Search Results for author:
Found 192 papers, 91 papers with code
Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling
Deployed spoken dialog systems receive user input in the form of automatic speech recognition (ASR) transcripts, and simply applying NER model trained on written text to ASR transcripts often leads to low accuracy because compared to written text, ASR transcripts lack important cues such as punctuation and capitalization.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals
Recommendation dialogs require the system to build a social bond with users to gain trust and develop affinity in order to increase the chance of a successful recommendation.
DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs
Real-world conversational agents must effectively handle long conversations that span multiple contexts.
Towards Socially Intelligent Agents with Mental State Transition and Human Value
One of which is to track the agent’s mental state transition and teach the agent to make decisions guided by its value like a human.
Fantastic Questions and Where to Find Them: FairytaleQA – An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Improving Conversational Recommendation Systems’ Quality with Context-Aware Item Meta-Information
In this paper, we propose a simple yet effective architecture comprising a pre-trained language model (PLM) and an item metadata encoder to integrate the recommendation and the dialog generation better.
CGIM: A Cycle Guided Interactive Learning Model for Consistency Identification in Task-oriented Dialogue
Consistency identification in task-oriented dialog (CI-ToD) usually consists of three subtasks, aiming to identify inconsistency between current system response and current user response, dialog history and the corresponding knowledge base.
ErAConD: Error Annotated Conversational Dialog Dataset for Grammatical Error Correction
Currently available grammatical error correction (GEC) datasets are compiled using essays or other long-form text written by language learners, limiting the applicability of these datasets to other domains such as informal writing and conversational dialog.
Growing a Twig to Accelerate Large Vision-Language Models
Despite the success of these token pruning methods, they still suffer from two major shortcomings: (i) considerable accuracy drop due to insensitive attention signals in early layers, and (ii) limited speedup when generating long responses (e. g., 30 tokens).
Program Synthesis Dialog Agents for Interactive Decision-Making
Many real-world eligibility problems, ranging from medical diagnosis to tax planning, can be mapped to decision problems expressed in natural language, wherein a model must make a binary choice based on user features.
Fréchet Cumulative Covariance Net for Deep Nonlinear Sufficient Dimension Reduction with Random Objects
Nonlinear sufficient dimension reduction\citep{libing_generalSDR}, which constructs nonlinear low-dimensional representations to summarize essential features of high-dimensional data, is an important branch of representation learning.
ConFit v2: Improving Resume-Job Matching using Hypothetical Resume Embedding and Runner-Up Hard-Negative Mining
A reliable resume-job matching system helps a company recommend suitable candidates from a pool of resumes and helps a job seeker find relevant jobs from a list of job posts.
A General Framework for Inference-time Scaling and Steering of Diffusion Models
For steering text-to-image models with a human preference reward, we find that FK steering a 0. 8B parameter model outperforms a 2. 6B parameter fine-tuned model on prompt fidelity, with faster sampling and no training.
Neural Networks Perform Sufficient Dimension Reduction
This paper investigates the connection between neural networks and sufficient dimension reduction (SDR), demonstrating that neural networks inherently perform SDR in regression tasks under appropriate rank regularizations.
Probability-density-aware Semi-supervised Learning
Semi-supervised learning (SSL) assumes that neighbor points lie in the same category (neighbor assumption), and points in different clusters belong to various categories (cluster assumption).
PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles
While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can host locally are often less capable than proprietary frontier models.
ExACT: Teaching AI Agents to Explore with Reflective-MCTS and Exploratory Learning
Autonomous agents have demonstrated significant potential in automating complex multistep decision-making tasks.
ACE: A LLM-based Negotiation Coaching System
To test the effectiveness of ACE-generated feedback, we conducted a user experiment with two consecutive trials of negotiation and found that it improves negotiation performances significantly compared to a system that doesn't provide feedback and one which uses an alternative method of providing feedback.
A Fairness-Driven Method for Learning Human-Compatible Negotiation Strategies
Despite recent advancements in AI and NLP, negotiation remains a difficult domain for AI agents.
