Search Results for author:
Found 154 papers, 68 papers with code
Learning and Evaluating Chinese Idiom Embeddings
We find that our method substantially outperforms existing methods on the evaluation dataset we have constructed.
Does BERT Understand Idioms? A Probing-Based Empirical Study of BERT Encodings of Idioms
Understanding idioms is important in NLP.
Translate-Train Embracing Translationese Artifacts
Translate-train is a general training approach to multilingual tasks.
Coupled Hierarchical Transformer for Stance-Aware Rumor Verification in Social Media Conversations
The prevalent use of social media enables rapid spread of rumors on a massive scale, which leads to the emerging need of automatic rumor verification (RV).
What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning
In sequential decision-making problems involving sensitive attributes like race and gender, reinforcement learning (RL) agents must carefully consider long-term fairness while maximizing returns.
Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments
Automated generation of feedback on programming assignments holds significant benefits for programming education, especially when it comes to advanced assignments.
Dual-Personalizing Adapter for Federated Foundation Models
To address challenges in this new setting, we explore a simple yet effective solution to learn a comprehensive foundation model.
Modularized Networks for Few-shot Hateful Meme Detection
We then use the few available annotated samples to train a module composer, which assigns weights to the LoRA modules based on their relevance.
Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use.
Knowledge Generation for Zero-shot Knowledge-based VQA
Previous solutions to knowledge-based visual question answering~(K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model.
GliDe with a CaPE: A Low-Hassle Method to Accelerate Speculative Decoding
Speculative decoding is a relatively new decoding framework that leverages small and efficient draft models to reduce the latency of LLMs.
Revisiting the Markov Property for Machine Translation
In this paper, we re-examine the Markov property in the context of neural machine translation.
Enhancing Document-level Translation of Large Language Model via Translation Mixed-instructions
Our proposed translation mixed-instructions enable LLMs (Llama-2~7B and 13B) to maintain consistent translation performance from the sentence level to documents containing as many as 2048 tokens.
Foundation Models for Weather and Climate Data Understanding: A Comprehensive Survey
Furthermore, in relation to the creation and application of foundation models for weather and climate data understanding, we delve into the field's prevailing challenges, offer crucial insights, and propose detailed avenues for future research.
Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorld
While large language models (LLMs) excel in a simulated world of texts, they struggle to interact with the more realistic world without perceptions of other modalities such as visual or audio signals.
Uplift Modeling based on Graph Neural Network Combined with Causal Knowledge
Through uplift modeling, we can identify the treatment with the greatest benefit.
Intriguing Properties of Data Attribution on Diffusion Models
Data attribution seeks to trace model outputs back to training data.
ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense
Humans possess a strong capability for reasoning beyond common sense.
Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution
Throughout long history, natural species have learned to survive by evolving their physical structures adaptive to the environment changes.
GPT-Lab: Next Generation Of Optimal Chemistry Discovery By GPT Driven Robotic Lab
The integration of robots in chemical experiments has enhanced experimental efficiency, but lacking the human intelligence to comprehend literature, they seldom provide assistance in experimental design.
Pro-Cap: Leveraging a Frozen Vision-Language Model for Hateful Meme Detection
Specifically, we prompt a frozen PVLM by asking hateful content-related questions and use the answers as image captions (which we call Pro-Cap), so that the captions contain information critical for hateful content detection.
Causal Reinforcement Learning: A Survey
Causality, however, offers a notable advantage as it can formalize knowledge in a systematic manner and leverage invariance for effective knowledge transfer.
Continual Task Allocation in Meta-Policy Network via Sparse Prompting
We address it by "Continual Task Allocation via Sparse Prompting (CoTASP)", which learns over-complete dictionaries to produce sparse masks as prompts extracting a sub-network for each task from a meta-policy network.
Modularized Zero-shot VQA with Pre-trained Models
We propose a modularized zero-shot network that explicitly decomposes questions into sub reasoning steps and is highly interpretable.
