United States

Although large neural language models (LMs) like BERT can be finetuned to yield state-of-the-art results on many NLP tasks, it is often unclear what these models actually learn.  Here we study using such LMs to fill in entities in human-authored comparative questions, like ``Which country is older, India or _____?&#39;&#39;---i.e., we study the ability of neural LMs to ask (not answer) reasonable questions.  We show that accuracy in this fill-in-the-blank task is well-correlated with human judgements of whether a question is reasonable, and that these models can be trained to achieve nearly human-level performance in completing comparative questions in three different subdomains. However, analysis shows that what they learn fails to model any sort of broad notion of which entities are semantically comparable or similar---instead the trained models are very domain-specific, and performance is highly correlated with co-occurrences between specific entities observed in the training set.  This is true both for models that are pretrained on general text corpora, as well as models trained on a large corpus of comparison questions. Our study thus reinforces recent results on the difficulty of making claims about a deep model&#39;s world knowledge or linguistic competence based on performance on specific benchmark problems. We make our evaluation datasets publicly available to foster future research on complex understanding and reasoning in such models at standards of human interaction.

AAAI 2021

What&#39;s the Best Place for an AI Conference, Vancouver or _______: Why Completing Comparative Questions Is Difficult

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Although large neural language models (LMs) like BERT can be finetuned to yield state-of-the-art results on many NLP tasks, it is often unclear what these models actually learn.  Here we study using such LMs to fill in entities in human-authored comparative questions, like ``Which country is older, India or _____?''---i.e., we study the ability of neural LMs to ask (not answer) reasonable questions.  We show that accuracy in this fill-in-the-blank task is well-correlated with human judgements of whether a question is reasonable, and that these models can be trained to achieve nearly human-level performance in completing comparative questions in three different subdomains. However, analysis shows that what they learn fails to model any sort of broad notion of which entities are semantically comparable or similar---instead the trained models are very domain-specific, and performance is highly correlated with co-occurrences between specific entities observed in the training set.  This is true both for models that are pretrained on general text corpora, as well as models trained on a large corpus of comparison questions. Our study thus reinforces recent results on the difficulty of making claims about a deep model's world knowledge or linguistic competence based on performance on specific benchmark problems. We make our evaluation datasets publicly available to foster future research on complex understanding and reasoning in such models at standards of human interaction.

What's the Best Place for an AI Conference, Vancouver or _______: Why Completing Comparative Questions Is Difficult

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

The connection between games and no-regret algorithms has been widely studied in the literature. A fundamental result is that when all players play no-regret strategies, this produces a sequence of actions whose time-average is a coarse-correlated equilibrium of the game. However, much less is known about equilibrium selection in the case that multiple equilibria exist. In this work, we study the convergence of no-regret bidding algorithms in auctions. Besides being of theoretical interest, bidding dynamics in auctions is an important question from a practical viewpoint as well. We study the repeated game between bidders in which a single item is sold at each time step and the bidder's value is drawn from an unknown distribution. We show that if the bidders use any mean-based learning rule then the bidders converge with high probability to the truthful pure Nash Equilibrium in a second price auction, in VCG auction in the multi-slot setting and to the Bayesian Nash equilibrium in a first price auction. We note mean-based algorithms cover a wide variety of known no-regret algorithms such as Exp3, UCB, \epsilon-Greedy etc. Also, we analyze the convergence of the individual iterates produced by such learning algorithms, as opposed to the time-average of the sequence. Our experiments corroborate our theoretical findings and also find a similar convergence when we use other strategies such as Deep Q-Learning.

Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions

End-to-end neural networks have achieved promising performances in natural language generation (NLG). However, they are treated as black boxes and lack interpretability. To address this problem, we propose a novel framework, heterogeneous rendering machines (HRM), that interprets how neural generators render an input dialogue act (DA) into an utterance. HRM consists of a renderer set and a mode switcher. The renderer set contains multiple decoders that vary in both structure and functionality. For every generation step, the mode switcher selects an appropriate decoder from the renderer set to generate an item (a word or a phrase). To verify the effectiveness of our method, we have conducted extensive experiments on 5 benchmark datasets. In terms of automatic metrics (e.g., BLEU), our model is competitive with the current state-of-the-art method. The qualitative analysis shows that our model can interpret the rendering process of neural generators well. Human evaluation also confirms the interpretability of our proposed approach.

