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.
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.
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets.
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.
Most prior work on task-oriented dialogue systems is restricted to supporting domain APIs.
Moreover, existing dialogue datasets do not explicitly focus on exhibiting commonsense as a facet.
Most prior work on task-oriented dialogue systems are restricted to limited coverage of domain APIs.
We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data.
In recent years, incorporating external knowledge for response generation in open-domain conversation systems has attracted great interest.
Pretrained language models have excelled at many NLP tasks recently; however, their social intelligence is still unsatisfactory.
Towards improving language models' social intelligence, we focus on the Social IQA dataset, a task requiring social and emotional commonsense reasoning.
no code implementations • • Anish Acharya, Suranjit Adhikari, Sanchit Agarwal, Vincent Auvray, Nehal Belgamwar, Arijit Biswas, Shubhra Chandra, Tagyoung Chung, Maryam Fazel-Zarandi, Raefer Gabriel, Shuyang Gao, Rahul Goel, Dilek Hakkani-Tur, Jan Jezabek, Abhay Jha, Jiun-Yu Kao, Prakash Krishnan, Peter Ku, Anuj Goyal, Chien-Wei Lin, Qing Liu, Arindam Mandal, Angeliki Metallinou, Vishal Naik, Yi Pan, Shachi Paul, Vittorio Perera, Abhishek Sethi, Minmin Shen, Nikko Strom, Eddie Wang
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.
This challenge track aims to expand the coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
Dialogue State Tracking (DST) forms a core component of automated chatbot based systems designed for specific goals like hotel, taxi reservation, tourist information, etc.
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.
no code implementations • 16 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.
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.
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)
Large end-to-end neural open-domain chatbots are becoming increasingly popular.
In this paper, we propose to expand coverage of task-oriented dialogue systems by incorporating external unstructured knowledge sources.
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.
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.
In this paper, we propose using machine reading comprehension (RC) in state tracking from two perspectives: model architectures and datasets.
We demonstrate the proposed strategy is substantially more realistic and data-efficient compared to previously proposed pre-exploration techniques.
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.
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.
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
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
Task-oriented dialog systems increasingly rely on deep learning-based slot filling models, usually needing extensive labeled training data for target domains.
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.
Our experiments show the feasibility of learning statistical NLG models for open-domain QA with larger ontologies.
no code implementations • 27 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.
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.
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.
This paper presents a novel approach for multi-task learning of language understanding (LU) and dialogue state tracking (DST) in task-oriented dialogue systems.
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.
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.
In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames.
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.
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.
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.
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.
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.
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.
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 (NLU) is a core component of a spoken dialogue system.
Our session-based models outperform the state-of-the-art method for entity extraction task in SDS.
We propose a novel zero-shot learning method for semantic utterance classification (SUC).