Enhancing Skin Lesion Diagnosis with Ensemble Learning
To further enhance classification accuracy, we developed ensemble models employing max voting, average voting, and stacking, resulting in accuracies of 0. 803, 0. 82, and 0. 83.
Deep Learning for Lung Disease Classification Using Transfer Learning and a Customized CNN Architecture with Attention
Eventually, our own model, MobileNet-Lung based on MobileNetV2, with fine-tuning and an additional layer of attention within feature layers, was invented to tackle the lung disease classification task and achieved an accuracy of 0. 933.
LIONs: An Empirically Optimized Approach to Align Language Models
Alignment is a crucial step to enhance the instruction-following and conversational abilities of language models.
DECOR: Improving Coherence in L2 English Writing with a Novel Benchmark for Incoherence Detection, Reasoning, and Rewriting
To bridge this gap, we introduce DECOR, a novel benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoherent sentences.
EDEN: Empathetic Dialogues for English learning
Student passion and perseverance, or grit, has been associated with language learning success.
VarBench: Robust Language Model Benchmarking Through Dynamic Variable Perturbation
As large language models achieve impressive scores on traditional benchmarks, an increasing number of researchers are becoming concerned about benchmark data leakage during pre-training, commonly known as the data contamination problem.
TinyStyler: Efficient Few-Shot Text Style Transfer with Authorship Embeddings
The goal of text style transfer is to transform the style of texts while preserving their original meaning, often with only a few examples of the target style.
Application of Multimodal Fusion Deep Learning Model in Disease Recognition
This paper introduces an innovative multi-modal fusion deep learning approach to overcome the drawbacks of traditional single-modal recognition techniques.
Imp: Highly Capable Large Multimodal Models for Mobile Devices
By harnessing the capabilities of large language models (LLMs), recent large multimodal models (LMMs) have shown remarkable versatility in open-world multimodal understanding.
Ranked #85 on
Visual Question Answering
on MM-Vet
Research on Intelligent Aided Diagnosis System of Medical Image Based on Computer Deep Learning
This paper combines Struts and Hibernate two architectures together, using DAO (Data Access Object) to store and access data.
Using Adaptive Empathetic Responses for Teaching English
Existing English-teaching chatbots rarely incorporate empathy explicitly in their feedback, but empathetic feedback could help keep students engaged and reduce learner anxiety.
Semi-supervised Fréchet Regression
This paper explores the field of semi-supervised Fr\'echet regression, driven by the significant costs associated with obtaining non-Euclidean labels.
Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs).
LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
Retrieval-augmented question-answering systems combine retrieval techniques with large language models to provide answers that are more accurate and informative.
Getting Serious about Humor: Crafting Humor Datasets with Unfunny Large Language Models
Humor is a fundamental facet of human cognition and interaction.
Parallel Structures in Pre-training Data Yield In-Context Learning
Pre-trained language models (LMs) are capable of in-context learning (ICL): they can adapt to a task with only a few examples given in the prompt without any parameter update.
The Mirrored Influence Hypothesis: Efficient Data Influence Estimation by Harnessing Forward Passes
Inspired by this, we introduce a new method for estimating the influence of training data, which requires calculating gradients for specific test samples, paired with a forward pass for each training point.
State Value Generation with Prompt Learning and Self-Training for Low-Resource Dialogue State Tracking
Experimental results on the MultiWOZ 2. 1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters.
ConFit: Improving Resume-Job Matching using Data Augmentation and Contrastive Learning
A reliable resume-job matching system helps a company find suitable candidates from a pool of resumes, and helps a job seeker find relevant jobs from a list of job posts.
GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow
However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers.
ProLex: A Benchmark for Language Proficiency-oriented Lexical Substitution
To bridge this gap, we propose a new task, language proficiency-oriented lexical substitution.
