Search Results for author:
Found 115 papers, 49 papers with code
Temporal Generalization for Spoken Language Understanding
Spoken Language Understanding (SLU) models in industry applications are usually trained offline on historic data, but have to perform well on incoming user requests after deployment.
StATIK: Structure and Text for Inductive Knowledge Graph Completion
Knowledge graphs (KGs) often represent knowledge bases that are incomplete.
All in the (Exponential) Family: Information Geometry and Thermodynamic Variational Inference
While the Evidence Lower Bound (ELBO) has become a ubiquitous objective for variational inference, the recently proposed Thermodynamic Variational Objective (TVO) leverages thermodynamic integration to provide a tighter and more general family of bounds.
Learning Morphisms with Gauss-Newton Approximation for Growing Networks
A popular method for Neural Architecture Search (NAS) is based on growing networks via small local changes to the network's architecture called network morphisms.
Adaptive Video Understanding Agent: Enhancing efficiency with dynamic frame sampling and feedback-driven reasoning
Understanding long-form video content presents significant challenges due to its temporal complexity and the substantial computational resources required.
SeRA: Self-Reviewing and Alignment of Large Language Models using Implicit Reward Margins
Direct alignment algorithms (DAAs), such as direct preference optimization (DPO), have become popular alternatives for Reinforcement Learning from Human Feedback (RLHF) due to their simplicity, efficiency, and stability.
QuAILoRA: Quantization-Aware Initialization for LoRA
In this paper we introduce QuAILoRA, a quantization-aware initialization for LoRA that mitigates this negative impact by decreasing quantization errors at initialization.
Attribute Controlled Fine-tuning for Large Language Models: A Case Study on Detoxification
We propose a constraint learning schema for fine-tuning Large Language Models (LLMs) with attribute control.
Data Advisor: Dynamic Data Curation for Safety Alignment of Large Language Models
Starting from a set of pre-defined principles in hand, Data Advisor monitors the status of the generated data, identifies weaknesses in the current dataset, and advises the next iteration of data generation accordingly.
Tree-of-Traversals: A Zero-Shot Reasoning Algorithm for Augmenting Black-box Language Models with Knowledge Graphs
Knowledge graphs (KGs) complement Large Language Models (LLMs) by providing reliable, structured, domain-specific, and up-to-date external knowledge.
Leveraging LLMs for Dialogue Quality Measurement
In task-oriented conversational AI evaluation, unsupervised methods poorly correlate with human judgments, and supervised approaches lack generalization.
Prompt Perturbation Consistency Learning for Robust Language Models
However, their performance on sequence labeling tasks such as intent classification and slot filling (IC-SF), which is a central component in personal assistant systems, lags significantly behind discriminative models.
Contrastive Instruction Tuning
Instruction tuning has been used as a promising approach to improve the performance of large language models (LLMs) on unseen tasks.
Tokenization Matters: Navigating Data-Scarce Tokenization for Gender Inclusive Language Technologies
Our paper is the first to link LLM misgendering to tokenization and deficient neopronoun grammar, indicating that LLMs unable to correctly treat neopronouns as pronouns are more prone to misgender.
JAB: Joint Adversarial Prompting and Belief Augmentation
With the recent surge of language models in different applications, attention to safety and robustness of these models has gained significant importance.
On the steerability of large language models toward data-driven personas
Large language models (LLMs) are known to generate biased responses where the opinions of certain groups and populations are underrepresented.
FLIRT: Feedback Loop In-context Red Teaming
In this work, we propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation.
Ensembled Prediction Intervals for Causal Outcomes Under Hidden Confounding
We present a simple approach to partial identification using existing causal sensitivity models and show empirically that Caus-Modens gives tighter outcome intervals, as measured by the necessary interval size to achieve sufficient coverage.
Multi-Task Knowledge Enhancement for Zero-Shot and Multi-Domain Recommendation in an AI Assistant Application
We propose in this work to unify these approaches: Using information from interactions in other domains as well as external knowledge graphs to make predictions in a new domain that would be impossible with either information source alone.
Toward More Accurate and Generalizable Evaluation Metrics for Task-Oriented Dialogs
Measurement of interaction quality is a critical task for the improvement of spoken dialog systems.
History Repeats: Overcoming Catastrophic Forgetting For Event-Centric Temporal Knowledge Graph Completion
Temporal knowledge graph (TKG) completion models typically rely on having access to the entire graph during training.
Jointly Reparametrized Multi-Layer Adaptation for Efficient and Private Tuning
This can be a drawback for low-resource applications and training with differential-privacy constraints, where excessive noise may be introduced during finetuning.
