31
Findings of the Association for Computational Linguistics: EMNLP 2021 (publié)
doi.org
Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
Zijing Ou
Qinliang Su
Jianxing Yu
Ruihui Zhao
Yefeng Zheng
Bang Liu
Existing unsupervised document hashing methods are mostly established on generative models. Due to the difficulties of capturing long depend… (voir plus)ency structures, these methods rarely model the raw documents directly, but instead to model the features extracted from them (e.g. bag-of-words (BOW), TFIDF). In this paper, we propose to learn hash codes from BERT embeddings after observing their tremendous successes on downstream tasks. As a first try, we modify existing generative hashing models to accommodate the BERT embeddings. However, little improvement is observed over the codes learned from the old BOW or TFIDF features. We attribute this to the reconstruction requirement in the generative hashing, which will enforce irrelevant information that is abundant in the BERT embeddings also compressed into the codes. To remedy this issue, a new unsupervised hashing paradigm is further proposed based on the mutual information (MI) maximization principle. Specifically, the method first constructs appropriate global and local codes from the documents and then seeks to maximize their mutual information. Experimental results on three benchmark datasets demonstrate that the proposed method is able to generate hash codes that outperform existing ones learned from BOW features by a substantial margin.
2021-10-31
Findings of the Association for Computational Linguistics: EMNLP 2021 (publié)
doi.org
arxiv.org
Sometimes We Want Ungrammatical Translations
Prasanna Parthasarathi
Koustuv Sinha
Joelle Pineau
Adina Williams
Rapid progress in Neural Machine Translation (NMT) systems over the last few years has focused primarily on improving translation quality, a… (voir plus)nd as a secondary focus, improving robustness to perturbations (e.g. spelling). While performance and robustness are important objectives, by over-focusing on these, we risk overlooking other important properties. In this paper, we draw attention to the fact that for some applications, faithfulness to the original (input) text is important to preserve, even if it means introducing unusual language patterns in the (output) translation. We propose a simple, novel way to quantify whether an NMT system exhibits robustness or faithfulness, by focusing on the case of word-order perturbations. We explore a suite of functions to perturb the word order of source sentences without deleting or injecting tokens, and measure their effects on the target side. Across several experimental conditions, we observe a strong tendency towards robustness rather than faithfulness. These results allow us to better understand the trade-off between faithfulness and robustness in NMT, and opens up the possibility of developing systems where users have more autonomy and control in selecting which prop-erty is best suited for their use case.
2021-10-31
Empirical Methods in Natural Language Processing (inconnu)
doi.org
Textual Time Travel: A Temporally Informed Approach to Theory of Mind
Akshatha Arodi
Jackie CK Cheung
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.
2021-10-31
Findings of the Association for Computational Linguistics: EMNLP 2021 (publié)
doi.org
The meaning of significant mean group differences for biomarker discovery
Eva Loth
Jumana Ahmad
Chris Chatham
Beatriz López
Ben Carter
Daisy Crawley
Bethany Oakley
Hannah Hayward
Jennifer Cooke
Antonia San José Cáceres
Danilo Bzdok
Emily Jones
Tony Charman
Christian Beckmann
Thomas Bourgeron
Roberto Toro
Jan Buitelaar
Declan Murphy
Guillaume Dumas
Over the past decade, biomarker discovery has become a key goal in psychiatry to aid in the more reliable diagnosis and prognosis of heterog… (voir plus)eneous psychiatric conditions and the development of tailored therapies. Nevertheless, the prevailing statistical approach is still the mean group comparison between “cases” and “controls,” which tends to ignore within-group variability. In this educational article, we used empirical data simulations to investigate how effect size, sample size, and the shape of distributions impact the interpretation of mean group differences for biomarker discovery. We then applied these statistical criteria to evaluate biomarker discovery in one area of psychiatric research—autism research. Across the most influential areas of autism research, effect size estimates ranged from small (d = 0.21, anatomical structure) to medium (d = 0.36 electrophysiology, d = 0.5, eye-tracking) to large (d = 1.1 theory of mind). We show that in normal distributions, this translates to approximately 45% to 63% of cases performing within 1 standard deviation (SD) of the typical range, i.e., they do not have a deficit/atypicality in a statistical sense. For a measure to have diagnostic utility as defined by 80% sensitivity and 80% specificity, Cohen’s d of 1.66 is required, with still 40% of cases falling within 1 SD. However, in both normal and nonnormal distributions, 1 (skewness) or 2 (platykurtic, bimodal) biologically plausible subgroups may exist despite small or even nonsignificant mean group differences. This conclusion drastically contrasts the way mean group differences are frequently reported. Over 95% of studies omitted the “on average” when summarising their findings in their abstracts (“autistic people have deficits in X”), which can be misleading as it implies that the group-level difference applies to all individuals in that group. We outline practical approaches and steps for researchers to explore mean group comparisons for the discovery of stratification biomarkers.