MPOD123: One Image to 3D Content Generation Using Mask-enhanced Progressive Outline-to-Detail Optimization
Specifically in the first stage MPOD123 utilizes the pretrained view-conditioned diffusion model to guide the outline shape optimization of the 3D content.
SPD-DDPM: Denoising Diffusion Probabilistic Models in the Symmetric Positive Definite Space
On the other hand, the model unconditionally learns the probability distribution of the data $p(X)$ and generates samples that conform to this distribution.
End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions
End-to-end task-oriented dialogue (EToD) can directly generate responses in an end-to-end fashion without modular training, which attracts escalating popularity.
Teaching Language Models to Self-Improve through Interactive Demonstrations
The self-improving ability of large language models (LLMs), enabled by prompting them to analyze and revise their own outputs, has garnered significant interest in recent research.
Alexpaca: Learning Factual Clarification Question Generation Without Examples
To enable evaluation of factual domain clarification question generation, We present a new task that focuses on the ability to elicit missing information in multi-hop reasoning tasks.
Building Persona Consistent Dialogue Agents with Offline Reinforcement Learning
Our automatic and human evaluations show that our framework improves both the persona consistency and dialogue quality of a state-of-the-art social chatbot.
Curriculum-Driven Edubot: A Framework for Developing Language Learning Chatbots Through Synthesizing Conversational Data
Chatbots have become popular in educational settings, revolutionizing how students interact with material and how teachers teach.
ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer
Our parameter-efficient approach, ParaGuide, leverages paraphrase-conditioned diffusion models alongside gradient-based guidance from both off-the-shelf classifiers and strong existing style embedders to transform the style of text while preserving semantic information.
MultiPA: A Multi-task Speech Pronunciation Assessment Model for Open Response Scenarios
Pronunciation assessment models designed for open response scenarios enable users to practice language skills in a manner similar to real-life communication.
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection for Conversational AI
Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness.
Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations
To answer these questions, we propose to evaluate $\textbf{counterfactual simulatability}$ of natural language explanations: whether an explanation can enable humans to precisely infer the model's outputs on diverse counterfactuals of the explained input.
Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler
In this paper, we propose a novel Knowledge-driven Differential Filter Sampler~(KDFS) with Masked Filter Modeling~(MFM) framework for filter pruning, which globally prunes the redundant filters based on the prior knowledge of a pre-trained model in a differential and non-alternative optimization.
Using Textual Interface to Align External Knowledge for End-to-End Task-Oriented Dialogue Systems
We demonstrate our paradigm in practice through MultiWOZ-Remake, including an interactive textual interface built for the MultiWOZ database and a correspondingly re-processed dataset.
Prompt-Based Monte-Carlo Tree Search for Goal-Oriented Dialogue Policy Planning
Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress.
IdEALS: Idiomatic Expressions for Advancement of Language Skills
Although significant progress has been made in developing methods for Grammatical Error Correction (GEC), addressing word choice improvements has been notably lacking and enhancing sentence expressivity by replacing phrases with advanced expressions is an understudied aspect.
Sociocultural Norm Similarities and Differences via Situational Alignment and Explainable Textual Entailment
Embedding Chain-of-Thought prompting in a human-AI collaborative framework, we build a high-quality dataset of 3, 069 social norms aligned with social situations across Chinese and American cultures alongside corresponding free-text explanations.
Controllable Mixed-Initiative Dialogue Generation through Prompting
The standard approach has been fine-tuning pre-trained language models to perform generation conditioned on these intents.
ANetQA: A Large-scale Benchmark for Fine-grained Compositional Reasoning over Untrimmed Videos
A recent benchmark AGQA poses a promising paradigm to generate QA pairs automatically from pre-annotated scene graphs, enabling it to measure diverse reasoning abilities with granular control.
User Adaptive Language Learning Chatbots with a Curriculum
Along with the development of systems for natural language understanding and generation, dialog systems have been widely adopted for language learning and practicing.
