Search Results for author:
Found 156 papers, 59 papers with code
Summarizing Behavioral Change Goals from SMS Exchanges to Support Health Coaches
In this paper, we present our work towards assisting health coaches by extracting the physical activity goal the user and coach negotiate via text messages.
Towards Enhancing Health Coaching Dialogue in Low-Resource Settings
In this paper, we propose to build a dialogue system that converses with the patients, helps them create and accomplish specific goals, and can address their emotions with empathy.
Semantic Novelty Detection in Natural Language Descriptions
This paper proposes to study a fine-grained semantic novelty detection task, which can be illustrated with the following example.
Human-Human Health Coaching via Text Messages: Corpus, Annotation, and Analysis
In this paper, we discuss these schemas and briefly talk about their application for automatically extracting activity goals and annotating the second round of data, collected with different health coaches and patients.
Class Incremental Learning via Likelihood Ratio Based Task Prediction
An emerging theoretically justified and effective approach is to train a task-specific model for each task in a shared network for all tasks based on a task-incremental learning (TIL) method to deal with forgetting.
Zero-shot information extraction from radiological reports using ChatGPT
Information extraction is the strategy to transform the sequence of characters into structured data, which can be employed for secondary analysis.
CT-Net: Arbitrary-Shaped Text Detection via Contour Transformer
Contour based scene text detection methods have rapidly developed recently, but still suffer from inaccurate frontend contour initialization, multi-stage error accumulation, or deficient local information aggregation.
Parameter-Level Soft-Masking for Continual Learning
Although several techniques have achieved learning with no CF, they attain it by letting each task monopolize a sub-network in a shared network, which seriously limits knowledge transfer (KT) and causes over-consumption of the network capacity, i. e., as more tasks are learned, the performance deteriorates.
Class-Incremental Learning based on Label Generation
Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF).
Dealing with Cross-Task Class Discrimination in Online Continual Learning
A novel optimization objective with a gradient-based adaptive method is proposed to dynamically deal with the problem in the online CL process.
Sentiment Analysis in the Era of Large Language Models: A Reality Check
This paper aims to provide a comprehensive investigation into the capabilities of LLMs in performing various sentiment analysis tasks, from conventional sentiment classification to aspect-based sentiment analysis and multifaceted analysis of subjective texts.
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.
Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast
Existing research has shown that a multilingual pre-trained language model fine-tuned with one (source) language also performs well on downstream tasks for non-source languages, even though no fine-tuning is done on these languages.
A Unified Evaluation Framework for Novelty Detection and Accommodation in NLP with an Instantiation in Authorship Attribution
To initiate a systematic research in this important area of 'dealing with novelties', we introduce 'NoveltyTask', a multi-stage task to evaluate a system's performance on pipelined novelty 'detection' and 'accommodation' tasks.
Open-World Continual Learning: Unifying Novelty Detection and Continual Learning
The key theoretical result is that regardless of whether WP and OOD detection (or TP) are defined explicitly or implicitly by a CIL algorithm, good WP and good OOD detection are necessary and sufficient conditions for good CIL, which unifies novelty or OOD detection and continual learning (CIL, in particular).
Grab What You Need: Rethinking Complex Table Structure Recognition with Flexible Components Deliberation
Recently, Table Structure Recognition (TSR) task, aiming at identifying table structure into machine readable formats, has received increasing interest in the community.
Continual Pre-training of Language Models
A novel proxy is also proposed to preserve the general knowledge in the original LM.
Ranked #1 on
Continual Pretraining
on SciERC
Adapting a Language Model While Preserving its General Knowledge
This paper shows that the existing methods are suboptimal and proposes a novel method to perform a more informed adaptation of the knowledge in the LM by (1) soft-masking the attention heads based on their importance to best preserve the general knowledge in the LM and (2) contrasting the representations of the general and the full (both general and domain knowledge) to learn an integrated representation with both general and domain-specific knowledge.
Joint Spatio-Temporal Modeling for the Semantic Change Detection in Remote Sensing Images
Semantic Change Detection (SCD) refers to the task of simultaneously extracting the changed areas and the semantic categories (before and after the changes) in Remote Sensing Images (RSIs).
