Search Results for author:
Found 119 papers, 60 papers with code
Interview: Large-scale Modeling of Media Dialog with Discourse Patterns and Knowledge Grounding
In this work, we perform the first large-scale analysis of discourse in media dialog and its impact on generative modeling of dialog turns, with a focus on interrogative patterns and use of external knowledge.
SkipBERT: Efficient Inference with Shallow Layer Skipping
In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.
Mirror: A Natural Language Interface for Data Querying, Summarization, and Visualization
We present Mirror, an open-source platform for data exploration and analysis powered by large language models.
Data Distillation: A Survey
The popularity of deep learning has led to the curation of a vast number of massive and multifarious datasets.
Synthetic Pre-Training Tasks for Neural Machine Translation
Our second approach explores the effect of pre-training on procedurally generated synthetic parallel data that does not depend on any real human language corpus.
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
Further, videos in the wild often contain off-screen sounds and background noise that may hinder the model from learning the desired audio-textual correspondence.
Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders
Based on this representation scheme, we further propose an enhanced contrastive pre-training approach, using semi-synthetic and mixed-domain code representations as hard negatives.
Efficiently Tuned Parameters are Task Embeddings
Thus, we propose to exploit these efficiently tuned parameters as off-the-shelf task embeddings for the efficient selection of source datasets for intermediate-task transfer.
InforMask: Unsupervised Informative Masking for Language Model Pretraining
In this paper, we propose InforMask, a new unsupervised masking strategy for training masked language models.
InterFair: Debiasing with Natural Language Feedback for Fair Interpretable Predictions
Debiasing methods in NLP models traditionally focus on isolating information related to a sensitive attribute (like gender or race).
Controlling Bias Exposure for Fair Interpretable Predictions
However, when sensitive information is semantically entangled with the task information of the input, e. g., gender information is predictive for a profession, a fair trade-off between task performance and bias mitigation is difficult to achieve.
CLIP also Understands Text: Prompting CLIP for Phrase Understanding
However, the application of its text encoder solely for text understanding has been less explored.
UCEpic: Unifying Aspect Planning and Lexical Constraints for Explainable Recommendation
In this paper, we propose UCEpic, an explanation generation model that unifies aspect planning and lexical constraints for controllable personalized generation.
On Faithfulness and Coherence of Language Explanations for Recommendation Systems
Reviews contain rich information about product characteristics and user interests and thus are commonly used to boost recommender system performance.
Factual and Informative Review Generation for Explainable Recommendation
Recent models can generate fluent and grammatical synthetic reviews while accurately predicting user ratings.
SPOT: Knowledge-Enhanced Language Representations for Information Extraction
To address these problems, we propose a new pre-trained model that learns representations of both entities and relationships from token spans and span pairs in the text respectively.
Ranked #4 on
Relation Extraction
on SemEval-2010 Task 8
Plug-and-Play Model-Agnostic Counterfactual Policy Synthesis for Deep Reinforcement Learning based Recommendation
Recent advances in recommender systems have proved the potential of Reinforcement Learning (RL) to handle the dynamic evolution processes between users and recommender systems.
Generating Negative Samples for Sequential Recommendation
Due to the dynamics of users' interests and model updates during training, considering randomly sampled items from a user's non-interacted item set as negatives can be uninformative.
Bundle MCR: Towards Conversational Bundle Recommendation
MCR, which uses a conversational paradigm to elicit user interests by asking user preferences on tags (e. g., categories or attributes) and handling user feedback across multiple rounds, is an emerging recommendation setting to acquire user feedback and narrow down the output space, but has not been explored in the context of bundle recommendation.
Contrastive Learning for Interactive Recommendation in Fashion
Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms.
Multitrack Music Transformer
Existing approaches for generating multitrack music with transformer models have been limited in terms of the number of instruments, the length of the music segments and slow inference.
Personalized Showcases: Generating Multi-Modal Explanations for Recommendations
In this paper, to further enrich explanations, we propose a new task named personalized showcases, in which we provide both textual and visual information to explain our recommendations.
Infinite Recommendation Networks: A Data-Centric Approach
We leverage the Neural Tangent Kernel and its equivalence to training infinitely-wide neural networks to devise $\infty$-AE: an autoencoder with infinitely-wide bottleneck layers.
Ranked #1 on
Recommendation Systems
on Douban
(AUC metric)
Assistive Recipe Editing through Critiquing
Prior studies have used pre-trained language models, or relied on small paired recipe data (e. g., a recipe paired with a similar one that satisfies a dietary constraint).