PRESTO: A Multilingual Dataset for Parsing Realistic Task-Oriented Dialogs
Research interest in task-oriented dialogs has increased as systems such as Google Assistant, Alexa and Siri have become ubiquitous in everyday life.
FaceChat: An Emotion-Aware Face-to-face Dialogue Framework
While current dialogue systems like ChatGPT have made significant advancements in text-based interactions, they often overlook the potential of other modalities in enhancing the overall user experience.
Prophet: Prompting Large Language Models with Complementary Answer Heuristics for Knowledge-based Visual Question Answering
Knowledge-based visual question answering (VQA) requires external knowledge beyond the image to answer the question.
Ranked #3 on
Visual Question Answering (VQA)
on A-OKVQA
Mixture of Soft Prompts for Controllable Data Generation
Large language models (LLMs) effectively generate fluent text when the target output follows natural language patterns.
Pre-Finetuning for Few-Shot Emotional Speech Recognition
Speech models have long been known to overfit individual speakers for many classification tasks.
Check Your Facts and Try Again: Improving Large Language Models with External Knowledge and Automated Feedback
Large language models (LLMs), such as ChatGPT, are able to generate human-like, fluent responses for many downstream tasks, e. g., task-oriented dialog and question answering.
Stabilized In-Context Learning with Pre-trained Language Models for Few Shot Dialogue State Tracking
Prompt-based methods with large pre-trained language models (PLMs) have shown impressive unaided performance across many NLP tasks.
PLACES: Prompting Language Models for Social Conversation Synthesis
Collecting high quality conversational data can be very expensive for most applications and infeasible for others due to privacy, ethical, or similar concerns.
DIONYSUS: A Pre-trained Model for Low-Resource Dialogue Summarization
In this work, we propose DIONYSUS (dynamic input optimization in pre-training for dialogue summarization), a pre-trained encoder-decoder model for summarizing dialogues in any new domain.
In-context Learning Distillation: Transferring Few-shot Learning Ability of Pre-trained Language Models
We propose to combine in-context learning objectives with language modeling objectives to distill both the ability to read in-context examples and task knowledge to the smaller models.
MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL
Conversational text-to-SQL is designed to translate multi-turn natural language questions into their corresponding SQL queries.
Sources of Noise in Dialogue and How to Deal with Them
Training dialogue systems often entails dealing with noisy training examples and unexpected user inputs.
Focus! Relevant and Sufficient Context Selection for News Image Captioning
In our paper, we first demonstrate that by combining more fine-grained context that captures the key named entities (obtained via an oracle) and the global context that summarizes the news, we can dramatically improve the model's ability to generate accurate news captions.
KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning
In task-oriented dialogs (TOD), reinforcement learning (RL) algorithms train a model to directly optimize response for task-related metrics.
AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies
Existing approaches built separate classifiers to detect nonsense in dialogues.
Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding
Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings.
Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems
Dialog systems are often designed or trained to output human-like responses.
Social Influence Dialogue Systems: A Survey of Datasets and Models For Social Influence Tasks
Dialogue systems capable of social influence such as persuasion, negotiation, and therapy, are essential for extending the use of technology to numerous realistic scenarios.
On the Relation between Sensitivity and Accuracy in In-context Learning
In-context learning (ICL) suffers from oversensitivity to the prompt, making it unreliable in real-world scenarios.
Stateful Memory-Augmented Transformers for Efficient Dialogue Modeling
Transformer encoder-decoder models have achieved great performance in dialogue generation tasks, however, their inability to process long dialogue history often leads to truncation of the context To address this problem, we propose a novel memory-augmented transformer that is compatible with existing pre-trained encoder-decoder models and enables efficient preservation of the dialogue history information.
Using Chatbots to Teach Languages
This paper reports on progress towards building an online language learning tool to provide learners with conversational experience by using dialog systems as conversation practice partners.
GODEL: Large-Scale Pre-Training for Goal-Directed Dialog
We introduce GODEL (Grounded Open Dialogue Language Model), a large pre-trained language model for dialog.