Spatial-temporal Prompt Learning for Federated Weather Forecasting
Federated weather forecasting is a promising collaborative learning framework for analyzing meteorological data across participants from different countries and regions, thus embodying a global-scale real-time weather data predictive analytics platform to tackle climate change.
Does Continual Learning Equally Forget All Parameters?
In this paper, we study which modules in neural networks are more prone to forgetting by investigating their training dynamics during CL.
Adaptive Policy Learning for Offline-to-Online Reinforcement Learning
In this paper, we consider an offline-to-online setting where the agent is first learned from the offline dataset and then trained online, and propose a framework called Adaptive Policy Learning for effectively taking advantage of offline and online data.
Prompting for Multimodal Hateful Meme Classification
Specifically, we construct simple prompts and provide a few in-context examples to exploit the implicit knowledge in the pre-trained RoBERTa language model for hateful meme classification.
Ranked #3 on
Hateful Meme Classification
on HarMeme
Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
To address these challenges, we create a small model for a new task from the pruned models of similar tasks.
Prompt Federated Learning for Weather Forecasting: Toward Foundation Models on Meteorological Data
To relieve the data exposure concern across regions, a novel federated learning approach has been proposed to collaboratively learn a brand-new spatio-temporal Transformer-based foundation model across participants with heterogeneous meteorological data.
P-Transformer: Towards Better Document-to-Document Neural Machine Translation
To alleviate this problem, we propose a position-aware Transformer (P-Transformer) to enhance both the absolute and relative position information in both self-attention and cross-attention.
Federated Learning on Non-IID Graphs via Structural Knowledge Sharing
Inspired by this, we propose FedStar, an FGL framework that extracts and shares the common underlying structure information for inter-graph federated learning tasks.
CCPrefix: Counterfactual Contrastive Prefix-Tuning for Many-Class Classification
Basically, an instance-dependent soft prefix, derived from fact-counterfactual pairs in the label space, is leveraged to complement the language verbalizers in many-class classification.
ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
Recently, a new training oaxe loss has proven effective to ameliorate the effect of multimodality for non-autoregressive translation (NAT), which removes the penalty of word order errors in the standard cross-entropy loss.
Federated Learning from Pre-Trained Models: A Contrastive Learning Approach
To prevent these issues from hindering the deployment of FL systems, we propose a lightweight framework where clients jointly learn to fuse the representations generated by multiple fixed pre-trained models rather than training a large-scale model from scratch.
Improving Compositional Generalization in Math Word Problem Solving
To improve the compositional generalization in MWP solving, we propose an iterative data augmentation method that includes diverse compositional variation into training data and could collaborate with MWP methods.
Disentangling Identity and Pose for Facial Expression Recognition
Combining identity and pose feature, a neutral face of input individual should be generated by the decoder.
Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective
Specifically, we consider the generation of cross-domain videos from two sets of latent factors, one encoding the static information and another encoding the dynamic information.
Boosting Facial Expression Recognition by A Semi-Supervised Progressive Teacher
On the one hand, PT introduces semi-supervised learning method to relieve the shortage of data in FER.
Facial Expression Recognition
Facial Expression Recognition (FER)
FedNoiL: A Simple Two-Level Sampling Method for Federated Learning with Noisy Labels
Federated learning (FL) aims at training a global model on the server side while the training data are collected and located at the local devices.
An Empirical Study of Memorization in NLP
We empirically show that our memorization attribution method is faithful, and share our interesting finding that the top-memorized parts of a training instance tend to be features negatively correlated with the class label.
Personalized Federated Learning With Graph
We propose a novel structured federated learning (SFL) framework to learn both the global and personalized models simultaneously using client-wise relation graphs and clients' private data.
Exploring and Adapting Chinese GPT to Pinyin Input Method
We find that a frozen GPT achieves state-of-the-art performance on perfect pinyin.