Instilling Type Knowledge in Language Models via Multi-Task QA
Understanding human language often necessitates understanding entities and their place in a taxonomy of knowledge -- their types.
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
Prompt-based learning (i. e., prompting) is an emerging paradigm for exploiting knowledge learned by a pretrained language model.
FaceSigns: Semi-Fragile Neural Watermarks for Media Authentication and Countering Deepfakes
We demonstrate that FaceSigns can embed a 128 bit secret as an imperceptible image watermark that can be recovered with a high bit recovery accuracy at several compression levels, while being non-recoverable when unseen Deepfake manipulations are applied.
Coarse-to-Fine Sparse Sequential Recommendation
We propose to model user dynamics from shopping intents and interacted items simultaneously.
Achieving Conversational Goals with Unsupervised Post-hoc Knowledge Injection
In this paper, we propose a post-hoc knowledge-injection technique where we first retrieve a diverse set of relevant knowledge snippets conditioned on both the dialog history and an initial response from an existing dialog model.
LaPraDoR: Unsupervised Pretrained Dense Retriever for Zero-Shot Text Retrieval
Experimental results show that LaPraDoR achieves state-of-the-art performance compared with supervised dense retrieval models, and further analysis reveals the effectiveness of our training strategy and objectives.
Leashing the Inner Demons: Self-Detoxification for Language Models
Language models (LMs) can reproduce (or amplify) toxic language seen during training, which poses a risk to their practical application.
A Survey on Dynamic Neural Networks for Natural Language Processing
Effectively scaling large Transformer models is a main driver of recent advances in natural language processing.
A Survey on Model Compression and Acceleration for Pretrained Language Models
Despite achieving state-of-the-art performance on many NLP tasks, the high energy cost and long inference delay prevent Transformer-based pretrained language models (PLMs) from seeing broader adoption including for edge and mobile computing.
Deep Performer: Score-to-Audio Music Performance Synthesis
Music performance synthesis aims to synthesize a musical score into a natural performance.
A Review of Modern Fashion Recommender Systems
The textile and apparel industries have grown tremendously over the last years.
Intent Contrastive Learning for Sequential Recommendation
Specifically, we introduce a latent variable to represent users' intents and learn the distribution function of the latent variable via clustering.
Rank List Sensitivity of Recommender Systems to Interaction Perturbations
We introduce a measure of stability for recommender systems, called Rank List Sensitivity (RLS), which measures how rank lists generated by a given recommender system at test time change as a result of a perturbation in the training data.
On Sampling Collaborative Filtering Datasets
We study the practical consequences of dataset sampling strategies on the ranking performance of recommendation algorithms.
Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning
We further propose a differentiable dataset-level balance and update the weights in a linear annealing schedule to simulate network pruning and thus obtain the optimal structure for BSNet with dataset-level balance achieved.
Self-Supervised Bot Play for Conversational Recommendation with Justifications
Conversational recommender systems offer the promise of interactive, engaging ways for users to find items they enjoy.
Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning
Our framework outperforms state-of-the-art algorithms on four benchmark datasets in both zero-shot and generalized zero-shot settings, which demonstrates the effectiveness of spiral learning in learning generalizable and complex correlations.
An Entropy-guided Reinforced Partial Convolutional Network for Zero-Shot Learning
Zero-Shot Learning (ZSL) aims to transfer learned knowledge from observed classes to unseen classes via semantic correlations.
Locality-Sensitive Experience Replay for Online Recommendation
Existing studies encourage the agent to learn from past experience via experience replay (ER).
Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation
Radiology report generation aims at generating descriptive text from radiology images automatically, which may present an opportunity to improve radiology reporting and interpretation.
Detect and Perturb: Neutral Rewriting of Biased and Sensitive Text via Gradient-based Decoding
Written language carries explicit and implicit biases that can distract from meaningful signals.
Modeling Dynamic Attributes for Next Basket Recommendation
However, properly integrating them into user interest models is challenging since attribute dynamics can be diverse such as time-interval aware, periodic patterns (etc.
A Survey of Deep Reinforcement Learning in Recommender Systems: A Systematic Review and Future Directions
In light of the emergence of deep reinforcement learning (DRL) in recommender systems research and several fruitful results in recent years, this survey aims to provide a timely and comprehensive overview of the recent trends of deep reinforcement learning in recommender systems.