Learning a Better Initialization for Soft Prompts via Meta-Learning
So pre-trained prompt tuning (PPT) is proposed to initialize prompts by leveraging pre-training data.
Just Fine-tune Twice: Selective Differential Privacy for Large Language Models
Utilizing the fact that sensitive information in language data tends to be sparse, Shi et al. (2021) formalized a DP notion extension called Selective Differential Privacy (SDP) to protect only the sensitive tokens defined by a policy function.
A Roadmap for Big Model
With the rapid development of deep learning, training Big Models (BMs) for multiple downstream tasks becomes a popular paradigm.
Fantastic Questions and Where to Find Them: FairytaleQA -- An Authentic Dataset for Narrative Comprehension
Through benchmarking with QG models, we show that the QG model trained on FairytaleQA is capable of asking high-quality and more diverse questions.
Ranked #1 on
Question Generation
on FairytaleQA
Bilaterally Slimmable Transformer for Elastic and Efficient Visual Question Answering
Recent advances in Transformer architectures [1] have brought remarkable improvements to visual question answering (VQA).
Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges
This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog.
FastKASSIM: A Fast Tree Kernel-Based Syntactic Similarity Metric
Syntax is a fundamental component of language, yet few metrics have been employed to capture syntactic similarity or coherence at the utterance- and document-level.
Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue
Complex conversation settings such as persuasion involve communicating changes in attitude or behavior, so users' perspectives need to be addressed, even when not directly related to the topic.
Random Forest Weighted Local Fréchet Regression with Random Objects
Statistical analysis is increasingly confronted with complex data from metric spaces.
Optimal Model Averaging of Support Vector Machines in Diverging Model Spaces
Support vector machine (SVM) is a powerful classification method that has achieved great success in many fields.
Insta-VAX: A Multimodal Benchmark for Anti-Vaccine and Misinformation Posts Detection on Social Media
The dataset and classifiers contribute to monitoring and tracking of vaccine discussions for social scientific and public health efforts in combating the problem of vaccine misinformation.
Improving Conversational Recommendation Systems' Quality with Context-Aware Item Meta Information
The encoder learns to map item metadata to embeddings that can reflect the semantic information in the dialog context.
AllWOZ: Towards Multilingual Task-Oriented Dialog Systems for All
A commonly observed problem of the state-of-the-art natural language technologies, such as Amazon Alexa and Apple Siri, is that their services do not extend to most developing countries' citizens due to language barriers.
Database Search Results Disambiguation for Task-Oriented Dialog Systems
We find that training on our augmented dialog data improves the model's ability to deal with ambiguous scenarios, without sacrificing performance on unmodified turns.
ErAConD : Error Annotated Conversational Dialog Dataset for Grammatical Error Correction
Currently available grammatical error correction (GEC) datasets are compiled using well-formed written text, limiting the applicability of these datasets to other domains such as informal writing and dialog.
DG2: Data Augmentation Through Document Grounded Dialogue Generation
Collecting data for training dialog systems can be extremely expensive due to the involvement of human participants and need for extensive annotation.
Knowledge-Grounded Dialogue Generation with a Unified Knowledge Representation
To address these challenges, we present PLUG, a language model that homogenizes different knowledge sources to a unified knowledge representation for knowledge-grounded dialogue generation tasks.
IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning
Also, we develop a strong IconQA baseline Patch-TRM that applies a pyramid cross-modal Transformer with input diagram embeddings pre-trained on the icon dataset.
Ranked #1 on
Visual Question Answering (VQA)
on IconQA
Clean or Annotate: How to Spend a Limited Data Collection Budget
Crowdsourcing platforms are often used to collect datasets for training machine learning models, despite higher levels of inaccurate labeling compared to expert labeling.
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.
GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation
Practical dialogue systems require robust methods of detecting out-of-scope (OOS) utterances to avoid conversational breakdowns and related failure modes.