Dependency-aware Self-training for Entity Alignment
Entity Alignment (EA), which aims to detect entity mappings (i. e. equivalent entity pairs) in different Knowledge Graphs (KGs), is critical for KG fusion.
Guiding Neural Entity Alignment with Compatibility
Making compatible predictions thus should be one of the goals of training an EA model along with fitting the labelled data: this aspect however is neglected in current methods.
Continual Learning of Natural Language Processing Tasks: A Survey
Continual learning (CL) is a learning paradigm that emulates the human capability of learning and accumulating knowledge continually without forgetting the previously learned knowledge and also transferring the learned knowledge to help learn new tasks better.
Lifelong and Continual Learning Dialogue Systems
This book introduces the new paradigm of lifelong learning dialogue systems to endow chatbots the ability to learn continually by themselves through their own self-initiated interactions with their users and working environments to improve themselves.
A Theoretical Study on Solving Continual Learning
Continual learning (CL) learns a sequence of tasks incrementally.
Semantic Novelty Detection and Characterization in Factual Text Involving Named Entities
Much of the existing work on text novelty detection has been studied at the topic level, i. e., identifying whether the topic of a document or a sentence is novel or not.
Knowledge-Guided Exploration in Deep Reinforcement Learning
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of state-action permissibility (SAP).
Continual Training of Language Models for Few-Shot Learning
Recent work on applying large language models (LMs) achieves impressive performance in many NLP applications.
Ranked #1 on
Continual Pretraining
on AG News
High-quality Task Division for Large-scale Entity Alignment
To include in the EA subtasks a high proportion of the potential mappings originally present in the large EA task, we devise a counterpart discovery method that exploits the locality principle of the EA task and the power of trained EA models.
A Multi-Head Model for Continual Learning via Out-of-Distribution Replay
Instead of using the saved samples in memory to update the network for previous tasks/classes in the existing approach, MORE leverages the saved samples to build a task specific classifier (adding a new classification head) without updating the network learned for previous tasks/classes.
Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings
Learning task-oriented dialog policies via reinforcement learning typically requires large amounts of interaction with users, which in practice renders such methods unusable for real-world applications.
TextDCT: Arbitrary-Shaped Text Detection via Discrete Cosine Transform Mask
Arbitrary-shaped scene text detection is a challenging task due to the variety of text changes in font, size, color, and orientation.
Beyond Opinion Mining: Summarizing Opinions of Customer Reviews
In this tutorial, we present various aspects of opinion summarization that are useful for researchers and practitioners.
KETOD: Knowledge-Enriched Task-Oriented Dialogue
We also propose two new models, SimpleToDPlus and Combiner, for the proposed task.
Unsupervised Meta Learning With Multiview Constraints for Hyperspectral Image Small Sample set Classification
However, the existing methods based on meta learning still need to construct a labeled source data set with several pre-collected HSIs, and must utilize a large number of labeled samples for meta-training, which is actually time-consuming and labor-intensive.
Open-set Recognition via Augmentation-based Similarity Learning
In many practical scenarios, this is not the case because there are unknowns or unseen class samples in the test data, which is called the open set scenario, and the unknowns need to be detected.
Continual Learning Based on OOD Detection and Task Masking
Existing continual learning techniques focus on either task incremental learning (TIL) or class incremental learning (CIL) problem, but not both.
AI Autonomy : Self-Initiated Open-World Continual Learning and Adaptation
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can (1) learn by themselves continually in a self-motivated and self-initiated manner rather than being retrained offline periodically on the initiation of human engineers and (2) accommodate or adapt to unexpected or novel circumstances.
Ensemble Semi-supervised Entity Alignment via Cycle-teaching
We also design a conflict resolution mechanism to resolve the alignment conflict when combining the new alignment of an aligner and that from its teacher.
Zero-Shot Aspect-Based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) typically requires in-domain annotated data for supervised training/fine-tuning.
Show, Deconfound and Tell: Image Captioning With Causal Inference
In the encoding stage, the IOD is able to disentangle the region-based visual features by deconfounding the visual confounder.
Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
To the best of our knowledge, no technique has been proposed to learn a sequence of mixed similar and dissimilar tasks that can deal with forgetting and also transfer knowledge forward and backward.
