Search Results for author:
Found 91 papers, 32 papers with code
Think Before You Speak: Learning to Generate Implicit Knowledge for Response Generation by Self-Talk
We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary.
Dialog Acts for Task Driven Embodied Agents
Embodied agents need to be able to interact in natural language – understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users.
Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.
Policy-Driven Neural Response Generation for Knowledge-Grounded Dialog Systems
Open-domain dialog systems aim to generate relevant, informative and engaging responses.
Semantic Aligned Multi-modal Transformer for Vision-LanguageUnderstanding: A Preliminary Study on Visual QA
Recent vision-language understanding approaches adopt a multi-modal transformer pre-training and finetuning paradigm.
Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations
We introduce Topical-Chat, a knowledge-grounded human-human conversation dataset where the underlying knowledge spans 8 broad topics and conversation partners don't have explicitly defined roles, to help further research in open-domain conversational AI.
Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI
The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge.
"What do others think?": Task-Oriented Conversational Modeling with Subjective Knowledge
We hope this task and dataset can promote further research on TOD and subjective content understanding.
Multimodal Contextualized Plan Prediction for Embodied Task Completion
Task planning is an important component of traditional robotics systems enabling robots to compose fine grained skills to perform more complex tasks.
Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead
Conversational, multi-turn, text-to-SQL (CoSQL) tasks map natural language utterances in a dialogue to SQL queries.
Role of Bias Terms in Dot-Product Attention
Moreover, we argue that the bias term of the value linear transformation has a more prominent role than that of the bias term of the query linear transformation.
Selective In-Context Data Augmentation for Intent Detection using Pointwise V-Information
This work focuses on in-context data augmentation for intent detection.
Ranked #1 on
Intent Detection
on BANKING77 10-shot
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.
DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines
These guidelines provide information about the context they are applicable to and what should be included in the response, allowing the models to generate responses that are more closely aligned with the developer's expectations and intent.
Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning
Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.
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.
N-Best Hypotheses Reranking for Text-To-SQL Systems
Text-to-SQL task maps natural language utterances to structured queries that can be issued to a database.
Dialog Acts for Task-Driven Embodied Agents
Embodied agents need to be able to interact in natural language understanding task descriptions and asking appropriate follow up questions to obtain necessary information to be effective at successfully accomplishing tasks for a wide range of users.
Alexa, Let's Work Together: Introducing the First Alexa Prize TaskBot Challenge on Conversational Task Assistance
Since its inception in 2016, the Alexa Prize program has enabled hundreds of university students to explore and compete to develop conversational agents through the SocialBot Grand Challenge.
A Systematic Evaluation of Response Selection for Open Domain Dialogue
In this work, we curated a dataset where responses from multiple response generators produced for the same dialog context are manually annotated as appropriate (positive) and inappropriate (negative).
Improving Bot Response Contradiction Detection via Utterance Rewriting
Previous work has treated contradiction detection in bot responses as a task similar to natural language inference, e. g., detect the contradiction between a pair of bot utterances.
Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks
Specifically, we show that for open-domain conversations with 10\% of seed data, our approach performs close to the baseline that uses 100% of the data, while for knowledge-grounded conversations, it achieves the same using only 1% of the data, on human ratings of engagingness, fluency, and relevance.
Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs
Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.
Alexa Teacher Model: Pretraining and Distilling Multi-Billion-Parameter Encoders for Natural Language Understanding Systems
We present results from a large-scale experiment on pretraining encoders with non-embedding parameter counts ranging from 700M to 9. 3B, their subsequent distillation into smaller models ranging from 17M-170M parameters, and their application to the Natural Language Understanding (NLU) component of a virtual assistant system.
Cross-Lingual Natural Language Inference
intent-classification
+5
Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
This paper revisits the approach from a matrix approximation perspective, and identifies two issues in the existing layer-wise sampling methods: suboptimal sampling probabilities and estimation biases induced by sampling without replacement.
Understanding How People Rate Their Conversations
In this work, we conduct a study to better understand how people rate their interactions with conversational agents.
On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
Natural language guided embodied task completion is a challenging problem since it requires understanding natural language instructions, aligning them with egocentric visual observations, and choosing appropriate actions to execute in the environment to produce desired changes.
Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
The massive amount of trainable parameters in the pre-trained language models (PLMs) makes them hard to be deployed to multiple downstream tasks.