Neural Architecture Search for Parameter-Efficient Fine-tuning of Large Pre-trained Language Models
Parameter-efficient tuning (PET) methods fit pre-trained language models (PLMs) to downstream tasks by either computing a small compressed update for a subset of model parameters, or appending and fine-tuning a small number of new model parameters to the pre-trained network.
ParaAMR: A Large-Scale Syntactically Diverse Paraphrase Dataset by AMR Back-Translation
Paraphrase generation is a long-standing task in natural language processing (NLP).
Graph Meets LLM: A Novel Approach to Collaborative Filtering for Robust Conversational Understanding
This paper presents our "Collaborative Query Rewriting" approach, which specifically addresses the task of rewriting new user interactions that have not been previously observed in the user's history.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+9
Measuring and Mitigating Local Instability in Deep Neural Networks
We formulate the model stability problem by studying how the predictions of a model change, even when it is retrained on the same data, as a consequence of stochasticity in the training process.
"I'm fully who I am": Towards Centering Transgender and Non-Binary Voices to Measure Biases in Open Language Generation
Transgender and non-binary (TGNB) individuals disproportionately experience discrimination and exclusion from daily life.
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
We take the first step by focusing on event commonsense that considers events and their relations, and is crucial in both dialogues and general commonsense reasoning.
Is the Elephant Flying? Resolving Ambiguities in Text-to-Image Generative Models
Natural language often contains ambiguities that can lead to misinterpretation and miscommunication.
Unsupervised Syntactically Controlled Paraphrase Generation with Abstract Meaning Representations
In this paper, we demonstrate that leveraging Abstract Meaning Representations (AMR) can greatly improve the performance of unsupervised syntactically controlled paraphrase generation.
Formal limitations of sample-wise information-theoretic generalization bounds
Remarkably, PAC-Bayes, single-draw and expected squared generalization gap bounds that depend on information in pairs of examples exist.
Robust Conversational Agents against Imperceptible Toxicity Triggers
Existing work to generate such attacks is either based on human-generated attacks which is costly and not scalable or, in case of automatic attacks, the attack vector does not conform to human-like language, which can be detected using a language model loss.
Partial Identification of Dose Responses with Hidden Confounders
Sensitivity analyses provide principled ways to give bounds on causal estimates when confounding variables are hidden.
On the Intrinsic and Extrinsic Fairness Evaluation Metrics for Contextualized Language Representations
Multiple metrics have been introduced to measure fairness in various natural language processing tasks.
Mitigating Gender Bias in Distilled Language Models via Counterfactual Role Reversal
Language models excel at generating coherent text, and model compression techniques such as knowledge distillation have enabled their use in resource-constrained settings.
Inferring topological transitions in pattern-forming processes with self-supervised learning
The identification and classification of transitions in topological and microstructural regimes in pattern-forming processes are critical for understanding and fabricating microstructurally precise novel materials in many application domains.
DEAM: Dialogue Coherence Evaluation using AMR-based Semantic Manipulations
We also show that DEAM can distinguish between coherent and incoherent dialogues generated by baseline manipulations, whereas those baseline models cannot detect incoherent examples generated by DEAM.
Failure Modes of Domain Generalization Algorithms
On Camelyon-17, domain-invariance degrades the quality of representations on unseen domains.
Implicit SVD for Graph Representation Learning
Recent improvements in the performance of state-of-the-art (SOTA) methods for Graph Representational Learning (GRL) have come at the cost of significant computational resource requirements for training, e. g., for calculating gradients via backprop over many data epochs.
Hamiltonian Dynamics with Non-Newtonian Momentum for Rapid Sampling
Auxiliary neural models can learn to speed up MCMC, but the overhead for training the extra model can be prohibitive.
Cognitively Inspired Learning of Incremental Drifting Concepts
Humans continually expand their learned knowledge to new domains and learn new concepts without any interference with past learned experiences.
Information-theoretic generalization bounds for black-box learning algorithms
We derive information-theoretic generalization bounds for supervised learning algorithms based on the information contained in predictions rather than in the output of the training algorithm.
Partner-Assisted Learning for Few-Shot Image Classification
In this paper, we focus on the design of training strategy to obtain an elemental representation such that the prototype of each novel class can be estimated from a few labeled samples.
Attributing Fair Decisions with Attention Interventions
The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods.