Interpretable NLG for Task-Oriented Dialogue Systems with Heterogeneous Rendering Machines

Metric clustering is fundamental in areas ranging from Combinatorial Optimization and Data Mining, to Machine Learning and Operations Research. However, in a variety of situations we may have additional requirements or knowledge, distinct from the underlying metric, regarding which pairs of points should be clustered together. To capture and analyze such scenarios, we introduce a novel family of stochastic pairwise constraints, which we incorporate into several essential clustering objectives (radius/median/means). Moreover, we demonstrate that these constraints can succinctly model an intriguing collection of applications, including among others Individual Fairness in clustering and Must-link constraints in semi-supervised learning. Our main result consists of a general framework that yields approximation algorithms with provable guarantees for important clustering objectives, while at the same time producing solutions that respect the stochastic pairwise constraints. Furthermore, for certain objectives we devise improved results in the case of Must-link constraints, which are also the best possible from a theoretical perspective. Finally, we present experimental evidence that validates the effectiveness of our algorithms.

Fairness, Semi-Supervised Learning, and More: A General Framework for Clustering with Stochastic Pairwise Constraints

Alzheimerâ€™s Disease (AD) is a chronic neurodegenerative disease that causes severe problems in patientsâ€™ thinking, memory, and behavior. An early diagnosis is crucial to prevent AD progression; to this end, many algorithmic approaches have recently been proposed to predict cognitive decline. However, these predictive models often fail to integrate heterogeneous genetic and neuroimaging biomarkers and struggle to handle missing data. In this work we propose a novel objective function and an associated optimization algorithm to identify cognitive decline related to AD. Our approach is designed to incorporate dynamic neuroimaging data by way of a participant-specific augmentation combined with multimodal data integration aligned via a regression task. Our approach, in order to incorporate additional side-information, utilizes structured regularization techniques popularized in recent AD literature. Armed with the fixed-length vector representation learned from the multimodal dynamic and static modalities, conventional machine learning methods can be used to predict the clinical outcomes associated with AD.  Our experimental results show that the proposed augmentation model improves the prediction performance on cognitive assessment scores for a collection of popular machine learning algorithms. The results of our approach are interpreted to validate existing genetic and neuroimaging biomarkers that have been shown to be predictive of cognitive decline.

Integrating Static and Dynamic Data for Improved Prediction of Cognitive Declines Using Augmented Genotype-Phenotype Representations

Probabilistic forecasting of high dimensional multivariate time series is a notoriously challenging task, both in terms of computational burden and distribution modeling. Most previous work either makes simple distribution assumptions or abandons modeling cross-series correlations.  A promising line of work exploits scalable matrix factorization for latent-space forecasting, but is limited to linear embeddings, unable to model distributions, and not trainable end-to-end when using deep learning forecasting. We introduce a novel temporal latent auto-encoder method which enables nonlinear factorization of multivariate time series, learned end-to-end with a temporal deep learning latent space forecast model. By imposing a probabilistic latent space model, complex distributions of the input series are modeled via the decoder.  
 Extensive experiments demonstrate that our model achieves state-of-the-art performance on many popular multivariate datasets, with gains sometimes as high as 50% for several standard metrics.

Temporal Latent Autoencoder: A Method for Probabilistic Multivariate Time Series Forecasting

Accurate prediction of the transmission of epidemic diseases such as COVID-19 is crucial for implementing effective mitigation measures. In this work, we develop a tensor method to predict the evolution of epidemic trends for many regions simultaneously. We construct a 3-way spatio-temporal tensor (location, attribute, time) of case counts and propose a nonnegative tensor factorization with latent epidemiological model regularization named STELAR. Unlike standard tensor factorization methods which cannot predict slabs ahead, STELAR enables long-term prediction by incorporating latent temporal regularization through a system of discrete-time difference equations of a widely adopted epidemiological model. We use latent instead of location/attribute-level epidemiological dynamics to capture common epidemic profile sub-types and improve collaborative learning and prediction. We conduct experiments using  both county- and state-level COVID-19 data and show that our model can identify interesting latent patterns of the epidemic. Finally, we evaluate the predictive ability of our method and show superior performance compared to the baselines, achieving up to 21% lower root mean square error and 25% lower mean absolute error for county-level prediction.