What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation
Existing model-based metrics for system response evaluation are trained on human annotated data, which is cumbersome to collect.
Towards Textual Out-of-Domain Detection without In-Domain Labels
In many real-world settings, machine learning models need to identify user inputs that are out-of-domain (OOD) so as to avoid performing wrong actions.
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.
Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Incorporating external knowledge sources effectively in conversations is a longstanding problem in open-domain dialogue research.
Analyzing the Limits of Self-Supervision in Handling Bias in Language
We define three broad classes of task descriptions for these tasks: statement, question, and completion, with numerous lexical variants within each class.
Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules.
User Response and Sentiment Prediction for Automatic Dialogue Evaluation
Automatic evaluation is beneficial for open-domain dialog system development.
Think Before You Speak: Explicitly Generating Implicit Commonsense Knowledge for Response Generation
Implicit knowledge, such as common sense, is key to fluid human conversations.
Training Conversational Agents with Generative Conversational Networks
Rich, open-domain textual data available on the web resulted in great advancements for language processing.
Rome was built in 1776: A Case Study on Factual Correctness in Knowledge-Grounded Response Generation
We demonstrate the benefit of our Conv-FEVER dataset by showing that the models trained on this data perform reasonably well to detect factually inconsistent responses with respect to the provided knowledge through evaluation on our human annotated data.
TEACh: Task-driven Embodied Agents that Chat
Robots operating in human spaces must be able to engage in natural language interaction with people, both understanding and executing instructions, and using conversation to resolve ambiguity and recover from mistakes.
Revisiting Layer-wise Sampling in Fast Training for Graph Convolutional Networks
To accelerate the training of graph convolutional networks (GCN), many sampling-based methods have been developed for approximating the embedding aggregation.
"How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets.
Style Control for Schema-Guided Natural Language Generation
Our results show that while high style accuracy and semantic correctness are easier to achieve for more lexically-defined styles with conditional training, stylistic control is also achievable for more semantically complex styles using discriminator-based guided decoding methods.
Towards Zero and Few-shot Knowledge-seeking Turn Detection in Task-orientated Dialogue Systems
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs.
Commonsense-Focused Dialogues for Response Generation: An Empirical Study
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet.
Can I Be of Further Assistance? Using Unstructured Knowledge Access to Improve Task-oriented Conversational Modeling
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs.
Generative Conversational Networks
We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data.
Entity Resolution in Open-domain Conversations
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest.
Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense
Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning.
Incorporating Commonsense Knowledge Graph in Pretrained Models for Social Commonsense Tasks
Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory.
Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over $50\%$ improvement in turn-level action signature prediction accuracy.
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access Track in DSTC9
This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Few Shot Dialogue State Tracking using Meta-learning
Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc.
Interactive Teaching for Conversational AI
Current conversational AI systems aim to understand a set of pre-designed requests and execute related actions, which limits them to evolve naturally and adapt based on human interactions.
Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systems
Our approach includes a novel goal-sampling technique for sampling plausible user goals and a dialog simulation technique that uses heuristic interplay between the user and the system (Alexa), where the user tries to achieve the sampled goal.
Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation
Here we explore, for the first time, whether it is possible to train an NLG for a new larger ontology using existing training sets for the restaurant domain, where each set is based on a different ontology.
DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue
A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains.
Ranked #5 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.1
(using extra training data)
Are Neural Open-Domain Dialog Systems Robust to Speech Recognition Errors in the Dialog History? An Empirical Study
Large end-to-end neural open-domain chatbots are becoming increasingly popular.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
Beyond Domain APIs: Task-oriented Conversational Modeling with Unstructured Knowledge Access
In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
In this paper, we propose using a dialogue policy to plan the content and style of target responses in the form of an action plan, which includes knowledge sentences related to the dialogue context, targeted dialogue acts, topic information, etc.
Schema-Guided Natural Language Generation
We train different state-of-the-art models for neural natural language generation on this dataset and show that in many cases, including rich schema information allows our models to produce higher quality outputs both in terms of semantics and diversity.
From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets.
MA-DST: Multi-Attention Based Scalable Dialog State Tracking
Task oriented dialog agents provide a natural language interface for users to complete their goal.
Just Ask:An Interactive Learning Framework for Vision and Language Navigation
We demonstrate the proposed strategy is substantially more realistic and data-efficient compared to previously proposed pre-exploration techniques.
MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension
Machine Reading Comprehension (MRC) for question answering (QA), which aims to answer a question given the relevant context passages, is an important way to test the ability of intelligence systems to understand human language.
DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks
Recent advances in neural sequence-to-sequence models have led to promising results for several language generation-based tasks, including dialogue response generation, summarization, and machine translation.
Dialog State Tracking: A Neural Reading Comprehension Approach
In contrast to traditional state tracking methods where the dialog state is often predicted as a distribution over a closed set of all the possible slot values within an ontology, our method uses a simple attention-based neural network to point to the slot values within the conversation.
Ranked #19 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
MultiWOZ 2.1: A Consolidated Multi-Domain Dialogue Dataset with State Corrections and State Tracking Baselines
To fix the noisy state annotations, we use crowdsourced workers to re-annotate state and utterances based on the original utterances in the dataset.
Ranked #16 on
Multi-domain Dialogue State Tracking
on MULTIWOZ 2.0
Dialogue State Tracking
Multi-domain Dialogue State Tracking
Robust Zero-Shot Cross-Domain Slot Filling with Example Values
Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains.
Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators
Having explicit feedback on the relevance and interestingness of a system response at each turn can be a useful signal for mitigating such issues and improving system quality by selecting responses from different approaches.
Natural Language Generation at Scale: A Case Study for Open Domain Question Answering
Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
In the second iteration of the competition in 2018, university teams advanced the state of the art by using context in dialog models, leveraging knowledge graphs for language understanding, handling complex utterances, building statistical and hierarchical dialog managers, and leveraging model-driven signals from user responses.
Learning to Navigate the Web
Even though recent approaches improve the success rate on relatively simple environments with the help of human demonstrations to guide the exploration, they still fail in environments where the set of possible instructions can reach millions.
Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems
This limits such systems in two different ways: If there is an update in the task domain, the dialogue system usually needs to be updated or completely re-trained.
Multi-task learning for Joint Language Understanding and Dialogue State Tracking
This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems.
User Modeling for Task Oriented Dialogues
We further develop several variants by utilizing a latent variable model to inject random variations into user responses to promote diversity in simulated user responses and a novel goal regularization mechanism to penalize divergence of user responses from the initial user goal.
Resolving Referring Expressions in Images With Labeled Elements
Images may have elements containing text and a bounding box associated with them, for example, text identified via optical character recognition on a computer screen image, or a natural image with labeled objects.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
An Efficient Approach to Encoding Context for Spoken Language Understanding
In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames.
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.
Scalable Multi-Domain Dialogue State Tracking
We introduce a novel framework for state tracking which is independent of the slot value set, and represent the dialogue state as a distribution over a set of values of interest (candidate set) derived from the dialogue history or knowledge.
Dialogue State Tracking
Multi-domain Dialogue State Tracking
+2
Federated Control with Hierarchical Multi-Agent Deep Reinforcement Learning
We present a framework combining hierarchical and multi-agent deep reinforcement learning approaches to solve coordination problems among a multitude of agents using a semi-decentralized model.
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.
Towards Zero-Shot Frame Semantic Parsing for Domain Scaling
While multi-task training of such models alleviates the need for large in-domain annotated datasets, bootstrapping a semantic parsing model for a new domain using only the semantic frame, such as the back-end API or knowledge graph schema, is still one of the holy grail tasks of language understanding for dialogue systems.
Sequential Dialogue Context Modeling for Spoken Language Understanding
We compare the performance of our proposed architecture with two context models, one that uses just the previous turn context and another that encodes dialogue context in a memory network, but loses the order of utterances in the dialogue history.
Goal-Oriented Dialogue Systems
Spoken Language Understanding
End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager
Natural language understanding and dialogue policy learning are both essential in conversational systems that predict the next system actions in response to a current user utterance.
Knowledge as a Teacher: Knowledge-Guided Structural Attention Networks
Natural language understanding (NLU) is a core component of a spoken dialogue system.
Leveraging Semantic Web Search and Browse Sessions for Multi-Turn Spoken Dialog Systems
Our session-based models outperform the state-of-the-art method for entity extraction task in SDS.
Zero-Shot Learning for Semantic Utterance Classification
We propose a novel zero-shot learning method for semantic utterance classification (SUC).