Selective Differential Privacy for Language Modeling
Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility.
ROSITA: Enhancing Vision-and-Language Semantic Alignments via Cross- and Intra-modal Knowledge Integration
Nevertheless, most existing VLP approaches have not fully utilized the intrinsic knowledge within the image-text pairs, which limits the effectiveness of the learned alignments and further restricts the performance of their models.
On the Generation of Medical Dialogs for COVID-19
Training complex dialog generation models on small datasets bears high risk of overfitting.
Discovering Dialogue Slots with Weak Supervision
Our model demonstrates state-of-the-art performance in slot tagging without labeled training data on four different dialogue domains.
PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation
However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored.
Evaluation of In-Person Counseling Strategies To Develop Physical Activity Chatbot for Women
To develop intervention chatbots, the first step is to understand natural language conversation strategies in human conversation.
The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity
Humans are increasingly interacting with machines through language, sometimes in contexts where the user may not know they are talking to a machine (like over the phone or a text chatbot).
Dialoging Resonance: How Users Perceive, Reciprocate and React to Chatbot's Self-Disclosure in Conversational Recommendations
Using chatbots to deliver recommendations is increasingly popular.
Towards Emotional Support Dialog Systems
Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats.
SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues
Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly.
Ranked #5 on
Dialog Relation Extraction
on DialogRE
HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations
Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience.
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.
Annotation Inconsistency and Entity Bias in MultiWOZ
In this work, we identify an overlooked issue with dialog state annotation inconsistencies in the dataset, where a slot type is tagged inconsistently across similar dialogs leading to confusion for DST modeling.
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.
LEGOEval: An Open-Source Toolkit for Dialogue System Evaluation via Crowdsourcing
We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk.
Revealing Persona Biases in Dialogue Systems
Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives.
DEUX: An Attribute-Guided Framework for Sociable Recommendation Dialog Systems
It is important for sociable recommendation dialog systems to perform as both on-task content and social content to engage users and gain their favor.
A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting
The most recent researches on domain adaption focus on giving the model a better initialization, rather than optimizing the adaptation process.
MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations
To validate our scheme, we leveraged transfer learning methods to train a multi-label dialog act prediction model and reached an F1 score of 0. 79.
Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems
Existing goal-oriented dialogue datasets focus mainly on identifying slots and values.
UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pre-training
Vision-and-language pre-training has achieved impressive success in learning multimodal representations between vision and language.
Towards Socially Intelligent Agents with Mental State Transition and Human Utility
One of which is to track the agent's mental state transition and teach the agent to make decisions guided by its value like a human.
ChainCQG: Flow-Aware Conversational Question Generation
Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these.
Refine and Imitate: Reducing Repetition and Inconsistency in Dialogue Generation via Reinforcement Learning and Human Demonstration
Despite the recent success of large-scale language models on various downstream NLP tasks, the repetition and inconsistency problems still persist in dialogue response generation.
Sufficient and Disentangled Representation Learning
We provide strong statistical guarantees for the learned representation by establishing an upper bound on the excess error of the objective function and show that it reaches the nonparametric minimax rate under mild conditions.
Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration
Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.
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.
Gunrock 2.0: A User Adaptive Social Conversational System
Gunrock 2. 0 is built on top of Gunrock with an emphasis on user adaptation.
Understanding User Resistance Strategies in Persuasive Conversations
Furthermore, we analyze the relationships between persuasion strategies and persuasion resistance strategies.
Memformer: A Memory-Augmented Transformer for Sequence Modeling
Transformers have reached remarkable success in sequence modeling.
Code to Comment "Translation": Data, Metrics, Baselining & Evaluation
We carefully examine the underlying assumption here: that the task of generating comments sufficiently resembles the task of translating between natural languages, and so similar models and evaluation metrics could be used.
INSPIRED: Toward Sociable Recommendation Dialog Systems
To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs.