Applications of blockchain and artificial intelligence technologies for enabling prosumers in smart grids: A review
The blockchain and artificial intelligence (AI) are innovative technologies to fulfil these two factors, by which the blockchain provides decentralised trading platforms for energy markets and the AI supports the optimal operational control of power systems.
On the Convergence of Clustered Federated Learning
Knowledge sharing and model personalization are essential components to tackle the non-IID challenge in federated learning (FL).
CO-PILOT: COllaborative Planning and reInforcement Learning On sub-Task curriculum
Next, a bottom-up traversal of the tree trains the RL agent from easier sub-tasks with denser rewards on bottom layers to harder ones on top layers and collects its cost on each sub-task train the planner in the next episode.
Handling Inter-class and Intra-class Imbalance in Class-imbalanced Learning
Class-imbalance is a common problem in machine learning practice.
False Correlation Reduction for Offline Reinforcement Learning
Offline reinforcement learning (RL) harnesses the power of massive datasets for resolving sequential decision problems.
Adaptive Q-learning for Interaction-Limited Reinforcement Learning
Specifically, we explicitly consider the difference between the online and offline data and apply an adaptive update scheme accordingly, i. e., a pessimistic update strategy for the offline dataset and a greedy or no pessimistic update scheme for the online dataset.
EAT-C: Environment-Adversarial sub-Task Curriculum for Efficient Reinforcement Learning
They are complementary in acquiring more informative feedback for RL: the planning policy provides dense reward of finishing easier sub-tasks while the environment policy modifies these sub-tasks to be adequately challenging and diverse so the RL agent can quickly adapt to different tasks/environments.
Digital Twins based Day-ahead Integrated Energy System Scheduling under Load and Renewable Energy Uncertainties
By constructing digital twins (DT) of an integrated energy system (IES), one can benefit from DT's predictive capabilities to improve coordinations among various energy converters, hence enhancing energy efficiency, cost savings and carbon emission reduction.
Uncertainty Regularized Policy Learning for Offline Reinforcement Learning
URPL adds an uncertainty regularization term in the policy learning objective to enforce to learn a more stable policy under the offline setting.
Pareto Policy Pool for Model-based Offline Reinforcement Learning
Model-based offline RL instead trains an environment model using a dataset of pre-collected experiences so online RL methods can learn in an offline manner by solely interacting with the model.
Vote for Nearest Neighbors Meta-Pruning of Self-Supervised Networks
Can we find a better initialization for a new task, e. g., a much smaller network closer to the final pruned model, by exploiting its similar tasks?
NOAHQA: Numerical Reasoning with Interpretable Graph Question Answering Dataset
While diverse question answering (QA) datasets have been proposed and contributed significantly to the development of deep learning models for QA tasks, the existing datasets fall short in two aspects.
Hierarchical Relation-Guided Type-Sentence Alignment for Long-Tail Relation Extraction with Distant Supervision
It consists of (1) a pairwise type-enriched sentence encoding module injecting both context-free and -related backgrounds to alleviate sentence-level wrong labeling, and (2) a hierarchical type-sentence alignment module enriching a sentence with the triple fact's basic attributes to support long-tail relations.
Sequential Diagnosis Prediction with Transformer and Ontological Representation
Sequential diagnosis prediction on the Electronic Health Record (EHR) has been proven crucial for predictive analytics in the medical domain.
Federated Learning for Open Banking
In the near future, it is foreseeable to have decentralized data ownership in the finance sector using federated learning.
Federated Learning for Privacy-Preserving Open Innovation Future on Digital Health
Implementing an open innovation framework in the healthcare industry, namely open health, is to enhance innovation and creative capability of health-related organisations by building a next-generation collaborative framework with partner organisations and the research community.
Multi-Center Federated Learning: Clients Clustering for Better Personalization
By comparison, a mixture of multiple global models could capture the heterogeneity across various clients if assigning the client to different global models (i. e., centers) in FL.
Complex Knowledge Base Question Answering: A Survey
Knowledge base question answering (KBQA) aims to answer a question over a knowledge base (KB).
