Search Results for author: Dilek Hakkani-Tur

Found 83 papers, 27 papers with code

Dialog Acts for Task Driven Embodied Agents

no code implementations SIGDIAL (ACL) 2022 Spandana Gella, Aishwarya Padmakumar, Patrick Lange, Dilek Hakkani-Tur

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.

Natural Language Understanding

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

no code implementations NAACL 2022 Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs.

Multi-Task Learning Response Generation

DialGuide: Aligning Dialogue Model Behavior with Developer Guidelines

no code implementations20 Dec 2022 Prakhar Gupta, Yang Liu, Di Jin, Behnam Hedayatnia, Spandana Gella, Sijia Liu, Patrick Lange, Julia Hirschberg, Dilek Hakkani-Tur

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.

Response Generation

Inducer-tuning: Connecting Prefix-tuning and Adapter-tuning

1 code implementation26 Oct 2022 Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Prefix-tuning, or more generally continuous prompt tuning, has become an essential paradigm of parameter-efficient transfer learning.

Language Modelling Natural Language Understanding +1

Weakly Supervised Data Augmentation Through Prompting for Dialogue Understanding

no code implementations25 Oct 2022 Maximillian Chen, Alexandros Papangelis, Chenyang Tao, Andy Rosenbaum, Seokhwan Kim, Yang Liu, Zhou Yu, Dilek Hakkani-Tur

Dialogue understanding tasks often necessitate abundant annotated data to achieve good performance and that presents challenges in low-resource settings.

Data Augmentation Dialogue Understanding +2

N-Best Hypotheses Reranking for Text-To-SQL Systems

no code implementations19 Oct 2022 Lu Zeng, Sree Hari Krishnan Parthasarathi, Dilek Hakkani-Tur

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

no code implementations26 Sep 2022 Spandana Gella, Aishwarya Padmakumar, Patrick Lange, Dilek Hakkani-Tur

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.

Natural Language Understanding

A Systematic Evaluation of Response Selection for Open Domain Dialogue

no code implementations SIGDIAL (ACL) 2022 Behnam Hedayatnia, Di Jin, Yang Liu, Dilek Hakkani-Tur

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

1 code implementation SIGDIAL (ACL) 2022 Di Jin, Sijia Liu, Yang Liu, Dilek Hakkani-Tur

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.

Natural Language Inference

Knowledge-Grounded Conversational Data Augmentation with Generative Conversational Networks

no code implementations SIGDIAL (ACL) 2022 Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Dilek Hakkani-Tur

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.

Data Augmentation

Enhanced Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

no code implementations15 Jun 2022 Sha Li, Mahdi Namazifar, Di Jin, Mohit Bansal, Heng Ji, Yang Liu, Dilek Hakkani-Tur

Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging.

Multi-Task Learning Response Generation

Understanding How People Rate Their Conversations

no code implementations1 Jun 2022 Alexandros Papangelis, Nicole Chartier, Pankaj Rajan, Julia Hirschberg, Dilek Hakkani-Tur

In this work, we conduct a study to better understand how people rate their interactions with conversational agents.

Spoken Dialogue Systems

Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks

no code implementations1 Jun 2022 Yifan Chen, Tianning Xu, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu

We identify two issues in the existing layer-wise sampling methods: sub-optimal sampling probabilities and the approximation bias induced by sampling without replacement.

On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets

no code implementations insights (ACL) 2022 Hyounghun Kim, Aishwarya Padmakumar, Di Jin, Mohit Bansal, Dilek Hakkani-Tur

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.

Towards Textual Out-of-Domain Detection without In-Domain Labels

no code implementations22 Mar 2022 Di Jin, Shuyang Gao, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

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.

Contrastive Learning intent-classification +4

Multi-Sentence Knowledge Selection in Open-Domain Dialogue

1 code implementation INLG (ACL) 2021 Mihail Eric, Nicole Chartier, Behnam Hedayatnia, Karthik Gopalakrishnan, Pankaj Rajan, Yang Liu, Dilek Hakkani-Tur

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

no code implementations16 Dec 2021 Lisa Bauer, Karthik Gopalakrishnan, Spandana Gella, Yang Liu, Mohit Bansal, Dilek Hakkani-Tur

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

1 code implementation NAACL 2022 Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang

Transformer-based models are not efficient in processing long sequences due to the quadratic space and time complexity of the self-attention modules.

Training Conversational Agents with Generative Conversational Networks

no code implementations15 Oct 2021 Yen-Ting Lin, Alexandros Papangelis, Seokhwan Kim, Dilek Hakkani-Tur

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

1 code implementation11 Oct 2021 Sashank Santhanam, Behnam Hedayatnia, Spandana Gella, Aishwarya Padmakumar, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

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.