Domain Adaptation for Sentiment Analysis Using Increased Intraclass Separation
We introduce a new domain adaptation method which induces large margins between different classes in an embedding space.
q-Paths: Generalizing the Geometric Annealing Path using Power Means
Many common machine learning methods involve the geometric annealing path, a sequence of intermediate densities between two distributions of interest constructed using the geometric average.
Plot-guided Adversarial Example Construction for Evaluating Open-domain Story Generation
We propose to tackle these issues by generating a more comprehensive set of implausible stories using {\em plots}, which are structured representations of controllable factors used to generate stories.
Lawyers are Dishonest? Quantifying Representational Harms in Commonsense Knowledge Resources
In addition, we analyze two downstream models that use ConceptNet as a source for commonsense knowledge and find the existence of biases in those models as well.
Fast Graph Learning with Unique Optimal Solutions
We consider two popular Graph Representation Learning (GRL) methods: message passing for node classification and network embedding for link prediction.
Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning
We propose Graph Traversal via Tensor Functionals(GTTF), a unifying meta-algorithm framework for easing the implementation of diverse graph algorithms and enabling transparent and efficient scaling to large graphs.
DiSCoL: Toward Engaging Dialogue Systems through Conversational Line Guided Response Generation
Having engaging and informative conversations with users is the utmost goal for open-domain conversational systems.
Learning a Max-Margin Classifier for Cross-Domain Sentiment Analysis
Large margins in the source domain help to reduce the effect of ``domain shift'' on the performance of a trained classifier in the target domain.
Likelihood Ratio Exponential Families
The exponential family is well known in machine learning and statistical physics as the maximum entropy distribution subject to a set of observed constraints, while the geometric mixture path is common in MCMC methods such as annealed importance sampling.
Exacerbating Algorithmic Bias through Fairness Attacks
Algorithmic fairness has attracted significant attention in recent years, with many quantitative measures suggested for characterizing the fairness of different machine learning algorithms.
Annealed Importance Sampling with q-Paths
Annealed importance sampling (AIS) is the gold standard for estimating partition functions or marginal likelihoods, corresponding to importance sampling over a path of distributions between a tractable base and an unnormalized target.
MUSCLE: Strengthening Semi-Supervised Learning Via Concurrent Unsupervised Learning Using Mutual Information Maximization
We also show that MUSCLE has the potential to boost the classification performance when used in the fine-tuning phase for a model pre-trained only on unlabeled data.
One-shot Learning for Temporal Knowledge Graphs
Most real-world knowledge graphs are characterized by a long-tail relation frequency distribution where a significant fraction of relations occurs only a handful of times.
Leveraging Clickstream Trajectories to Reveal Low-Quality Workers in Crowdsourced Forecasting Platforms
In this study, we propose the use of a computational framework to identify clusters of underperforming workers using clickstream trajectories.
Compressing Deep Neural Networks via Layer Fusion
This paper proposes \textit{layer fusion} - a model compression technique that discovers which weights to combine and then fuses weights of similar fully-connected, convolutional and attention layers.
Robust Classification under Class-Dependent Domain Shift
Investigation of machine learning algorithms robust to changes between the training and test distributions is an active area of research.
All in the Exponential Family: Bregman Duality in Thermodynamic Variational Inference
We propose to choose intermediate distributions using equal spacing in the moment parameters of our exponential family, which matches grid search performance and allows the schedule to adaptively update over the course of training.
Overcoming Concept Shift in Domain-Aware Settings through Consolidated Internal Distributions
We develop an algorithm to improve the performance of a pre-trained model under concept shift without retraining the model from scratch when only unannotated samples of initial concepts are accessible.
A Metric Space for Point Process Excitations
A multivariate Hawkes process enables self- and cross-excitations through a triggering matrix that behaves like an asymmetrical covariance structure, characterizing pairwise interactions between the event types.
ForecastQA: A Question Answering Challenge for Event Forecasting with Temporal Text Data
In this work, we aim to formulate a task, construct a dataset, and provide benchmarks for developing methods for event forecasting with large volumes of unstructured text data.
Improving Generalization by Controlling Label-Noise Information in Neural Network Weights
In the presence of noisy or incorrect labels, neural networks have the undesirable tendency to memorize information about the noise.
Bin2vec: Learning Representations of Binary Executable Programs for Security Tasks
We demonstrate the versatility of this approach by using our representations to solve two semantically different binary analysis tasks - functional algorithm classification and vulnerability discovery.
Predictive Engagement: An Efficient Metric For Automatic Evaluation of Open-Domain Dialogue Systems
In this paper, we investigate the possibility and efficacy of estimating utterance-level engagement and define a novel metric, {\em predictive engagement}, for automatic evaluation of open-domain dialogue systems.