Disentangling Hate in Online Memes
Our experiment results show that DisMultiHate is able to outperform state-of-the-art unimodal and multimodal baselines in the hateful meme classification task.
Ranked #4 on
Hateful Meme Classification
on HarMeme
Modeling Transitions of Focal Entities for Conversational Knowledge Base Question Answering
We propose a novel graph-based model to capture the transitions of focal entities and apply a graph neural network to derive a probability distribution of focal entities for each question, which is then combined with a standard KBQA module to perform answer ranking.
COSY: COunterfactual SYntax for Cross-Lingual Understanding
Pre-trained multilingual language models, e. g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance.
MIPO: Mutual Integration of Patient Journey and Medical Ontology for Healthcare Representation Learning
Hence, some recent works train healthcare representations by incorporating medical ontology, by self-supervised tasks like diagnosis prediction, but (1) the small-scale, monotonous ontology is insufficient for robust learning, and (2) critical contexts or dependencies underlying patient journeys are barely exploited to enhance ontology learning.
Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
Second, the bandwidth of existing graph convolutional filters is fixed.
Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translation
We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models.
A Survey on Complex Knowledge Base Question Answering: Methods, Challenges and Solutions
In this paper, we elaborately summarize the typical challenges and solutions for complex KBQA.
Investigating Math Word Problems using Pretrained Multilingual Language Models
In this paper, we revisit math word problems~(MWPs) from the cross-lingual and multilingual perspective.
FedProto: Federated Prototype Learning across Heterogeneous Clients
Heterogeneity across clients in federated learning (FL) usually hinders the optimization convergence and generalization performance when the aggregation of clients' knowledge occurs in the gradient space.
Cross-Topic Rumor Detection using Topic-Mixtures
After deriving a vector representation for each topic, given an instance, we derive a {``}topic mixture{''} vector for the instance based on its topic distribution.
A Low-Complexity ADMM-based Massive MIMO Detectors via Deep Neural Networks
An alternate direction method of multipliers (ADMM)-based detectors can achieve good performance in both small and large-scale multiple-input multiple-output (MIMO) systems.
Isometric Propagation Network for Generalized Zero-shot Learning
To resolve this problem, we propose Isometric Propagation Network (IPN), which learns to strengthen the relation between classes within each space and align the class dependency in the two spaces.
Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
Typical methods to study cognitive function are to record the electrical activities of animal neurons during the training of animals performing behavioral tasks.
Attention-Guided Black-box Adversarial Attacks with Large-Scale Multiobjective Evolutionary Optimization
In this paper, we propose an attention-guided black-box adversarial attack based on the large-scale multiobjective evolutionary optimization, termed as LMOA.
PICA: A Pixel Correlation-based Attentional Black-box Adversarial Attack
The studies on black-box adversarial attacks have become increasingly prevalent due to the intractable acquisition of the structural knowledge of deep neural networks (DNNs).
Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
In our approach, the student network aims to find the correct answer to the query, while the teacher network tries to learn intermediate supervision signals for improving the reasoning capacity of the student network.
Ranked #2 on
Semantic Parsing
on WebQuestionsSP
Extract Local Inference Chains of Deep Neural Nets
In this paper, we introduce an efficient method, \name, to extract the local inference chains by optimizing a differentiable sparse scoring for the filters and layers to preserve the outputs on given data from a local region.
MASP: Model-Agnostic Sample Propagation for Few-shot learning
Few-shot learning aims to train a classifier given only a few samples per class that are highly insufficient to describe the whole data distribution.
SemiNLL: A Framework of Noisy-Label Learning by Semi-Supervised Learning
We also instantiate our framework with different combinations, which set the new state of the art on benchmark-simulated and real-world datasets with noisy labels.
Confusable Learning for Large-class Few-Shot Classification
Specifically, our method maintains a dynamically updating confusion matrix, which analyzes confusable classes in the dataset.
