Reference-Centric Models for Grounded Collaborative Dialogue
- URL: http://arxiv.org/abs/2109.05042v1
- Date: Fri, 10 Sep 2021 18:03:54 GMT
- Title: Reference-Centric Models for Grounded Collaborative Dialogue
- Authors: Daniel Fried and Justin T. Chiu and Dan Klein
- Abstract summary: We present a grounded neural dialogue model that successfully collaborates with people in a partially-observable reference game.
We focus on a setting where two agents each observe an overlapping part of a world context and need to identify and agree on some object they share.
Our dialogue agent accurately grounds referents from the partner's utterances using a structured reference resolver, conditions on these referents using a recurrent memory, and uses a pragmatic generation procedure to ensure the partner can resolve the references the agent produces.
- Score: 42.48421111626639
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We present a grounded neural dialogue model that successfully collaborates
with people in a partially-observable reference game. We focus on a setting
where two agents each observe an overlapping part of a world context and need
to identify and agree on some object they share. Therefore, the agents should
pool their information and communicate pragmatically to solve the task. Our
dialogue agent accurately grounds referents from the partner's utterances using
a structured reference resolver, conditions on these referents using a
recurrent memory, and uses a pragmatic generation procedure to ensure the
partner can resolve the references the agent produces. We evaluate on the
OneCommon spatial grounding dialogue task (Udagawa and Aizawa 2019), involving
a number of dots arranged on a board with continuously varying positions,
sizes, and shades. Our agent substantially outperforms the previous state of
the art for the task, obtaining a 20% relative improvement in successful task
completion in self-play evaluations and a 50% relative improvement in success
in human evaluations.
Related papers
- Grounding Language in Multi-Perspective Referential Communication [16.421832484760987]
We introduce a task and dataset for referring expression generation and comprehension in multi-agent embodied environments.
We collect a dataset of 2,970 human-written referring expressions, each paired with human comprehension judgments.
We evaluate the performance of automated models as speakers and listeners paired with human partners, finding that model performance in both reference generation and comprehension lags behind that of pairs of human agents.
arXiv Detail & Related papers (2024-10-04T22:42:30Z) - Common Ground Tracking in Multimodal Dialogue [13.763043173931024]
We present a method for automatically identifying the current set of shared beliefs and questions under discussion'' (QUDs) of a group with a shared goal.
We annotate a dataset of multimodal interactions in a shared physical space with speech transcriptions, prosodic features, gestures, actions, and facets of collaboration.
We cascade into a set of formal closure rules derived from situated evidence and belief axioms and update operations.
arXiv Detail & Related papers (2024-03-26T00:25:01Z) - Dialogue Agents 101: A Beginner's Guide to Critical Ingredients for Designing Effective Conversational Systems [29.394466123216258]
This study provides a comprehensive overview of the primary characteristics of a dialogue agent, their corresponding open-domain datasets, and the methods used to benchmark these datasets.
We propose UNIT, a UNified dIalogue dataseT constructed from conversations of existing datasets for different dialogue tasks capturing the nuances for each of them.
arXiv Detail & Related papers (2023-07-14T10:05:47Z) - Don't Copy the Teacher: Data and Model Challenges in Embodied Dialogue [92.01165203498299]
Embodied dialogue instruction following requires an agent to complete a complex sequence of tasks from a natural language exchange.
This paper argues that imitation learning (IL) and related low-level metrics are actually misleading and do not align with the goals of embodied dialogue research.
arXiv Detail & Related papers (2022-10-10T05:51:40Z) - DialogZoo: Large-Scale Dialog-Oriented Task Learning [52.18193690394549]
We aim to build a unified foundation model which can solve massive diverse dialogue tasks.
To achieve this goal, we first collect a large-scale well-labeled dialogue dataset from 73 publicly available datasets.
arXiv Detail & Related papers (2022-05-25T11:17:16Z) - Opponent Modeling in Negotiation Dialogues by Related Data Adaptation [20.505272677769355]
We propose a ranker for identifying priorities from negotiation dialogues.
The model takes in a partial dialogue as input and predicts the priority order of the opponent.
We show the utility of our proposed approach through extensive experiments based on two dialogue datasets.
arXiv Detail & Related papers (2022-04-30T21:11:41Z) - Dual Task Framework for Debiasing Persona-grounded Dialogue Dataset [17.403065663306567]
We introduce a data-centric approach for the task of improving persona-conditioned dialogue agents.
Specifically, we augment relevant personas to improve dialogue dataset/agent, by leveraging the primal-dual structure of the two tasks.
Experiments on Persona-Chat show that our approach outperforms pre-trained LMs by an 11.7 point gain in terms of accuracy.
arXiv Detail & Related papers (2022-02-11T04:08:46Z) - Probing Task-Oriented Dialogue Representation from Language Models [106.02947285212132]
This paper investigates pre-trained language models to find out which model intrinsically carries the most informative representation for task-oriented dialogue tasks.
We fine-tune a feed-forward layer as the classifier probe on top of a fixed pre-trained language model with annotated labels in a supervised way.
arXiv Detail & Related papers (2020-10-26T21:34:39Z) - Is this Dialogue Coherent? Learning from Dialogue Acts and Entities [82.44143808977209]
We create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues annotated with turn coherence ratings.
Our statistical analysis of the corpus indicates how turn coherence perception is affected by patterns of distribution of entities.
We find that models combining both DA and entity information yield the best performances both for response selection and turn coherence rating.
arXiv Detail & Related papers (2020-06-17T21:02:40Z) - Modeling Long Context for Task-Oriented Dialogue State Generation [51.044300192906995]
We propose a multi-task learning model with a simple yet effective utterance tagging technique and a bidirectional language model.
Our approaches attempt to solve the problem that the performance of the baseline significantly drops when the input dialogue context sequence is long.
In our experiments, our proposed model achieves a 7.03% relative improvement over the baseline, establishing a new state-of-the-art joint goal accuracy of 52.04% on the MultiWOZ 2.0 dataset.
arXiv Detail & Related papers (2020-04-29T11:02:25Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.