Ranked #1 on
Continual Learning
on F-CelebA (10 tasks)
Continual Learning with Knowledge Transfer for Sentiment Classification
In this setting, the CL system learns a sequence of SC tasks incrementally in a neural network, where each task builds a classifier to classify the sentiment of reviews of a particular product category or domain.
Ranked #4 on
Continual Learning
on DSC (10 tasks)
Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks
This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks.
Ranked #3 on
Continual Learning
on ASC (19 tasks)
CLASSIC: Continual and Contrastive Learning of Aspect Sentiment Classification Tasks
The key novelty is a contrastive continual learning method that enables both knowledge transfer across tasks and knowledge distillation from old tasks to the new task, which eliminates the need for task ids in testing.
Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning
Although several papers have tried to deal with both CF and KT, our experiments show that they suffer from serious CF when the tasks do not have much shared knowledge.
Ranked #1 on
Continual Learning
on DSC (10 tasks)
BNS: Building Network Structures Dynamically for Continual Learning
Continual learning (CL) of a sequence of tasks is often accompanied with the catastrophic forgetting(CF) problem.
Neural Collaborative Graph Machines for Table Structure Recognition
We also show that the proposed NCGM can modulate collaborative pattern of different modalities conditioned on the context of intra-modality cues, which is vital for diversified table cases.
Ranked #5 on
Table Recognition
on PubTabNet
Defeating Catastrophic Forgetting via Enhanced Orthogonal Weights Modification
what is the upper bound of the learningable tasks sequentially for a given CL method?
Self-Initiated Open World Learning for Autonomous AI Agents
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained periodically on the initiation of human engineers using expanded training data.
ActiveEA: Active Learning for Neural Entity Alignment
Entity Alignment (EA) aims to match equivalent entities across different Knowledge Graphs (KGs) and is an essential step of KG fusion.
Efficient Out-of-Distribution Detection via CVAE data Generation
Recently, contrastive loss with data augmentation and pseudo class creation has been shown to produce markedly better results for out-of-distribution (OOD) detection than previous methods.
Gradient Imbalance and solution in Online Continual learning
Most existing techniques for online continual learning are based on experience-replay.
Continual Learning Using Pseudo-Replay via Latent Space Sampling
PLS is not only simple and efficient but also does not invade data privacy due to the fact that it works in the latent feature space.
Partially Relaxed Masks for Lightweight Knowledge Transfer without Forgetting in Continual Learning
The goal of this work is to endow such systems with the additional ability to transfer knowledge among tasks when the tasks are similar and have shared knowledge to achieve higher accuracy.
Zero-Shot Dialogue State Tracking via Cross-Task Transfer
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data.
Zero-Shot Out-of-Distribution Detection Based on the Pre-trained Model CLIP
In an out-of-distribution (OOD) detection problem, samples of known classes(also called in-distribution classes) are used to train a special classifier.
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
+2
Concept-Based Label Embedding via Dynamic Routing for Hierarchical Text Classification
In this paper, we propose a novel concept-based label embedding method that can explicitly represent the concept and model the sharing mechanism among classes for the hierarchical text classification.
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data.
Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data.
Analyzing the Forgetting Problem in Pretrain-Finetuning of Open-domain Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Learning to Dynamically Select Between Reward Shaping Signals
Automatic reward shaping is one approach to solving this problem, using automatic identification and modulation of shaping reward signals that are more informative about how agents should behave in any given scenario to learn and adapt faster.
Continual Learning in Task-Oriented Dialogue Systems
Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining.
A Deep Reinforcement Learning Approach for Ramp Metering Based on Traffic Video Data
Ramp metering that uses traffic signals to regulate vehicle flows from the on-ramps has been widely implemented to improve vehicle mobility of the freeway.
Translation vs. Dialogue: A Comparative Analysis of Sequence-to-Sequence Modeling
Understanding neural models is a major topic of interest in the deep learning community.
HRN: A Holistic Approach to One Class Learning
Existing neural network based one-class learning methods mainly use various forms of auto-encoders or GAN style adversarial training to learn a latent representation of the given one class of data.
Bayes-enhanced Lifelong Attention Networks for Sentiment Classification
After each sentiment classification task is learned, its knowledge is retained to help future task learning.