ALICE: Active Learning with Contrastive Natural Language Explanations
We propose Active Learning with Contrastive Explanations (ALICE), an expert-in-the-loop training framework that utilizes contrastive natural language explanations to improve data efficiency in learning.
Structured Attention for Unsupervised Dialogue Structure Induction
Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics.
Perception Score, A Learned Metric for Open-ended Text Generation Evaluation
Automatic evaluation for open-ended natural language generation tasks remains a challenge.
SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing
Dialogue state tracker is responsible for inferring user intentions through dialogue history.
Deep Dimension Reduction for Supervised Representation Learning
We propose a deep dimension reduction approach to learning representations with these characteristics.
Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation
Our experiments show that CMADE achieves 89. 2% accuracy in the dialog comparison task.
On the Generation of Medical Dialogues for COVID-19
On these two datasets, we train several dialogue generation models based on Transformer, GPT, and BERT-GPT.
Deep Multimodal Neural Architecture Search
Most existing works focus on a single task and design neural architectures manually, which are highly task-specific and hard to generalize to different tasks.
Ranked #18 on
Visual Question Answering (VQA)
on VQA v2 test-std
Data Annealing for Informal Language Understanding Tasks
We pro-pose a data annealing transfer learning procedure to bridge the performance gap on informal natural language understanding tasks.
A Tailored Pre-Training Model for Task-Oriented Dialog Generation
The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks.
Paraphrase Augmented Task-Oriented Dialog Generation
Neural generative models have achieved promising performance on dialog generation tasks if given a huge data set.
TextGAIL: Generative Adversarial Imitation Learning for Text Generation
Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts.
Weakly-Supervised Multi-Level Attentional Reconstruction Network for Grounding Textual Queries in Videos
The task of temporally grounding textual queries in videos is to localize one video segment that semantically corresponds to the given query.
Matching Text with Deep Mutual Information Estimation
Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network's input and output.
Distributed estimation of principal support vector machines for sufficient dimension reduction
The principal support vector machines method (Li et al., 2011) is a powerful tool for sufficient dimension reduction that replaces original predictors with their low-dimensional linear combinations without loss of information.
End-to-End Trainable Non-Collaborative Dialog System
End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task.
Filling Conversation Ellipsis for Better Social Dialog Understanding
We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances.
Importance-Aware Learning for Neural Headline Editing
We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers.
Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context
Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context.
Ranked #6 on
End-To-End Dialogue Modelling
on MULTIWOZ 2.0
Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks.
Gunrock: A Social Bot for Complex and Engaging Long Conversations
Gunrock is the winner of the 2018 Amazon Alexa Prize, as evaluated by coherence and engagement from both real users and Amazon-selected expert conversationalists.
Abstractive Dialog Summarization with Semantic Scaffolds
The demand for abstractive dialog summary is growing in real-world applications.
Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History
We train FSTs on a set of strategies and tactics used in negotiation dialogs.
MOSS: End-to-End Dialog System Framework with Modular Supervision
To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation.
Dependency Parsing for Spoken Dialog Systems
Dependency parsing of conversational input can play an important role in language understanding for dialog systems by identifying the relationships between entities extracted from user utterances.
Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation
Reinforcement learning (RL) is an effective approach to learn an optimal dialog policy for task-oriented visual dialog systems.
How to Build User Simulators to Train RL-based Dialog Systems
We propose a method of standardizing user simulator building that can be used by the community to compare dialog system quality using the same set of user simulators fairly.
A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog
This study tests the effect of cognitive-emotional expression in an Alexa text-to-speech (TTS) voice on users{'} experience with a social dialog system.
MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations
Previous dialog act schemes, such as SWBD-DAMSL, are designed for human-human conversations, in which conversation partners have perfect language understanding ability.
Multimodal Unified Attention Networks for Vision-and-Language Interactions
Learning an effective attention mechanism for multimodal data is important in many vision-and-language tasks that require a synergic understanding of both the visual and textual contents.