A BERT-based Dual Embedding Model for Chinese Idiom Prediction
Specifically, we first match the embedding of each candidate idiom with the hidden representation corresponding to the blank in the context.
Cooperative Heterogeneous Deep Reinforcement Learning
Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws.
MESA: Boost Ensemble Imbalanced Learning with MEta-SAmpler
This makes MESA generally applicable to most of the existing learning models and the meta-sampler can be efficiently applied to new tasks.
Counterfactual Variable Control for Robust and Interpretable Question Answering
We then conduct two novel CVC inference methods (on trained models) to capture the effect of comprehensive reasoning as the final prediction.
RatE: Relation-Adaptive Translating Embedding for Knowledge Graph Completion
Many graph embedding approaches have been proposed for knowledge graph completion via link prediction.
Improving Long-Tail Relation Extraction with Collaborating Relation-Augmented Attention
Then, facilitated by the proposed base model, we introduce collaborating relation features shared among relations in the hierarchies to promote the relation-augmenting process and balance the training data for long-tail relations.
Cross-Thought for Sentence Encoder Pre-training
In this paper, we propose Cross-Thought, a novel approach to pre-training sequence encoder, which is instrumental in building reusable sequence embeddings for large-scale NLP tasks such as question answering.
Context Modeling with Evidence Filter for Multiple Choice Question Answering
In addition to the effective reduction of human efforts of our approach compared, through extensive experiments on OpenbookQA, we show that the proposed approach outperforms the models that use the same backbone and more training data; and our parameter analysis also demonstrates the interpretability of our approach.
Attribute Propagation Network for Graph Zero-shot Learning
To address this challenging task, most ZSL methods relate unseen test classes to seen(training) classes via a pre-defined set of attributes that can describe all classes in the same semantic space, so the knowledge learned on the training classes can be adapted to unseen classes.
BiteNet: Bidirectional Temporal Encoder Network to Predict Medical Outcomes
Electronic health records (EHRs) are longitudinal records of a patient's interactions with healthcare systems.
Improving Multimodal Named Entity Recognition via Entity Span Detection with Unified Multimodal Transformer
To tackle the first issue, we propose a multimodal interaction module to obtain both image-aware word representations and word-aware visual representations.
Multi-modal Named Entity Recognition
named-entity-recognition
+1
Query Graph Generation for Answering Multi-hop Complex Questions from Knowledge Bases
Previous work on answering complex questions from knowledge bases usually separately addresses two types of complexity: questions with constraints and questions with multiple hops of relations.
Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy
We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings.
A Universal Representation Transformer Layer for Few-Shot Image Classification
We consider the problem of multi-domain few-shot image classification, where unseen classes and examples come from diverse data sources.
Ranked #1 on
Few-Shot Image Classification
on Meta-Dataset Rank
Self-Attention Enhanced Patient Journey Understanding in Healthcare System
The key challenge of patient journey understanding is to design an effective encoding mechanism which can properly tackle the aforementioned multi-level structured patient journey data with temporal sequential visits and a set of medical codes.
Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
Modeling multivariate time series has long been a subject that has attracted researchers from a diverse range of fields including economics, finance, and traffic.
Ranked #1 on
Univariate Time Series Forecasting
on Electricity
Online non-convex learning for river pollution source identification
In this paper, novel gradient-based online learning algorithms are developed to investigate an important environmental application: real-time river pollution source identification, which aims at estimating the released mass, location, and time of a river pollution source based on downstream sensor data monitoring the pollution concentration.
Multi-Center Federated Learning: Clients Clustering for Better Personalization
However, due to the diverse nature of user behaviors, assigning users' gradients to different global models (i. e., centers) can better capture the heterogeneity of data distributions across users.
Aspect and Opinion Aware Abstractive Review Summarization with Reinforced Hard Typed Decoder
In this paper, we study abstractive review summarization. Observing that review summaries often consist of aspect words, opinion words and context words, we propose a two-stage reinforcement learning approach, which first predicts the output word type from the three types, and then leverages the predicted word type to generate the final word distribution. Experimental results on two Amazon product review datasets demonstrate that our method can consistently outperform several strong baseline approaches based on ROUGE scores.