Attention Aware Cost Volume Pyramid Based Multi-view Stereo Network for 3D Reconstruction
This strategy estimates the depth map at coarsest level, while the depth maps at finer levels are considered as the upsampled depth map from previous level with pixel-wise depth residual.
Lifelong Knowledge Learning in Rule-based Dialogue Systems
One of the main weaknesses of current chatbots or dialogue systems is that they do not learn online during conversations after they are deployed.
MP-ResNet: Multi-path Residual Network for the Semantic segmentation of High-Resolution PolSAR Images
This CNN architecture can be used as a baseline method for future studies on the semantic segmentation of PolSAR images.
Using the Past Knowledge to Improve Sentiment Classification
It proposes a new lifelong learning model (called L2PG) that can retain and selectively transfer the knowledge learned in the past to help learn the new task.
Understanding Pre-trained BERT for Aspect-based Sentiment Analysis
Most features in the representation of an aspect are dedicated to the fine-grained semantics of the domain (or product category) and the aspect itself, instead of carrying summarized opinions from its context.
Aspect-Based Sentiment Analysis (ABSA)
Language Modelling
+1
Adding Chit-Chat to Enhance Task-Oriented Dialogues
Existing dialogue corpora and models are typically designed under two disjoint motives: while task-oriented systems focus on achieving functional goals (e. g., booking hotels), open-domain chatbots aim at making socially engaging conversations.
NUANCED: Natural Utterance Annotation for Nuanced Conversation with Estimated Distributions
As there is no clean mapping for a user's free form utterance to an ontology, we first model the user preferences as estimated distributions over the system ontology and map the users' utterances to such distributions.
A Knowledge-Driven Approach to Classifying Object and Attribute Coreferences in Opinion Mining
Classifying and resolving coreferences of objects (e. g., product names) and attributes (e. g., product aspects) in opinionated reviews is crucial for improving the opinion mining performance.
Controllable Text Generation with Focused Variation
This work introduces Focused-Variation Network (FVN), a novel model to control language generation.
Text Classification with Novelty Detection
In this paper, we propose a significantly more effective approach that converts the original problem to a pair-wise matching problem and then outputs how probable two instances belong to the same class.
Lifelong Learning Dialogue Systems: Chatbots that Self-Learn On the Job
Due to the huge amount of manual effort involved, they are difficult to scale and also tend to produce many errors ought to their limited ability to understand natural language and the limited knowledge in their KBs.
Active Deep Densely Connected Convolutional Network for Hyperspectral Image Classification
First, a deep densely connected convolutional network is considered for hyperspectral image classification.
Feature Projection for Improved Text Classification
In this paper, we propose a novel angle to further improve this representation learning, i. e., feature projection.
Entity-Aware Dependency-Based Deep Graph Attention Network for Comparative Preference Classification
This paper studies the task of comparative preference classification (CPC).
User Memory Reasoning for Conversational Recommendation
We study a conversational recommendation model which dynamically manages users' past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph, to allow for natural interactions and accurate recommendations.
Detecting Domain Polarity-Changes of Words in a Sentiment Lexicon
We refer to this problem as domain polarity-changes of words.
DomBERT: Domain-oriented Language Model for Aspect-based Sentiment Analysis
This paper focuses on learning domain-oriented language models driven by end tasks, which aims to combine the worlds of both general-purpose language models (such as ELMo and BERT) and domain-specific language understanding.
Computational Performance of a Germline Variant Calling Pipeline for Next Generation Sequencing
With the booming of next generation sequencing technology and its implementation in clinical practice and life science research, the need for faster and more efficient data analysis methods becomes pressing in the field of sequencing.
Transformation of Dense and Sparse Text Representations
The key idea of the proposed approach is to use a Forward Transformation to transform dense representations to sparse representations.
A Failure of Aspect Sentiment Classifiers and an Adaptive Re-weighting Solution
Aspect-based sentiment classification (ASC) is an important task in fine-grained sentiment analysis.~Deep supervised ASC approaches typically model this task as a pair-wise classification task that takes an aspect and a sentence containing the aspect and outputs the polarity of the aspect in that sentence.