Response Generation

TEACh: Task-driven Embodied Agents that Chat

2 code implementations1 Oct 2021 Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava, Patrick Lange, Anjali Narayan-Chen, Spandana Gella, Robinson Piramuthu, Gokhan Tur, Dilek Hakkani-Tur

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.

Dialogue Understanding

Revisiting Layer-wise Sampling in Fast Training for Graph Convolutional Networks

no code implementations29 Sep 2021 Yifan Chen, Tianning Xu, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu

To accelerate the training of graph convolutional networks (GCN), many sampling-based methods have been developed for approximating the embedding aggregation.

Style Control for Schema-Guided Natural Language Generation

no code implementations EMNLP (NLP4ConvAI) 2021 Alicia Y. Tsai, Shereen Oraby, Vittorio Perera, Jiun-Yu Kao, Yuheng Du, Anjali Narayan-Chen, Tagyoung Chung, Dilek Hakkani-Tur

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.

Pretrained Language Models Task-Oriented Dialogue Systems +1

Go Beyond Plain Fine-tuning: Improving Pretrained Models for Social Commonsense

no code implementations12 May 2021 Ting-Yun Chang, Yang Liu, Karthik Gopalakrishnan, Behnam Hedayatnia, Pei Zhou, Dilek Hakkani-Tur

Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning.

Pretrained Language Models

Few Shot Dialogue State Tracking using Meta-learning

1 code implementation EACL 2021 Saket Dingliwal, Bill Gao, Sanchit Agarwal, Chien-Wei Lin, Tagyoung Chung, Dilek Hakkani-Tur

Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc.

Chatbot Dialogue State Tracking +1

Interactive Teaching for Conversational AI

no code implementations2 Dec 2020 Qing Ping, Feiyang Niu, Govind Thattai, Joel Chengottusseriyil, Qiaozi Gao, Aishwarya Reganti, Prashanth Rajagopal, Gokhan Tur, Dilek Hakkani-Tur, Prem Nataraja

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

no code implementations16 Nov 2020 Chien-Wei Lin, Vincent Auvray, Daniel Elkind, Arijit Biswas, Maryam Fazel-Zarandi, Nehal Belgamwar, Shubhra Chandra, Matt Zhao, Angeliki Metallinou, Tagyoung Chung, Charlie Shucheng Zhu, Suranjit Adhikari, Dilek Hakkani-Tur

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.

Goal-Oriented Dialog Natural Language Understanding

Learning from Mistakes: Combining Ontologies via Self-Training for Dialogue Generation

no code implementations SIGDIAL (ACL) 2020 Lena Reed, Vrindavan Harrison, Shereen Oraby, Dilek Hakkani-Tur, Marilyn Walker

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.

Dialogue Generation

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

1 code implementation28 Sep 2020 Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains.

Ranked #4 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)

Domain Adaptation Multi-domain Dialogue State Tracking +1

Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems

no code implementations26 May 2020 Behnam Hedayatnia, Karthik Gopalakrishnan, Seokhwan Kim, Yang Liu, Mihail Eric, Dilek Hakkani-Tur

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.

Response Generation

Schema-Guided Natural Language Generation

1 code implementation INLG (ACL) 2020 Yuheng Du, Shereen Oraby, Vittorio Perera, Minmin Shen, Anjali Narayan-Chen, Tagyoung Chung, Anu Venkatesh, Dilek Hakkani-Tur

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.

dialog state tracking Text Generation

Just Ask:An Interactive Learning Framework for Vision and Language Navigation

no code implementations2 Dec 2019 Ta-Chung Chi, Mihail Eric, Seokhwan Kim, Minmin Shen, Dilek Hakkani-Tur

We demonstrate the proposed strategy is substantially more realistic and data-efficient compared to previously proposed pre-exploration techniques.

Continual Learning Data Augmentation +1

MMM: Multi-stage Multi-task Learning for Multi-choice Reading Comprehension

2 code implementations1 Oct 2019 Di Jin, Shuyang Gao, Jiun-Yu Kao, Tagyoung Chung, Dilek Hakkani-Tur

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.

Logical Reasoning Machine Reading Comprehension +3

DeepCopy: Grounded Response Generation with Hierarchical Pointer Networks

no code implementations WS 2019 Semih Yavuz, Abhinav Rastogi, Guan-Lin Chao, Dilek Hakkani-Tur

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.

