Commonsense Reasoning for Conversational AI: A Survey of the State of
the Art
- URL: http://arxiv.org/abs/2302.07926v1
- Date: Wed, 15 Feb 2023 19:55:57 GMT
- Title: Commonsense Reasoning for Conversational AI: A Survey of the State of
the Art
- Authors: Christopher Richardson and Larry Heck
- Abstract summary: 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.
- Score: 0.76146285961466
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large, transformer-based pretrained language models like BERT, GPT, and T5
have demonstrated a deep understanding of contextual semantics and language
syntax. Their success has enabled significant advances in conversational AI,
including the development of open-dialogue systems capable of coherent, salient
conversations which can answer questions, chat casually, and complete tasks.
However, state-of-the-art models still struggle with tasks that involve higher
levels of reasoning - including commonsense reasoning that humans find trivial.
This paper presents a survey of recent conversational AI research focused on
commonsense reasoning. The paper lists relevant training datasets and describes
the primary approaches to include commonsense in conversational AI. The paper
also discusses benchmarks used for evaluating commonsense in conversational AI
problems. Finally, the paper presents preliminary observations of the limited
commonsense capabilities of two state-of-the-art open dialogue models,
BlenderBot3 and LaMDA, and its negative effect on natural interactions. These
observations further motivate research on commonsense reasoning in
conversational AI.
Related papers
- 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) - DiPlomat: A Dialogue Dataset for Situated Pragmatic Reasoning [89.92601337474954]
Pragmatic reasoning plays a pivotal role in deciphering implicit meanings that frequently arise in real-life conversations.
We introduce a novel challenge, DiPlomat, aiming at benchmarking machines' capabilities on pragmatic reasoning and situated conversational understanding.
arXiv Detail & Related papers (2023-06-15T10:41:23Z) - Discourse over Discourse: The Need for an Expanded Pragmatic Focus in
Conversational AI [0.5884031187931463]
We discuss several challenges in both summarization of conversations and other conversational AI applications.
We illustrate the importance of pragmatics with so-called star sentences.
Because the baseline for quality of AI is indistinguishability from human behavior, we label our complaints as "Turing Test Triggers"
arXiv Detail & Related papers (2023-04-27T21:51:42Z) - Question-Interlocutor Scope Realized Graph Modeling over Key Utterances
for Dialogue Reading Comprehension [61.55950233402972]
We propose a new key utterances extracting method for dialogue reading comprehension.
It performs prediction on the unit formed by several contiguous utterances, which can realize more answer-contained utterances.
As a graph constructed on the text of utterances, we then propose Question-Interlocutor Scope Realized Graph (QuISG) modeling.
arXiv Detail & Related papers (2022-10-26T04:00:42Z) - State-of-the-art in Open-domain Conversational AI: A Survey [1.6507910904669727]
We survey SoTA open-domain conversational AI models with the purpose of presenting the prevailing challenges that still exist to spur future research.
We provide statistics on the gender of conversational AI in order to guide the ethics discussion surrounding the issue.
arXiv Detail & Related papers (2022-05-02T15:08:18Z) - Advances in Multi-turn Dialogue Comprehension: A Survey [51.215629336320305]
Training machines to understand natural language and interact with humans is an elusive and essential task of artificial intelligence.
This paper reviews the previous methods from the technical perspective of dialogue modeling for the dialogue comprehension task.
In addition, we categorize dialogue-related pre-training techniques which are employed to enhance PrLMs in dialogue scenarios.
arXiv Detail & Related papers (2021-10-11T03:52:37Z) - Retrieval Augmentation Reduces Hallucination in Conversation [49.35235945543833]
We explore the use of neural-retrieval-in-the-loop architectures for knowledge-grounded dialogue.
We show that our best models obtain state-of-the-art performance on two knowledge-grounded conversational tasks.
arXiv Detail & Related papers (2021-04-15T16:24:43Z) - Advances in Multi-turn Dialogue Comprehension: A Survey [51.215629336320305]
We review the previous methods from the perspective of dialogue modeling.
We discuss three typical patterns of dialogue modeling that are widely-used in dialogue comprehension tasks.
arXiv Detail & Related papers (2021-03-04T15:50:17Z) - Contextual Dialogue Act Classification for Open-Domain Conversational
Agents [10.576497782941697]
Classifying the general intent of the user utterance in a conversation, also known as Dialogue Act (DA), is a key step in Natural Language Understanding (NLU) for conversational agents.
We propose CDAC (Contextual Dialogue Act), a simple yet effective deep learning approach for contextual dialogue act classification.
We use transfer learning to adapt models trained on human-human conversations to predict dialogue acts in human-machine dialogues.
arXiv Detail & Related papers (2020-05-28T06:48:10Z) - You Impress Me: Dialogue Generation via Mutual Persona Perception [62.89449096369027]
The research in cognitive science suggests that understanding is an essential signal for a high-quality chit-chat conversation.
Motivated by this, we propose P2 Bot, a transmitter-receiver based framework with the aim of explicitly modeling understanding.
arXiv Detail & Related papers (2020-04-11T12:51:07Z)
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.