Beyond Preserved Accuracy: Evaluating Loyalty and Robustness of BERT Compression
Recent studies on compression of pretrained language models (e. g., BERT) usually use preserved accuracy as the metric for evaluation.
Black-Box Attacks on Sequential Recommenders via Data-Free Model Extraction
Under this setting, we propose an API-based model extraction method via limited-budget synthetic data generation and knowledge distillation.
Contrastive Self-supervised Sequential Recommendation with Robust Augmentation
In this paper, we investigate the application of contrastive Self-Supervised Learning (SSL) to the sequential recommendation, as a way to alleviate some of these issues.
An Empirical Evaluation of End-to-End Polyphonic Optical Music Recognition
Monophonic and homophonic music can be described as homorhythmic, or having a single musical rhythm.
Towards Automatic Instrumentation by Learning to Separate Parts in Symbolic Multitrack Music
In this paper, we aim to further extend this idea and examine the feasibility of automatic instrumentation -- dynamically assigning instruments to notes in solo music during performance.
SVP-CF: Selection via Proxy for Collaborative Filtering Data
As we demonstrate, commonly-used data sampling schemes can have significant consequences on algorithm performance -- masking performance deficiencies in algorithms or altering the relative performance of algorithms, as compared to models trained on the complete dataset.
Weakly Supervised Named Entity Tagging with Learnable Logical Rules
We study the problem of building entity tagging systems by using a few rules as weak supervision.
Knowledge-Grounded Self-Rationalization via Extractive and Natural Language Explanations
Our framework improves over previous methods by: (i) reaching SOTA task performance while also providing explanations, (ii) providing two types of explanations, while existing models usually provide only one type, and (iii) beating by a large margin the previous SOTA in terms of quality of both types of explanations.
Unsupervised Enrichment of Persona-grounded Dialog with Background Stories
Humans often refer to personal narratives, life experiences, and events to make a conversation more engaging and rich.
BERT Learns to Teach: Knowledge Distillation with Meta Learning
We present Knowledge Distillation with Meta Learning (MetaDistil), a simple yet effective alternative to traditional knowledge distillation (KD) methods where the teacher model is fixed during training.
SHARE: a System for Hierarchical Assistive Recipe Editing
The large population of home cooks with dietary restrictions is under-served by existing cooking resources and recipe generation models.
Ask what's missing and what's useful: Improving Clarification Question Generation using Global Knowledge
The ability to generate clarification questions i. e., questions that identify useful missing information in a given context, is important in reducing ambiguity.
Blow the Dog Whistle: A Chinese Dataset for Cant Understanding with Common Sense and World Knowledge
Cant is important for understanding advertising, comedies and dog-whistle politics.
WaveGuard: Understanding and Mitigating Audio Adversarial Examples
There has been a recent surge in adversarial attacks on deep learning based automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Cross-modal Adversarial Reprogramming
Recent works on adversarial reprogramming have shown that it is possible to repurpose neural networks for alternate tasks without modifying the network architecture or parameters.
Expressive Neural Voice Cloning
In this work, we propose a controllable voice cloning method that allows fine-grained control over various style aspects of the synthesized speech for an unseen speaker.
Zero-shot Generalization in Dialog State Tracking through Generative Question Answering
Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs.
Like hiking? You probably enjoy nature: Persona-grounded Dialog with Commonsense Expansions
Existing persona-grounded dialog models often fail to capture simple implications of given persona descriptions, something which humans are able to do seamlessly.
Learning Visual-Semantic Embeddings for Reporting Abnormal Findings on Chest X-rays
In this work, we focus on reporting abnormal findings on radiology images; instead of training on complete radiology reports, we propose a method to identify abnormal findings from the reports in addition to grouping them with unsupervised clustering and minimal rules.
MusPy: A Toolkit for Symbolic Music Generation
MusPy provides easy-to-use tools for essential components in a music generation system, including dataset management, data I/O, data preprocessing and model evaluation.
BERT Loses Patience: Fast and Robust Inference with Early Exit
In this paper, we propose Patience-based Early Exit, a straightforward yet effective inference method that can be used as a plug-and-play technique to simultaneously improve the efficiency and robustness of a pretrained language model (PLM).
How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
We investigate a growing body of work that seeks to improve recommender systems through the use of review text.
Speech Recognition and Multi-Speaker Diarization of Long Conversations
Speech recognition (ASR) and speaker diarization (SD) models have traditionally been trained separately to produce rich conversation transcripts with speaker labels.