Machine Translation Response Generation +2

Dialog State Tracking: A Neural Reading Comprehension Approach

no code implementations WS 2019 Shuyang Gao, Abhishek Sethi, Sanchit Agarwal, Tagyoung Chung, Dilek Hakkani-Tur

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.

dialog state tracking Machine Reading Comprehension +2

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

1 code implementation ACL 2019 Darsh J Shah, Raghav Gupta, Amir A Fayazi, Dilek Hakkani-Tur

Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains.

slot-filling Zero-shot Slot Filling

Towards Coherent and Engaging Spoken Dialog Response Generation Using Automatic Conversation Evaluators

no code implementations WS 2019 Sanghyun Yi, Rahul Goel, Chandra Khatri, Alessandra Cervone, Tagyoung Chung, Behnam Hedayatnia, Anu Venkatesh, Raefer Gabriel, Dilek Hakkani-Tur

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.

Chatbot Open-Domain Dialog +1

Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize

no code implementations27 Dec 2018 Chandra Khatri, Behnam Hedayatnia, Anu Venkatesh, Jeff Nunn, Yi Pan, Qing Liu, Han Song, Anna Gottardi, Sanjeev Kwatra, Sanju Pancholi, Ming Cheng, Qinglang Chen, Lauren Stubel, Karthik Gopalakrishnan, Kate Bland, Raefer Gabriel, Arindam Mandal, Dilek Hakkani-Tur, Gene Hwang, Nate Michel, Eric King, Rohit Prasad

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.

Knowledge Graphs Management +4

Learning to Navigate the Web

no code implementations ICLR 2019 Izzeddin Gur, Ulrich Rueckert, Aleksandra Faust, Dilek Hakkani-Tur

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.

Instruction Following Meta-Learning +3

Flexible and Scalable State Tracking Framework for Goal-Oriented Dialogue Systems

no code implementations30 Nov 2018 Rahul Goel, Shachi Paul, Tagyoung Chung, Jeremie Lecomte, Arindam Mandal, Dilek Hakkani-Tur

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.

Dialogue State Tracking Goal-Oriented Dialogue Systems +1

Multi-task learning for Joint Language Understanding and Dialogue State Tracking

no code implementations WS 2018 Abhinav Rastogi, Raghav Gupta, Dilek Hakkani-Tur

This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems.

Dialogue State Tracking Multi-Task Learning +1

User Modeling for Task Oriented Dialogues

no code implementations11 Nov 2018 Izzeddin Gur, Dilek Hakkani-Tur, Gokhan Tur, Pararth Shah

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.

Dialogue State Tracking Task-Oriented Dialogue Systems

Resolving Referring Expressions in Images With Labeled Elements

no code implementations24 Oct 2018 Nevan Wichers, Dilek Hakkani-Tur, Jindong Chen

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 Referring Expression

An Efficient Approach to Encoding Context for Spoken Language Understanding

no code implementations1 Jul 2018 Raghav Gupta, Abhinav Rastogi, Dilek Hakkani-Tur

In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames.

Spoken Language Understanding Task-Oriented Dialogue Systems

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

1 code implementation NAACL 2018 Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, Larry Heck

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.

Dialogue State Tracking Imitation Learning +3

Scalable Multi-Domain Dialogue State Tracking

1 code implementation29 Dec 2017 Abhinav Rastogi, Dilek Hakkani-Tur, Larry Heck

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

1 code implementation22 Dec 2017 Saurabh Kumar, Pararth Shah, Dilek Hakkani-Tur, Larry Heck

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.

Efficient Exploration reinforcement-learning +2

End-to-End Optimization of Task-Oriented Dialogue Model with Deep Reinforcement Learning

no code implementations29 Nov 2017 Bing Liu, Gokhan Tur, Dilek Hakkani-Tur, Pararth Shah, Larry Heck

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.

reinforcement-learning reinforcement Learning

Towards Zero-Shot Frame Semantic Parsing for Domain Scaling

1 code implementation7 Jul 2017 Ankur Bapna, Gokhan Tur, Dilek Hakkani-Tur, Larry Heck

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.

Semantic Parsing slot-filling +1

Sequential Dialogue Context Modeling for Spoken Language Understanding

1 code implementation WS 2017 Ankur Bapna, Gokhan Tur, Dilek Hakkani-Tur, Larry Heck

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

1 code implementation3 Dec 2016 Xuesong Yang, Yun-Nung Chen, Dilek Hakkani-Tur, Paul Crook, Xiujun Li, Jianfeng Gao, Li Deng

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.

Natural Language Understanding

Cannot find the paper you are looking for? You can Submit a new open access paper.