Nearly-Unsupervised Hashcode Representations for Biomedical Relation Extraction
Recently, kernelized locality sensitive hashcodes have been successfully employed as representations of natural language text, especially showing high relevance to biomedical relation extraction tasks.
Man is to Person as Woman is to Location: Measuring Gender Bias in Named Entity Recognition
We study the bias in several state-of-the-art named entity recognition (NER) models---specifically, a difference in the ability to recognize male and female names as PERSON entity types.
Deep Structured Neural Network for Event Temporal Relation Extraction
We propose a novel deep structured learning framework for event temporal relation extraction.
Stacking Models for Nearly Optimal Link Prediction in Complex Networks
These results indicate that the state-of-the-art for link prediction comes from combining individual algorithms, which achieves nearly optimal predictions.
Nearly-Unsupervised Hashcode Representations for Relation Extraction
Recently, kernelized locality sensitive hashcodes have been successfully employed as representations of natural language text, especially showing high relevance to biomedical relation extraction tasks.
A Survey on Bias and Fairness in Machine Learning
With the commercialization of these systems, researchers are becoming aware of the biases that these applications can contain and have attempted to address them.
BioRelEx 1.0: Biological Relation Extraction Benchmark
Automatic extraction of relations and interactions between biological entities from scientific literature remains an extremely challenging problem in biomedical information extraction and natural language processing in general.
Analysis | OPEN | Published: 17 June 2019 Multitask learning and benchmarking with clinical time series data
Health care is one of the most exciting frontiers in data mining and machine learning.
Efficient Covariance Estimation from Temporal Data
Estimating the covariance structure of multivariate time series is a fundamental problem with a wide-range of real-world applications -- from financial modeling to fMRI analysis.
MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing
Existing popular methods for semi-supervised learning with Graph Neural Networks (such as the Graph Convolutional Network) provably cannot learn a general class of neighborhood mixing relationships.
Better Automatic Evaluation of Open-Domain Dialogue Systems with Contextualized Embeddings
Despite advances in open-domain dialogue systems, automatic evaluation of such systems is still a challenging problem.
Exact Rate-Distortion in Autoencoders via Echo Noise
The noise is constructed in a data-driven fashion that does not require restrictive distributional assumptions.
Identifying and Analyzing Cryptocurrency Manipulations in Social Media
Because of the speed and relative anonymity offered by social platforms such as Twitter and Telegram, social media has become a preferred platform for scammers who wish to spread false hype about the cryptocurrency they are trying to pump.
Invariant Representations without Adversarial Training
Representations of data that are invariant to changes in specified factors are useful for a wide range of problems: removing potential biases in prediction problems, controlling the effects of covariates, and disentangling meaningful factors of variation.
A Forest Mixture Bound for Block-Free Parallel Inference
Coordinate ascent variational inference is an important algorithm for inference in probabilistic models, but it is slow because it updates only a single variable at a time.
Capturing Edge Attributes via Network Embedding
Here we propose a novel embedding method that uses both network structure and edge attributes to learn better network representations.
Social and Information Networks
Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
We also derive a novel lower bound on mutual information, used as a model-selection criterion favoring representations with better alignment between the utterances of participants in a collaborative dialogue setting, as well as higher predictability of the generated responses.
Auto-Encoding Total Correlation Explanation
Advances in unsupervised learning enable reconstruction and generation of samples from complex distributions, but this success is marred by the inscrutability of the representations learned.
Stochastic Learning of Nonstationary Kernels for Natural Language Modeling
Natural language processing often involves computations with semantic or syntactic graphs to facilitate sophisticated reasoning based on structural relationships.
Kernelized Hashcode Representations for Relation Extraction
Here we propose to use random subspaces of KLSH codes for efficiently constructing an explicit representation of NLP structures suitable for general classification methods.
Disentangled Representations via Synergy Minimization
Scientists often seek simplified representations of complex systems to facilitate prediction and understanding.
Unifying Local and Global Change Detection in Dynamic Networks
Many real-world networks are complex dynamical systems, where both local (e. g., changing node attributes) and global (e. g., changing network topology) processes unfold over time.
Fast structure learning with modular regularization
We also use our approach for estimating covariance structure for a number of real-world datasets and show that it consistently outperforms state-of-the-art estimators at a fraction of the computational cost.
Multitask learning and benchmarking with clinical time series data
Health care is one of the most exciting frontiers in data mining and machine learning.
Toward Interpretable Topic Discovery via Anchored Correlation Explanation
Many predictive tasks, such as diagnosing a patient based on their medical chart, are ultimately defined by the decisions of human experts.