Interview: A Large-Scale Open-Source Corpus of Media Dialog
Compared to existing large-scale proxies for conversational data, language models trained on our dataset exhibit better zero-shot out-of-domain performance on existing spoken dialog datasets, demonstrating its usefulness in modeling real-world conversations.
Developing a Recommendation Benchmark for MLPerf Training and Inference
Deep learning-based recommendation models are used pervasively and broadly, for example, to recommend movies, products, or other information most relevant to users, in order to enhance the user experience.
ReZero is All You Need: Fast Convergence at Large Depth
Deep networks often suffer from vanishing or exploding gradients due to inefficient signal propagation, leading to long training times or convergence difficulties.
Adversarial Deepfakes: Evaluating Vulnerability of Deepfake Detectors to Adversarial Examples
Recent advances in video manipulation techniques have made the generation of fake videos more accessible than ever before.
TiSASRec: Time Interval Aware Self-Attention for Sequential Recommendation
Sequential recommender systems seek to exploit the order of users' interactions, in order to predict their next action based on the context of what they have done recently.
Addressing Marketing Bias in Product Recommendations
However, these interactions can be biased by how the product is marketed, for example due to the selection of a particular human model in a product image.
Justifying Recommendations using Distantly-Labeled Reviews and Fine-Grained Aspects
Several recent works have considered the problem of generating reviews (or {`}tips{'}) as a form of explanation as to why a recommendation might match a customer{'}s interests.
Candidate Generation with Binary Codes for Large-Scale Top-N Recommendation
Generating the Top-N recommendations from a large corpus is computationally expensive to perform at scale.
Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation
Experiments on both the multi-domain and the single domain dialogue state tracking dataset show that our model not only scales easily with the increasing number of pre-defined domains and slots but also reaches the state-of-the-art performance.
Ranked #14 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Generating Personalized Recipes from Historical User Preferences
Existing approaches to recipe generation are unable to create recipes for users with culinary preferences but incomplete knowledge of ingredients in specific dishes.
Ranked #1 on
Recipe Generation
on Food.com
CosRec: 2D Convolutional Neural Networks for Sequential Recommendation
Sequential patterns play an important role in building modern recommender systems.
Improving Neural Story Generation by Targeted Common Sense Grounding
Stories generated with neural language models have shown promise in grammatical and stylistic consistency.
LakhNES: Improving multi-instrumental music generation with cross-domain pre-training
We are interested in the task of generating multi-instrumental music scores.
Fine-Grained Spoiler Detection from Large-Scale Review Corpora
This paper presents computational approaches for automatically detecting critical plot twists in reviews of media products.
Universal Adversarial Perturbations for Speech Recognition Systems
In this work, we demonstrate the existence of universal adversarial audio perturbations that cause mis-transcription of audio signals by automatic speech recognition (ASR) systems.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Expediting TTS Synthesis with Adversarial Vocoding
Recent approaches in text-to-speech (TTS) synthesis employ neural network strategies to vocode perceptually-informed spectrogram representations directly into listenable waveforms.
Embryo staging with weakly-supervised region selection and dynamically-decoded predictions
First, noting that in each image the embryo occupies a small subregion, we jointly train a region proposal network with the downstream classifier to isolate the embryo.
Complete the Look: Scene-based Complementary Product Recommendation
We design an approach to extract training data for this task, and propose a novel way to learn the scene-product compatibility from fashion or interior design images.
Recommendation Through Mixtures of Heterogeneous Item Relationships
Recommender Systems have proliferated as general-purpose approaches to model a wide variety of consumer interaction data.
Learning to Attend On Essential Terms: An Enhanced Retriever-Reader Model for Open-domain Question Answering
In this paper we propose a retriever-reader model that learns to attend on essential terms during the question answering process.
Multiple-choice
Multiple Choice Question Answering (MCQA)
+2
Self-Attentive Sequential Recommendation
Sequential dynamics are a key feature of many modern recommender systems, which seek to capture the `context' of users' activities on the basis of actions they have performed recently.
Ranked #1 on
Recommendation Systems
on Steam
Personalized Review Generation By Expanding Phrases and Attending on Aspect-Aware Representations
In this paper, we focus on the problem of building assistive systems that can help users to write reviews.
Visually-Aware Personalized Recommendation using Interpretable Image Representations
Visually-aware recommender systems use visual signals present in the underlying data to model the visual characteristics of items and users' preferences towards them.
