Search Results for author:
Found 70 papers, 26 papers with code
Entity and Evidence Guided Document-Level Relation Extraction
In this paper, we propose a novel framework E2GRE (Entity and Evidence Guided Relation Extraction) that jointly extracts relations and the underlying evidence sentences by using large pretrained language model (LM) as input encoder.
Semisupervised score based matching algorithm to evaluate the effect of public health interventions
We proposed a novel one-to-one matching algorithm based on a quadratic score function $S_{\beta}(x_i, x_j)= \beta^T (x_i-x_j)(x_i-x_j)^T \beta$.
pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
Interventions on model-internal states are fundamental operations in many areas of AI, including model editing, steering, robustness, and interpretability.
RAVEL: Evaluating Interpretability Methods on Disentangling Language Model Representations
Individual neurons participate in the representation of multiple high-level concepts.
A Reply to Makelov et al. (2023)'s "Interpretability Illusion" Arguments
We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause "interpretability illusions".
HyperMix: Out-of-Distribution Detection and Classification in Few-Shot Settings
Out-of-distribution (OOD) detection is an important topic for real-world machine learning systems, but settings with limited in-distribution samples have been underexplored.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives
We present Ego-Exo4D, a diverse, large-scale multimodal multiview video dataset and benchmark challenge.
Contextual Data Augmentation for Task-Oriented Dialog Systems
While dialog response generation has been widely studied on the agent side, it is not evident if similar generative models can be used to generate a large variety of, and often unexpected, user inputs that real dialog systems encounter in practice.
Universal Humanoid Motion Representations for Physics-Based Control
We close this gap by significantly increasing the coverage of our motion representation space.
OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials
Machine learning plays an important and growing role in molecular simulation.
Rigorously Assessing Natural Language Explanations of Neurons
Natural language is an appealing medium for explaining how large language models process and store information, but evaluating the faithfulness of such explanations is challenging.
A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions
Fortunately, the availability of open-source stable diffusion models and their underlying mathematical principles has enabled the academic community to extensively analyze the performance of current image generation models and make improvements based on this stable diffusion framework.
Unsupervised Melody-to-Lyric Generation
Automatic melody-to-lyric generation is a task in which song lyrics are generated to go with a given melody.
Code-Switched Text Synthesis in Unseen Language Pairs
In this work, we study the problem of synthesizing code-switched texts for language pairs absent from the training data.
BiomedGPT: A Unified and Generalist Biomedical Generative Pre-trained Transformer for Vision, Language, and Multimodal Tasks
Conventional task- and modality-specific artificial intelligence (AI) models are inflexible in real-world deployment and maintenance for biomedicine.
Ranked #1 on
Text Summarization
on MeQSum
Do We Need an Encoder-Decoder to Model Dynamical Systems on Networks?
As deep learning gains popularity in modelling dynamical systems, we expose an underappreciated misunderstanding relevant to modelling dynamics on networks.
Unsupervised Melody-Guided Lyrics Generation
At inference time, we leverage the crucial alignments between melody and lyrics and compile the given melody into constraints to guide the generation process.
Crowd3D: Towards Hundreds of People Reconstruction from a Single Image
However, existing methods cannot deal with large scenes containing hundreds of people, which encounter the challenges of large number of people, large variations in human scale, and complex spatial distribution.
Self-Supervised Object Detection from Egocentric Videos
Understanding the visual world from the perspective of humans (egocentric) has been a long-standing challenge in computer vision.
Inducing Character-level Structure in Subword-based Language Models with Type-level Interchange Intervention Training
Language tasks involving character-level manipulations (e. g., spelling corrections, arithmetic operations, word games) are challenging for models operating on subword units.
Context-Situated Pun Generation
In this work, we propose a new task, context-situated pun generation, where a specific context represented by a set of keywords is provided, and the task is to first identify suitable pun words that are appropriate for the context, then generate puns based on the context keywords and the identified pun words.
ExPUNations: Augmenting Puns with Keywords and Explanations
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master.
Task Grouping for Multilingual Text Recognition
Most existing OCR methods focus on alphanumeric characters due to the popularity of English and numbers, as well as their corresponding datasets.
SpanDrop: Simple and Effective Counterfactual Learning for Long Sequences
Distilling supervision signal from a long sequence to make predictions is a challenging task in machine learning, especially when not all elements in the input sequence contribute equally to the desired output.
Video2StyleGAN: Encoding Video in Latent Space for Manipulation
To this end, we propose a novel network to encode face videos into the latent space of StyleGAN for semantic face video manipulation.
PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision
Existing self-supervised 3D human pose estimation schemes have largely relied on weak supervisions like consistency loss to guide the learning, which, inevitably, leads to inferior results in real-world scenarios with unseen poses.
Ranked #37 on
3D Human Pose Estimation
on MPI-INF-3DHP
Improving Time Sensitivity for Question Answering over Temporal Knowledge Graphs
These questions often involve three time-related challenges that previous work fail to adequately address: 1) questions often do not specify exact timestamps of interest (e. g., "Obama" instead of 2000); 2) subtle lexical differences in time relations (e. g., "before" vs "after"); 3) off-the-shelf temporal KG embeddings that previous work builds on ignore the temporal order of timestamps, which is crucial for answering temporal-order related questions.
Ranked #2 on
Question Answering
on CronQuestions
HDhuman: High-quality Human Novel-view Rendering from Sparse Views
To this end, we propose HDhuman, which uses a human reconstruction network with a pixel-aligned spatial transformer and a rendering network with geometry-guided pixel-wise feature integration to achieve high-quality human reconstruction and rendering.
Cross-modal Contrastive Distillation for Instructional Activity Anticipation
In this study, we aim to predict the plausible future action steps given an observation of the past and study the task of instructional activity anticipation.
Semantic Categorization of Social Knowledge for Commonsense Question Answering
Large pre-trained language models (PLMs) have led to great success on various commonsense question answering (QA) tasks in an end-to-end fashion.
On the Opportunities and Risks of Foundation Models
AI is undergoing a paradigm shift with the rise of models (e. g., BERT, DALL-E, GPT-3) that are trained on broad data at scale and are adaptable to a wide range of downstream tasks.
Tight Mutual Information Estimation With Contrastive Fenchel-Legendre Optimization
Successful applications of InfoNCE and its variants have popularized the use of contrastive variational mutual information (MI) estimators in machine learning.
Open Temporal Relation Extraction for Question Answering
Understanding the temporal relations among events in text is a critical aspect of reading comprehension, which can be evaluated in the form of temporal question answering (TQA).
Joint System-Wise Optimization for Pipeline Goal-Oriented Dialog System
Recent work (Takanobu et al., 2020) proposed the system-wise evaluation on dialog systems and found that improvement on individual components (e. g., NLU, policy) in prior work may not necessarily bring benefit to pipeline systems in system-wise evaluation.
Variance-reduced First-order Meta-learning for Natural Language Processing Tasks
The core of our algorithm is to introduce a novel variance reduction term to the gradient estimation when performing the task adaptation.
Conversational AI Systems for Social Good: Opportunities and Challenges
Conversational artificial intelligence (ConvAI) systems have attracted much academic and commercial attention recently, making significant progress on both fronts.
TextOCR: Towards large-scale end-to-end reasoning for arbitrary-shaped scene text
A crucial component for the scene text based reasoning required for TextVQA and TextCaps datasets involve detecting and recognizing text present in the images using an optical character recognition (OCR) system.
Optical Character Recognition
Optical Character Recognition (OCR)
+2
UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks
In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs.
Residual Enhanced Multi-Hypergraph Neural Network
Hypergraphs are a generalized data structure of graphs to model higher-order correlations among entities, which have been successfully adopted into various research domains.
A Multiplexed Network for End-to-End, Multilingual OCR
Recent advances in OCR have shown that an end-to-end (E2E) training pipeline that includes both detection and recognition leads to the best results.
Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification
Recent work on aspect-level sentiment classification has demonstrated the efficacy of incorporating syntactic structures such as dependency trees with graph neural networks(GNN), but these approaches are usually vulnerable to parsing errors.
Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling
In this paper, we propose two novel techniques, adaptive thresholding and localized context pooling, to solve the multi-label and multi-entity problems.
Ranked #6 on
Relation Extraction
on ReDocRED
Document-level Relation Extraction
Multi-Label Classification
+2
Multi-hop Attention Graph Neural Network
Currently, at every layer, attention is computed between connected pairs of nodes and depends solely on the representation of the two nodes.
Inductive Learning on Commonsense Knowledge Graph Completion
Here, we propose to study the inductive learning setting for CKG completion where unseen entities may present at test time.
Entity and Evidence Guided Relation Extraction for DocRED
Document-level relation extraction is a challenging task which requires reasoning over multiple sentences in order to predict relations in a document.
Ranked #14 on
Relation Extraction
on DocRED
Mask TextSpotter v3: Segmentation Proposal Network for Robust Scene Text Spotting
Recent end-to-end trainable methods for scene text spotting, integrating detection and recognition, showed much progress.
