Conversational Neuro-Symbolic Commonsense Reasoning

• URL: http://arxiv.org/abs/2006.10022v3
• Date: Tue, 2 Feb 2021 07:37:41 GMT
• Title: Conversational Neuro-Symbolic Commonsense Reasoning
• Authors: Forough Arabshahi, Jennifer Lee, Mikayla Gawarecki, Kathryn Mazaitis, Amos Azaria, Tom Mitchell
• Abstract summary: We present a neuro-symbolic theorem prover that extracts multi-hop reasoning chains. We also present an interactive conversational framework built on our neuro-symbolic system.
• Score: 10.894217510063086
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In order for conversational AI systems to hold more natural and broad-ranging conversations, they will require much more commonsense, including the ability to identify unstated presumptions of their conversational partners. For example, in the command "If it snows at night then wake me up early because I don't want to be late for work" the speaker relies on commonsense reasoning of the listener to infer the implicit presumption that they wish to be woken only if it snows enough to cause traffic slowdowns. We consider here the problem of understanding such imprecisely stated natural language commands given in the form of "if-(state), then-(action), because-(goal)" statements. More precisely, we consider the problem of identifying the unstated presumptions of the speaker that allow the requested action to achieve the desired goal from the given state (perhaps elaborated by making the implicit presumptions explicit). We release a benchmark data set for this task, collected from humans and annotated with commonsense presumptions. We present a neuro-symbolic theorem prover that extracts multi-hop reasoning chains, and apply it to this problem. Furthermore, to accommodate the reality that current AI commonsense systems lack full coverage, we also present an interactive conversational framework built on our neuro-symbolic system, that conversationally evokes commonsense knowledge from humans to complete its reasoning chains.

Related papers

• Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic Systems [67.01132165581667]
  We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components. We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
  arXiv  Detail & Related papers  (2023-11-13T21:20:17Z)
• Expanding the Set of Pragmatic Considerations in Conversational AI [0.26206189324400636]
  We discuss several pragmatic limitations of current conversational AI systems. We label our complaints as "Turing Test Triggers" (TTTs) We develop a taxonomy of pragmatic considerations intended to identify what pragmatic competencies a conversational AI system requires.
  arXiv  Detail & Related papers  (2023-10-27T19:21:50Z)
• Commonsense Reasoning for Conversational AI: A Survey of the State of the Art [0.76146285961466]
  The paper lists relevant training datasets and describes the primary approaches to include commonsense in conversational AI. The paper presents preliminary observations of the limited commonsense capabilities of two state-of-the-art open dialogue models, BlenderBot3 and LaMDA.
  arXiv  Detail & Related papers  (2023-02-15T19:55:57Z)
• RHO ($\rho$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding [57.46495388734495]
  This paper presents RHO ($rho$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG) We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism.
  arXiv  Detail & Related papers  (2022-12-03T10:36:34Z)
• NELLIE: A Neuro-Symbolic Inference Engine for Grounded, Compositional, and Explainable Reasoning [59.16962123636579]
  This paper proposes a new take on Prolog-based inference engines. We replace handcrafted rules with a combination of neural language modeling, guided generation, and semi dense retrieval. Our implementation, NELLIE, is the first system to demonstrate fully interpretable, end-to-end grounded QA.
  arXiv  Detail & Related papers  (2022-09-16T00:54:44Z)
• Is Neuro-Symbolic AI Meeting its Promise in Natural Language Processing? A Structured Review [2.064612766965483]
  Advocates for Neuro-Symbolic AI (NeSy) assert that combining deep learning with symbolic reasoning will lead to stronger AI. We conduct a structured review of studies implementing NeSy for NLP, challenges and future directions. We aim to answer the question of whether NeSy is indeed meeting its promises: reasoning, out-of-distribution generalization, interpretability, learning and reasoning from small data, and transferability to new domains.
  arXiv  Detail & Related papers  (2022-02-24T17:13:33Z)
• Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules [38.15523098189754]
  We propose a zero-shot commonsense reasoning system for conversational agents. Our reasoner uncovers unstated presumptions satisfying a general template of if-(state), then-(action), because-(goal) We evaluate the model with a user study with human users that achieves a 35% higher success rate compared to SOTA.
  arXiv  Detail & Related papers  (2021-09-17T13:40:07Z)
• Temporal Reasoning on Implicit Events from Distant Supervision [91.20159064951487]
  We propose a novel temporal reasoning dataset that evaluates the degree to which systems understand implicit events. We find that state-of-the-art models struggle when predicting temporal relationships between implicit and explicit events. We propose a neuro-symbolic temporal reasoning model, SYMTIME, which exploits distant supervision signals from large-scale text and uses temporal rules to infer end times.
  arXiv  Detail & Related papers  (2020-10-24T03:12:27Z)
• Towards Data Distillation for End-to-end Spoken Conversational Question Answering [65.124088336738]
  We propose a new Spoken Conversational Question Answering task (SCQA) SCQA aims at enabling QA systems to model complex dialogues flow given the speech utterances and text corpora. Our main objective is to build a QA system to deal with conversational questions both in spoken and text forms.
  arXiv  Detail & Related papers  (2020-10-18T05:53:39Z)
• "I'd rather just go to bed": Understanding Indirect Answers [61.234722570671686]
  We revisit a pragmatic inference problem in dialog: understanding indirect responses to questions. We create and release the first large-scale English language corpus 'Circa' with 34,268 (polar question, indirect answer) pairs. We present BERT-based neural models to predict such categories for a question-answer pair.
  arXiv  Detail & Related papers  (2020-10-07T14:41:40Z)
• Teaching Machines to Converse [24.64148203917298]
  This dissertation attempts to tackle challenges presented by neural network models in open-domain dialogue generation systems. We develop interactive question-answering dialogue systems by giving the agent the ability to ask questions and training a conversation agent through interactions with humans in an online fashion.
  arXiv  Detail & Related papers  (2020-01-31T08:28:07Z)

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.