The NES Music Database: A multi-instrumental dataset with expressive performance attributes
Existing research on music generation focuses on composition, but often ignores the expressive performance characteristics required for plausible renditions of resultant pieces.
Adversarial Audio Synthesis
Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of timescales.
IJCNLP-2017 Task 3: Review Opinion Diversification (RevOpiD-2017)
Unlike Entity Disambiguation in web search results, Opinion Disambiguation is a relatively unexplored topic.
Does mitigating ML's impact disparity require treatment disparity?
Following related work in law and policy, two notions of disparity have come to shape the study of fairness in algorithmic decision-making.
Visually-Aware Fashion Recommendation and Design with Generative Image Models
Here, we seek to extend this contribution by showing that recommendation performance can be significantly improved by learning `fashion aware' image representations directly, i. e., by training the image representation (from the pixel level) and the recommender system jointly; this contribution is related to recent work using Siamese CNNs, though we are able to show improvements over state-of-the-art recommendation techniques such as BPR and variants that make use of pre-trained visual features.
Estimating Reactions and Recommending Products with Generative Models of Reviews
Natural language approaches that model information like product reviews have proved to be incredibly useful in improving the performance of such methods, as reviews provide valuable auxiliary information that can be used to better estimate latent user preferences and item properties.
Translation-based Recommendation
Modeling the complex interactions between users and items as well as amongst items themselves is at the core of designing successful recommender systems.
Semantically Decomposing the Latent Spaces of Generative Adversarial Networks
Corresponding samples from the real dataset consist of two distinct photographs of the same subject.
Dance Dance Convolution
For the step placement task, we combine recurrent and convolutional neural networks to ingest spectrograms of low-level audio features to predict steps, conditioned on chart difficulty.
Predicting Surgery Duration with Neural Heteroscedastic Regression
Scheduling surgeries is a challenging task due to the fundamental uncertainty of the clinical environment, as well as the risks and costs associated with under- and over-booking.
Modeling Ambiguity, Subjectivity, and Diverging Viewpoints in Opinion Question Answering Systems
Product review websites provide an incredible lens into the wide variety of opinions and experiences of different people, and play a critical role in helping users discover products that match their personal needs and preferences.
Fusing Similarity Models with Markov Chains for Sparse Sequential Recommendation
We show quantitatively that Fossil outperforms alternative algorithms, especially on sparse datasets, and qualitatively that it captures personalized dynamics and is able to make meaningful recommendations.
Vista: A Visually, Socially, and Temporally-aware Model for Artistic Recommendation
Understanding users' interactions with highly subjective content---like artistic images---is challenging due to the complex semantics that guide our preferences.
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
Feature matching is a key problem in computer vision and pattern recognition.
Sherlock: Sparse Hierarchical Embeddings for Visually-aware One-class Collaborative Filtering
Building successful recommender systems requires uncovering the underlying dimensions that describe the properties of items as well as users' preferences toward them.
Learning Compatibility Across Categories for Heterogeneous Item Recommendation
Identifying relationships between items is a key task of an online recommender system, in order to help users discover items that are functionally complementary or visually compatible.
Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering
Building a successful recommender system depends on understanding both the dimensions of people's preferences as well as their dynamics.
Addressing Complex and Subjective Product-Related Queries with Customer Reviews
In this paper we hope to fuse these two paradigms: given a large volume of previously answered queries about products, we hope to automatically learn whether a review of a product is relevant to a given query.
Generative Concatenative Nets Jointly Learn to Write and Classify Reviews
A recommender system's basic task is to estimate how users will respond to unseen items.
VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback
In this paper we propose a scalable factorization model to incorporate visual signals into predictors of people's opinions, which we apply to a selection of large, real-world datasets.
Learning Visual Clothing Style with Heterogeneous Dyadic Co-occurrences
In this paper, we propose a novel learning framework to help answer these types of questions.
Image-based Recommendations on Styles and Substitutes
Humans inevitably develop a sense of the relationships between objects, some of which are based on their appearance.
From Amateurs to Connoisseurs: Modeling the Evolution of User Expertise through Online Reviews
Recommending products to consumers means not only understanding their tastes, but also understanding their level of experience.
Image Labeling on a Network: Using Social-Network Metadata for Image Classification
Many of these benchmarks are derived from online photo sharing networks, like Flickr, which in addition to hosting images also provide a highly interactive social community.