Variational Information Maximization for Feature Selection
We demonstrate that approximations made by existing methods are based on unrealistic assumptions.
Sifting Common Information from Many Variables
Measuring the relationship between any pair of variables is a rich and active area of research that is central to scientific practice.
Predicting online extremism, content adopters, and interaction reciprocity
We present a machine learning framework that leverages a mixture of metadata, network, and temporal features to detect extremist users, and predict content adopters and interaction reciprocity in social media.
The DARPA Twitter Bot Challenge
A number of organizations ranging from terrorist groups such as ISIS to politicians and nation states reportedly conduct explicit campaigns to influence opinion on social media, posing a risk to democratic processes.
Extracting Biomolecular Interactions Using Semantic Parsing of Biomedical Text
We advance the state of the art in biomolecular interaction extraction with three contributions: (i) We show that deep, Abstract Meaning Representations (AMR) significantly improve the accuracy of a biomolecular interaction extraction system when compared to a baseline that relies solely on surface- and syntax-based features; (ii) In contrast with previous approaches that infer relations on a sentence-by-sentence basis, we expand our framework to enable consistent predictions over sets of sentences (documents); (iii) We further modify and expand a graph kernel learning framework to enable concurrent exploitation of automatically induced AMR (semantic) and dependency structure (syntactic) representations.
Latent Space Model for Multi-Modal Social Data
We validate the proposed framework on two problems: prediction of social interactions from user attributes and behaviors, and behavior prediction exploiting network information.
The Information Sieve
Each layer of the sieve recovers a single latent factor that is maximally informative about multivariate dependence in the data.
Understanding confounding effects in linguistic coordination: an information-theoretic approach
We revisit some of the previous studies that reported strong signatures of stylistic accommodation, and find that a significant part of the observed coordination can be attributed to a simple confounding effect - length coordination.
Scalable Link Prediction in Dynamic Networks via Non-Negative Matrix Factorization
We propose a scalable temporal latent space model for link prediction in dynamic social networks, where the goal is to predict links over time based on a sequence of previous graph snapshots.
Efficient Estimation of Mutual Information for Strongly Dependent Variables
We demonstrate that a popular class of nonparametric mutual information (MI) estimators based on k-nearest-neighbor graphs requires number of samples that scales exponentially with the true MI.
Active Inference for Binary Symmetric Hidden Markov Models
We consider active maximum a posteriori (MAP) inference problem for Hidden Markov Models (HMM), where, given an initial MAP estimate of the hidden sequence, we select to label certain states in the sequence to improve the estimation accuracy of the remaining states.
Maximally Informative Hierarchical Representations of High-Dimensional Data
We present bounds on how informative a representation is about input data.
Discovering Structure in High-Dimensional Data Through Correlation Explanation
We introduce a method to learn a hierarchy of successively more abstract representations of complex data based on optimizing an information-theoretic objective.
Tripartite Graph Clustering for Dynamic Sentiment Analysis on Social Media
We further investigate the evolution of user-level sentiments and latent feature vectors in an online framework and devise an efficient online algorithm to sequentially update the clustering of tweets, users and features with newly arrived data.
Comparative Analysis of Viterbi Training and Maximum Likelihood Estimation for HMMs
We present an asymptotic analysis of Viterbi Training (VT) and contrast it with a more conventional Maximum Likelihood (ML) approach to parameter estimation in Hidden Markov Models.
Phase Transitions in Community Detection: A Solvable Toy Model
It predicts a first-order detectability transition whenever $q > 2$, while the finite-temperature cavity method shows that this is the case only when $q > 4$.
Demystifying Information-Theoretic Clustering
We propose a novel method for clustering data which is grounded in information-theoretic principles and requires no parametric assumptions.
Coevolutionary networks of reinforcement-learning agents
This paper presents a model of network formation in repeated games where the players adapt their strategies and network ties simultaneously using a simple reinforcement-learning scheme.
Latent Self-Exciting Point Process Model for Spatial-Temporal Networks
We propose a latent self-exciting point process model that describes geographically distributed interactions between pairs of entities.
Information-Theoretic Measures of Influence Based on Content Dynamics
The fundamental building block of social influence is for one person to elicit a response in another.
Social and Information Networks Physics and Society Applications
Information Transfer in Social Media
Recent research has explored the increasingly important role of social media by examining the dynamics of individual and group behavior, characterizing patterns of information diffusion, and identifying influential individuals.
Social and Information Networks Physics and Society Applications