Omni-Scale CNNs: a simple and effective kernel size configuration for time series classification
Particularly, it is a set of kernel sizes that can efficiently cover the best RF size across different datasets via consisting of multiple prime numbers according to the length of the time series.
Interpretable Rumor Detection in Microblogs by Attending to User Interactions
We propose a post-level attention model (PLAN) to model long distance interactions between tweets with the multi-head attention mechanism in a transformer network.
Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching
Transformer has been successfully applied to many natural language processing tasks.
Multimodal Story Generation on Plural Images
In this work, we propose the architecture to use images instead of text as the input of the text generation model, called StoryGen.
Self-Attention Enhanced Selective Gate with Entity-Aware Embedding for Distantly Supervised Relation Extraction
Distantly supervised relation extraction intrinsically suffers from noisy labels due to the strong assumption of distant supervision.
Two-Headed Monster And Crossed Co-Attention Networks
This paper presents some preliminary investigations of a new co-attention mechanism in neural transduction models.
What does BERT Learn from Multiple-Choice Reading Comprehension Datasets?
Based on our experiments on the 5 key MCRC datasets - RACE, MCTest, MCScript, MCScript2. 0, DREAM - we observe that 1) fine-tuned BERT mainly learns how keywords lead to correct prediction, instead of learning semantic understanding and reasoning; and 2) BERT does not need correct syntactic information to solve the task; 3) there exists artifacts in these datasets such that they can be solved even without the full context.
Temporal Self-Attention Network for Medical Concept Embedding
In this paper, we propose a medical concept embedding method based on applying a self-attention mechanism to represent each medical concept.
Learning to Propagate for Graph Meta-Learning
It can significantly improve tasks that suffer from insufficient training data, e. g., few shot learning.
Effective Search of Logical Forms for Weakly Supervised Knowledge-Based Question Answering
These two problems lead to a poorly-trained semantic parsing model.
Attributed Graph Clustering: A Deep Attentional Embedding Approach
Graph clustering is a fundamental task which discovers communities or groups in networks.
Ranked #8 on
Node Clustering
on Cora
Graph WaveNet for Deep Spatial-Temporal Graph Modeling
Spatial-temporal graph modeling is an important task to analyze the spatial relations and temporal trends of components in a system.
Ranked #5 on
Traffic Prediction
on NE-BJ
Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph
The resulting graph of prototypes can be continually re-used and updated for new tasks and classes.
MahiNet: A Neural Network for Many-Class Few-Shot Learning with Class Hierarchy
It addresses the ``many-class'' problem by exploring the class hierarchy, e. g., the coarse-class label that covers a subset of fine classes, which helps to narrow down the candidates for the fine class and is cheaper to obtain.
DAGCN: Dual Attention Graph Convolutional Networks
In this paper, we propose a novel framework called, dual attention graph convolutional networks (DAGCN) to address these problems.
Ranked #25 on
Graph Classification
on NCI1
Unsupervised Deep Structured Semantic Models for Commonsense Reasoning
Commonsense reasoning is fundamental to natural language understanding.
Ranked #2 on
Natural Language Understanding
on PDP60
Learning Graph Embedding with Adversarial Training Methods
Based on this framework, we derive two variants of adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively.
Ranked #7 on
Node Clustering
on Cora
Learning Private Neural Language Modeling with Attentive Aggregation
Federated learning (FL) provides a promising approach to learning private language modeling for intelligent personalized keyboard suggestion by training models in distributed clients rather than training in a central server.
Global Inference for Aspect and Opinion Terms Co-Extraction Based on Multi-Task Neural Networks
However, most existing methods fail to explicitly consider the syntactic relations among aspect terms and opinion terms, which may lead to the inconsistencies between the model predictions and the syntactic constraints.