STELAR: Spatio-Temporal Tensor Factorization with Latent Epidemiological Regularization

We propose a hierarchical normalizing flow model for generating molecular graphs. The model produces new molecular structures from a single-node graph by recursively splitting every node into two. All operations are invertible and can be used as plug-and-play modules. The hierarchical nature of the latent codes allows for precise changes in the resulting graph: perturbations in the first layer cause global structural changes, while perturbations in the consequent layers change the resulting molecule only marginally. Proposed model outperforms existing generative graph models on the distribution learning task. We also show successful experiments on global and constrained optimization of chemical properties using latent codes of the model.

MolGrow: A Graph Normalizing Flow for Hierarchical Molecular Generation

Scores based on Shapley values are widely used for providing explanations to classification results over machine learning models. A prime example of this is the influential SHAP-score, a version of the Shapley value that can help explain the result of a learned model on a specific entity by assigning a score to every feature. While in general computing Shapley values is a computationally intractable problem, it has recently been claimed that the SHAP-score can be computed in polynomial time over the class of decision trees. In this paper, we provide a proof of a stronger result over Boolean models: the SHAP-score can be computed in polynomial time over deterministic and decomposable Boolean circuits. Such circuits, also known as tractable Boolean circuits, generalize a wide range of Boolean circuits and binary decision diagrams classes, including binary decision trees, Ordered Binary Decision Diagrams (OBDDs) and Free Binary Decision Diagrams (FBDDs). We also establish the computational limits of the notion of SHAP-score by observing that, under a mild condition, computing it over a class of Boolean models is always polynomially as hard as the model counting problem for that class. This implies that both determinism and decomposability are essential properties for the circuits that we consider, as removing one or the other renders the problem of computing the SHAP-score intractable (namely, #P-hard).

The Tractability of SHAP-Score-Based Explanations for Classification over Deterministic and Decomposable Boolean Circuits

Fairness in machine learning is getting rising attention as it is directly related to real-world applications and social problems. Recent methods have been explored to alleviate the discrimination between certain demographic groups that are characterized by sensitive attributes (such as race, age, or gender). Some studies have found that the data itself is biased, so training directly on the data causes unfair decision making. Models directly trained on raw data can replicate or even exacerbate bias in the prediction between demographic groups. This leads to vastly different prediction performance in different demographic groups. In order to address this issue, we propose a new approach to improve machine learning fairness by generating fair data. We introduce a generative model to generate cross-domain samples w.r.t. multiple sensitive attributes. This ensures that we can generate infinite number of samples that are balanced \wrt both target label and sensitive attributes to enhance fair prediction. By training the classifier solely with the synthetic data and then transfer the model to real data, we can overcome the under-representation problem which is non-trivial since collecting real data is extremely time and resource consuming. We provide empirical evidence to demonstrate the benefit of our model with respect to both fairness and accuracy.

Constructing a Fair Classifier with Generated Fair Data

We propose a hypothesis disparity regularized mutual information maximization (HDMI) approach to tackle unsupervised hypothesis transfer---as an effort towards unifying hypothesis transfer learning (HTL) and unsupervised domain adaptation (UDA)---where the knowledge from a source domain is transferred solely through hypotheses and adapted to the target domain in an unsupervised manner. In contrast to the prevalent HTL and UDA approaches that typically use a single hypothesis, HDMI employs multiple hypotheses to leverage the underlying distributions of the source and target hypotheses. To better utilize the crucial relationship among different hypotheses---as opposed to unconstrained optimization of each hypothesis independently---while adapting to the unlabeled target domain through mutual information maximization, HDMI incorporates a hypothesis disparity regularization that coordinates the target hypotheses jointly learn better target representations while preserving more transferable source knowledge with better-calibrated prediction uncertainty. HDMI achieves state-of-the-art adaptation performance on benchmark datasets for UDA in the context of HTL, without the need to access the source data during the adaptation.

Downloads

Next from AAAI 2021

Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions

Similar lecture

Entity Cloze By Date: What LMs Know About Unseen Entities

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Convergence Analysis of No-Regret Bidding Algorithms in Repeated Auctions

Similar lecture

Entity Cloze By Date: What LMs Know About Unseen Entities

Downloads