Building an Application Independent Natural Language Interface
Traditional approaches to building natural language (NL) interfaces typically use a semantic parser to parse the user command and convert it to a logical form, which is then translated to an executable action in an application.
Analyzing the Forgetting Problem in the Pretrain-Finetuning of Dialogue Response Models
We find that mix-review effectively regularizes the finetuning process, and the forgetting problem is alleviated to some extent.
Continual Learning via Principal Components Projection
The idea is that in learning a new task, if we can ensure that the gradient updates will only occur in the orthogonal directions to the input vectors of the previous tasks, then the weight updates for learning the new task will not affect the previous tasks.
Learning from Positive and Unlabeled Data with Adversarial Training
Positive-unlabeled (PU) learning learns a binary classifier using only positive and unlabeled examples without labeled negative examples.
Learning with Noisy Labels for Sentence-level Sentiment Classification
We propose a novel DNN model called NetAb (as shorthand for convolutional neural Networks with Ab-networks) to handle noisy labels during training.
Modeling Multi-Action Policy for Task-Oriented Dialogues
Dialogue management (DM) plays a key role in the quality of the interaction with the user in a task-oriented dialogue system.
Flexibly-Structured Model for Task-Oriented Dialogues
It is based on a simple and practical yet very effective sequence-to-sequence approach, where language understanding and state tracking tasks are modeled jointly with a structured copy-augmented sequential decoder and a multi-label decoder for each slot.
Lifelong and Interactive Learning of Factual Knowledge in Dialogues
Dialogue systems are increasingly using knowledge bases (KBs) storing real-world facts to help generate quality responses.
Forward and Backward Knowledge Transfer for Sentiment Classification
That is, it is possible to improve the NB classifier for a task by improving its model parameters directly by using the retained knowledge from other tasks.
DOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
This paper focuses on two related subtasks of aspect-based sentiment analysis, namely aspect term extraction and aspect sentiment classification, which we call aspect term-polarity co-extraction.
Aspect-Based Sentiment Analysis (ABSA)
Sentiment Classification
+1
GSN: A Graph-Structured Network for Multi-Party Dialogues
Existing neural models for dialogue response generation assume that utterances are sequentially organized.
Spectral Perturbation Meets Incomplete Multi-view Data
In this work, we show a strong link between perturbation risk bounds and incomplete multi-view clustering.
Controlled CNN-based Sequence Labeling for Aspect Extraction
The modified CNN has two types of control modules.
A Guider Network for Multi-Dual Learning
A large amount of parallel data is needed to train a strong neural machine translation (NMT) system.
Overcoming Catastrophic Forgetting via Model Adaptation
Several continual learning methods have been proposed to address the problem.
Attention-based 3D Convolutional Network for Alzheimer’s Disease Diagnosis and Biomarkers Exploration
Modern advancements in deep learning provide a powerful framework for disease classification based on neuroimaging data.
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC.
Review Conversational Reading Comprehension
Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses.
Guided Exploration in Deep Reinforcement Learning
This paper proposes a new method to drastically speed up deep reinforcement learning (deep RL) training for problems that have the property of \textit{state-action permissibility} (SAP).
Open-world Learning and Application to Product Classification
Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training.
An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection
With the abundant attributes in existing entities and knowledge in other domains, we successfully solve the problem of data scarcity in the cold-start settings.
Target-Sensitive Memory Networks for Aspect Sentiment Classification
In MNs, attention mechanism plays a crucial role in detecting the sentiment context for the given target.
Bootstrapping a Neural Conversational Agent with Dialogue Self-Play, Crowdsourcing and On-Line Reinforcement Learning
End-to-end neural models show great promise towards building conversational agents that are trained from data and on-line experience using supervised and reinforcement learning.
End-to-End Learning of Task-Oriented Dialogs
In this thesis proposal, we address the limitations of conventional pipeline design of task-oriented dialog systems and propose end-to-end learning solutions.
Adversarial Learning of Task-Oriented Neural Dialog Models
We further discuss the covariate shift problem in online adversarial dialog learning and show how we can address that with partial access to user feedback.
Lifelong Domain Word Embedding via Meta-Learning
Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks.
Improving Aspect Term Extraction with Bidirectional Dependency Tree Representation
The key idea is to explicitly incorporate both representations gained separately from the bottom-up and top-down propagation on the given dependency syntactic tree.