Aspect Term Extraction and Sentiment Classification
Multi-Task Learning
+2
Improving Multi-label Emotion Classification via Sentiment Classification with Dual Attention Transfer Network
In this paper, we target at improving the performance of multi-label emotion classification with the help of sentiment classification.
Did you take the pill? - Detecting Personal Intake of Medicine from Twitter
We believe that the developed classifier has direct uses in the areas of psychology, health informatics, pharmacovigilance and affective computing for tracking moods, emotions and sentiments of patients expressing intake of medicine in social media.
Embedding WordNet Knowledge for Textual Entailment
In this paper, we study how we can improve a deep learning approach to textual entailment by incorporating lexical entailment relations from WordNet.
A Co-Matching Model for Multi-choice Reading Comprehension
Multi-choice reading comprehension is a challenging task, which involves the matching between a passage and a question-answer pair.
Tensorized Self-Attention: Efficiently Modeling Pairwise and Global Dependencies Together
Neural networks equipped with self-attention have parallelizable computation, light-weight structure, and the ability to capture both long-range and local dependencies.
Bi-Directional Block Self-Attention for Fast and Memory-Efficient Sequence Modeling
In this paper, we propose a model, called "bi-directional block self-attention network (Bi-BloSAN)", for RNN/CNN-free sequence encoding.
Adversarially Regularized Graph Autoencoder for Graph Embedding
Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics.
Ranked #5 on
Link Prediction
on Pubmed
Reinforced Self-Attention Network: a Hybrid of Hard and Soft Attention for Sequence Modeling
In this paper, we integrate both soft and hard attention into one context fusion model, "reinforced self-attention (ReSA)", for the mutual benefit of each other.
Ranked #56 on
Natural Language Inference
on SNLI
Modelling Domain Relationships for Transfer Learning on Retrieval-based Question Answering Systems in E-commerce
In this paper, we study transfer learning for the PI and NLI problems, aiming to propose a general framework, which can effectively and efficiently adapt the shared knowledge learned from a resource-rich source domain to a resource- poor target domain.
Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
We propose two methods, namely, strength-based re-ranking and coverage-based re-ranking, to make use of the aggregated evidence from different passages to better determine the answer.
Ranked #1 on
Open-Domain Question Answering
on Quasar
Marginalized graph autoencoder for graph clustering
In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering.
Leveraging Auxiliary Tasks for Document-Level Cross-Domain Sentiment Classification
In this paper, we study domain adaptation with a state-of-the-art hierarchical neural network for document-level sentiment classification.
DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding
Recurrent neural nets (RNN) and convolutional neural nets (CNN) are widely used on NLP tasks to capture the long-term and local dependencies, respectively.
Ranked #68 on
Natural Language Inference
on SNLI
R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering
Second, we propose a novel method that jointly trains the Ranker along with an answer-generation Reader model, based on reinforcement learning.
Ranked #4 on
Open-Domain Question Answering
on Quasar
Can Syntax Help? Improving an LSTM-based Sentence Compression Model for New Domains
In this paper, we study how to improve the domain adaptability of a deletion-based Long Short-Term Memory (LSTM) neural network model for sentence compression.
Ranked #6 on
Sentence Compression
on Google Dataset
Pairwise Relation Classification with Mirror Instances and a Combined Convolutional Neural Network
Relation classification is the task of classifying the semantic relations between entity pairs in text.
Hashtag Recommendation with Topical Attention-Based LSTM
Microblogging services allow users to create hashtags to categorize their posts.
A Compare-Aggregate Model for Matching Text Sequences
We particularly focus on the different comparison functions we can use to match two vectors.
Machine Comprehension Using Match-LSTM and Answer Pointer
We propose two ways of using Pointer Net for our task.
Ranked #47 on
Question Answering
on SQuAD1.1 dev
Learning Natural Language Inference with LSTM
On the SNLI corpus, our model achieves an accuracy of 86. 1%, outperforming the state of the art.
Ranked #60 on
Natural Language Inference
on SNLI