2021-10-31
PLoS Computational Biology (publié)
doi.org
The Topic Confusion Task: A Novel Evaluation Scenario for Authorship Attribution
Malik H. Altakrori
Jackie CK Cheung
Benjamin C. M. Fung
2021-10-31
Findings of the Association for Computational Linguistics: EMNLP 2021 (publié)
doi.org
arxiv.org
Visually Grounded Reasoning across Languages and Cultures
Fangyu Liu
Emanuele Bugliarello
Edoardo Ponti
Siva Reddy
Nigel Collier
Desmond Elliott
The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and … (voir plus)images of ImageNet. While one can hardly overestimate how much this benchmark contributed to progress in computer vision, it is mostly derived from lexical databases and image queries in English, resulting in source material with a North American or Western European bias. Therefore, we devise a new protocol to construct an ImageNet-style hierarchy representative of more languages and cultures. In particular, we let the selection of both concepts and images be entirely driven by native speakers, rather than scraping them automatically. Specifically, we focus on a typologically diverse set of languages, namely, Indonesian, Mandarin Chinese, Swahili, Tamil, and Turkish. On top of the concepts and images obtained through this new protocol, we create a multilingual dataset for Multicultural Reasoning over Vision and Language (MaRVL) by eliciting statements from native speaker annotators about pairs of images. The task consists of discriminating whether each grounded statement is true or false. We establish a series of baselines using state-of-the-art models and find that their cross-lingual transfer performance lags dramatically behind supervised performance in English. These results invite us to reassess the robustness and accuracy of current state-of-the-art models beyond a narrow domain, but also open up new exciting challenges for the development of truly multilingual and multicultural systems.
2021-10-31
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (publié)
doi.org
openreview.net
THE EFFECT SIZE OF GENES ON COGNITIVE ABILITIES IS LINKED TO THEIR EXPRESSION ALONG THE MAJOR HIERARCHICAL GRADIENT IN THE HUMAN BRAIN
Sébastien Jacquemont
Guillaume Huguet
Élise Douard
Zohra Saci
Guillaume Dumas
Laura Almasy
David C. Glahn
2021-10-30
European Neuropsychopharmacology (publié)
doi.org
From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence
Nicholas Roy
Ingmar Posner
T. Barfoot
Philippe Beaudoin
Yoshua Bengio
Jeannette Bohg
Oliver Brock
Isabelle Depatie
Dieter Fox
D. Koditschek
Tom'as Lozano-p'erez
Vikash K. Mansinghka
Christopher Pal
Blake Aaron Richards
Dorsa Sadigh
Stefan Schaal
G. Sukhatme
Denis Therien
Marc Emile Toussaint
Michiel van de Panne
2021-10-27
ArXiv (prépublication)
arxiv.org
arxiv.org
How do AI systems fail socially?: an engineering risk analysis approach
Shalaleh Rismani
AJung Moon
Failure Mode and Effect Analysis (FMEA) has been used as an engineering risk assessment tool since 1949. FMEAs are effective in preemptively… (voir plus) identifying and addressing how a device or process might fail in operation and are often used in the design of high-risk technology applications such as military, automotive industry and medical devices. In this work, we explore whether FMEAs can serve as a risk assessment tool for machine learning practitioners, especially in deploying systems for high-risk applications (e.g. algorithms for recidivism assessment). In particular, we discuss how FMEAs can be used to identify social and ethical failures of Artificial Intelligent Systemss (AISs), recognizing that FMEAs have the potential to uncover a broader range of failures. We first propose a process for developing a Social FMEAs (So-FMEAs) by building on the existing FMEAs framework and a recently published definition of Social Failure Modes by Millar. We then demonstrate a simple proof-of-concept, So-FMEAs for the COMPAS algorithm, a risk assessment tool used by judges to make recidivism-related decisions for convicted individuals. Through this preliminary investigation, we illustrate how a traditional engineering risk management tool could be adapted for analyzing social and ethical failures of AIS. Engineers and designers of AISs can use this new approach to improve their system's design and perform due diligence with respect to potential ethical and social failures.
2021-10-27
2021 IEEE International Symposium on Ethics in Engineering, Science and Technology (ETHICS) (publié)
doi.org
Rademacher Random Projections with Tensor Networks
Beheshteh T. Rakhshan
Guillaume Rabusseau
Random projection (RP) have recently emerged as popular techniques in the machine learning community for their ability in reducing the dimen… (voir plus)sion of very high-dimensional tensors. Following the work in [30], we consider a tensorized random projection relying on Tensor Train (TT) decomposition where each element of the core tensors is drawn from a Rademacher distribution. Our theoretical results reveal that the Gaussian low-rank tensor represented in compressed form in TT format in [30] can be replaced by a TT tensor with core elements drawn from a Rademacher distribution with the same embedding size. Experiments on synthetic data demonstrate that tensorized Rademacher RP can outperform the tensorized Gaussian RP studied in [30]. In addition, we show both theoretically and experimentally, that the tensorized RP in the Matrix Product Operator (MPO) format is not a Johnson-Lindenstrauss transform (JLT) and therefore not a well-suited random projection map
2021-10-25
ArXiv (prépublication)
arxiv.org
arxiv.org
Data-Driven Learning of Geometric Scattering Modules for GNNs
Alexander Tong
Frederick Wenkel
Kincaid MacDonald
Smita Krishnaswamy
Guy Wolf
We propose a new graph neural network (GNN) module, based on relaxations of recently proposed geometric scattering transforms, which consist… (voir plus) of a cascade of graph wavelet filters. Our learnable geometric scattering (LEGS) module enables adaptive tuning of the wavelets to encourage band-pass features to emerge in learned representations. The incorporation of our LEGS-module in GNNs enables the learning of longer-range graph relations compared to many popular GNNs, which often rely on encoding graph structure via smoothness or similarity between neighbors. Further, its wavelet priors result in simplified architectures with significantly fewer learned parameters compared to competing GNNs. We demonstrate the predictive performance of LEGS-based networks on graph classification benchmarks, as well as the descriptive quality of their learned features in biochemical graph data exploration tasks.
2021-10-24
PubMed Central (accepté)
doi.org
arxiv.org