Double Embeddings and CNN-based Sequence Labeling for Aspect Extraction
Unlike other highly sophisticated supervised deep learning models, this paper proposes a novel and yet simple CNN model employing two types of pre-trained embeddings for aspect extraction: general-purpose embeddings and domain-specific embeddings.
Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems
To address this challenge, we propose a hybrid imitation and reinforcement learning method, with which a dialogue agent can effectively learn from its interaction with users by learning from human teaching and feedback.
Disentangling Aspect and Opinion Words in Target-based Sentiment Analysis using Lifelong Learning
Stage one extracts/groups the target-related words (call t-words) for a given target.
Towards a Continuous Knowledge Learning Engine for Chatbots
We model the task as an open-world knowledge base completion problem and propose a novel technique called lifelong interactive learning and inference (LiLi) to solve it.
Deep Learning for Sentiment Analysis : A Survey
Deep learning has emerged as a powerful machine learning technique that learns multiple layers of representations or features of the data and produces state-of-the-art prediction results.
Contextual and Position-Aware Factorization Machines for Sentiment Classification
While existing machine learning models have achieved great success for sentiment classification, they typically do not explicitly capture sentiment-oriented word interaction, which can lead to poor results for fine-grained analysis at the snippet level (a phrase or sentence).
Unseen Class Discovery in Open-world Classification
It is reasonable to assume that this knowledge can be transferred to the rejected examples and used to discover the hidden unseen classes in them.
Lifelong Learning for Sentiment Classification
This paper proposes a novel lifelong learning (LL) approach to sentiment classification.
Lifelong Word Embedding via Meta-Learning
We observe that domains are not isolated and a small domain corpus can leverage the learned knowledge from many past domains to augment that corpus in order to generate high-quality embeddings.
Topic-Based Question Generation
In the paper, we propose a new question generation problem, which also requires the input of a target topic in addition to a piece of descriptive text.
Context-aware Path Ranking for Knowledge Base Completion
PR algorithms enumerate paths between entity pairs in a KB and use those paths as features to train a model for missing fact prediction.
Multi-Domain Adversarial Learning for Slot Filling in Spoken Language Understanding
Model that produces such shared representations can be combined with models trained on individual domain SLU data to reduce the amount of training samples required for developing a new domain.
End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning
We show that deep RL based optimization leads to significant improvement on task success rate and reduction in dialogue length comparing to supervised training model.
Customized Nonlinear Bandits for Online Response Selection in Neural Conversation Models
Moreover, we report encouraging response selection performance of the proposed neural bandit model using the Recall@k metric for a small set of online training samples.
Reconstruction of Hidden Representation for Robust Feature Extraction
We believe that minimizing the reconstruction error of the hidden representation is more robust than minimizing the Frobenius norm of the Jacobian matrix of the hidden representation.
DOC: Deep Open Classification of Text Documents
As learning is used increasingly in dynamic open environments where some new/test documents may not belong to any of the training classes, identifying these novel documents during classification presents an important problem.
Iterative Policy Learning in End-to-End Trainable Task-Oriented Neural Dialog Models
In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems.
Sentiment Lexicon Expansion Based on Neural PU Learning, Double Dictionary Lookup, and Polarity Association
Although many sentiment lexicons in different languages exist, most are not comprehensive.
An End-to-End Trainable Neural Network Model with Belief Tracking for Task-Oriented Dialog
We present a novel end-to-end trainable neural network model for task-oriented dialog systems.
Lifelong Learning CRF for Supervised Aspect Extraction
This paper makes a focused contribution to supervised aspect extraction.
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents.
Dialog Context Language Modeling with Recurrent Neural Networks
In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling.
Supervised Opinion Aspect Extraction by Exploiting Past Extraction Results
When "screen" appears in a review of a new domain (or product), it is likely to be an aspect too.
Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks
On SLU tasks, our joint model outperforms the independent task training model by 22. 3% on intent detection error rate, with slight degradation on slot filling F1 score.
Ranked #3 on
Intent Detection
on ATIS
Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling
Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition.
Ranked #2 on
Intent Detection
on ATIS