Ranked #11 on
Text Spotting
on Total-Text
SkipConvNet: Skip Convolutional Neural Network for Speech Dereverberation using Optimally Smoothed Spectral Mapping
The reliability of using fully convolutional networks (FCNs) has been successfully demonstrated by recent studies in many speech applications.
Improving Weakly Supervised Visual Grounding by Contrastive Knowledge Distillation
Our core innovation is the learning of a region-phrase score function, based on which an image-sentence score function is further constructed.
Improving Neural Language Generation with Spectrum Control
Recent Transformer-based models such as Transformer-XL and BERT have achieved huge success on various natural language processing tasks.
Speaker Diarization with Lexical Information
This work presents a novel approach for speaker diarization to leverage lexical information provided by automatic speech recognition.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Graph Sequential Network for Reasoning over Sequences
We validate the proposed GSN on two NLP tasks: interpretable multi-hop reading comprehension on HotpotQA and graph based fact verification on FEVER.
Deep Visual Waterline Detection within Inland Marine Environment
This paper attempts to find a solution to guarantee the effectiveness of waterline detection for inland maritime applications with general digital camera sensor.
Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
Translational distance-based knowledge graph embedding has shown progressive improvements on the link prediction task, from TransE to the latest state-of-the-art RotatE.
Ranked #18 on
Link Prediction
on FB15k-237
Speaker-invariant Affective Representation Learning via Adversarial Training
In this paper, we propose a machine learning framework to obtain speech emotion representations by limiting the effect of speaker variability in the speech signals.
Relation Module for Non-Answerable Predictions on Reading Comprehension
We test the relation module on the SQuAD 2. 0 dataset using both the BiDAF and BERT models as baseline readers.
Select, Answer and Explain: Interpretable Multi-hop Reading Comprehension over Multiple Documents
Interpretable multi-hop reading comprehension (RC) over multiple documents is a challenging problem because it demands reasoning over multiple information sources and explaining the answer prediction by providing supporting evidences.
Improving Graph Attention Networks with Large Margin-based Constraints
Graph Attention Networks (GATs) are the state-of-the-art neural architecture for representation learning with graphs.
Selective Attention Based Graph Convolutional Networks for Aspect-Level Sentiment Classification
Aspect-level sentiment classification aims to identify the sentiment polarity towards a specific aspect term in a sentence.
Relation Module for Non-answerable Prediction on Question Answering
In this paper, we aim to improve a MRC model's ability to determine whether a question has an answer in a given context (e. g. the recently proposed SQuAD 2. 0 task).
Zero-shot Text-to-SQL Learning with Auxiliary Task
Recent years have seen great success in the use of neural seq2seq models on the text-to-SQL task.
Cross-lingual Text-independent Speaker Verification using Unsupervised Adversarial Discriminative Domain Adaptation
Speaker verification systems often degrade significantly when there is a language mismatch between training and testing data.
Multiple instance learning with graph neural networks
In this paper, we propose a new end-to-end graph neural network (GNN) based algorithm for MIL: we treat each bag as a graph and use GNN to learn the bag embedding, in order to explore the useful structural information among instances in bags.
Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
We introduce a heterogeneous graph with different types of nodes and edges, which is named as Heterogeneous Document-Entity (HDE) graph.
I4U Submission to NIST SRE 2018: Leveraging from a Decade of Shared Experiences
The I4U consortium was established to facilitate a joint entry to NIST speaker recognition evaluations (SRE).
Deep Speaker Embedding Learning with Multi-Level Pooling for Text-Independent Speaker Verification
This paper aims to improve the widely used deep speaker embedding x-vector model.
Improving Rotated Text Detection with Rotation Region Proposal Networks
In this work, we extend the scene-text extraction system at Facebook, Rosetta, to efficiently handle text in various orientations.
End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
The recent graph convolutional network (GCN) provides another way of learning graph node embedding by successfully utilizing graph connectivity structure.
Ranked #28 on
Link Prediction
on FB15k-237
DeepGlobe 2018: A Challenge to Parse the Earth through Satellite Images
We present the DeepGlobe 2018 Satellite Image Understanding Challenge, which includes three public competitions for segmentation, detection, and classification tasks on satellite images.
End-to-end Planning of Fixed Millimeter-Wave Networks
This article discusses a framework to support the design and end-to-end planning of fixed millimeter-wave networks.
Learning Two-Branch Neural Networks for Image-Text Matching Tasks
Image-language matching tasks have recently attracted a lot of attention in the computer vision field.