Deep Modular Co-Attention Networks for Visual Question Answering
In this paper, we propose a deep Modular Co-Attention Network (MCAN) that consists of Modular Co-Attention (MCA) layers cascaded in depth.
Ranked #7 on
Question Answering
on SQA3D
Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
Developing intelligent persuasive conversational agents to change people's opinions and actions for social good is the frontier in advancing the ethical development of automated dialogue systems.
Quantifying Intrinsic Uncertainty in Classification via Deep Dirichlet Mixture Networks
With the widespread success of deep neural networks in science and technology, it is becoming increasingly important to quantify the uncertainty of the predictions produced by deep learning.
Domain Adaptive Dialog Generation via Meta Learning
We train a dialog system model using multiple rich-resource single-domain dialog data by applying the model-agnostic meta-learning algorithm to dialog domain.
ActivityNet-QA: A Dataset for Understanding Complex Web Videos via Question Answering
It is both crucial and natural to extend this research direction to the video domain for video question answering (VideoQA).
Ranked #31 on
Video Question Answering
on ActivityNet-QA
Visual Question Answering (VQA)
Zero-Shot Video Question Answer
Multimodal Transformer with Multi-View Visual Representation for Image Captioning
Despite the success of existing studies, current methods only model the co-attention that characterizes the inter-modal interactions while neglecting the self-attention that characterizes the intra-modal interactions.
Single Pixel Reconstruction for One-stage Instance Segmentation
In this paper, we propose a one-stage framework, SPRNet, which performs efficient instance segmentation by introducing a single pixel reconstruction (SPR) branch to off-the-shelf one-stage detectors.
Unsupervised Dialog Structure Learning
The learned dialog structure can shed light on how to analyze human dialogs, and more importantly contribute to the design and evaluation of dialog systems.
Incorporating Structured Commonsense Knowledge in Story Completion
The ability to select an appropriate story ending is the first step towards perfect narrative comprehension.
Structured Content Preservation for Unsupervised Text Style Transfer
Text style transfer aims to modify the style of a sentence while keeping its content unchanged.
A Visual Attention Grounding Neural Model for Multimodal Machine Translation
The model leverages a visual attention grounding mechanism that links the visual semantics with the corresponding textual semantics.
Ranked #12 on
Multimodal Machine Translation
on Multi30K
Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content
With the increasing popularity of smart devices, rumors with multimedia content become more and more common on social networks.
Overlapping Sliced Inverse Regression for Dimension Reduction
The new algorithm, called overlapping sliced inverse regression (OSIR), is able to estimate the effective dimension reduction space and determine the number of effective factors more accurately.
Rethinking Diversified and Discriminative Proposal Generation for Visual Grounding
Visual grounding aims to localize an object in an image referred to by a textual query phrase.
Ranked #9 on
Phrase Grounding
on Flickr30k Entities Test
Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog
We propose a multimodal hierarchical reinforcement learning framework that dynamically integrates vision and language for task-oriented visual dialog.
Hierarchical Reinforcement Learning
reinforcement-learning
+4
Sentiment Adaptive End-to-End Dialog Systems
End-to-end learning framework is useful for building dialog systems for its simplicity in training and efficiency in model updating.
Beyond Bilinear: Generalized Multimodal Factorized High-order Pooling for Visual Question Answering
For fine-grained image and question representations, a `co-attention' mechanism is developed by using a deep neural network architecture to jointly learn the attentions for both the image and the question, which can allow us to reduce the irrelevant features effectively and obtain more discriminative features for image and question representations.
Multi-modal Factorized Bilinear Pooling with Co-Attention Learning for Visual Question Answering
For multi-modal feature fusion, here we develop a Multi-modal Factorized Bilinear (MFB) pooling approach to efficiently and effectively combine multi-modal features, which results in superior performance for VQA compared with other bilinear pooling approaches.
Learning Conversational Systems that Interleave Task and Non-Task Content
These systems work well when users have clear and explicit intentions that are well-aligned to the systems' capabilities.
