The paper describes a system that uses large language model (LLM) technology
to support the automatic learning of new entries in an intelligent agent's
semantic lexicon. The process is bootstrapped by an existing non-toy lexicon
and a natural language generator that converts formal, ontologically-grounded
representations of meaning into natural language sentences. The learning method
involves a sequence of LLM requests and includes an automatic quality control
step. To date, this learning method has been applied to learning multiword
expressions whose meanings are equivalent to those of transitive verbs in the
agent's lexicon. The experiment demonstrates the benefits of a hybrid learning
architecture that integrates knowledge-based methods and resources with both
traditional data analytics and LLMs.

该论文介绍了一种利用大型语言模型技术支持智能代理语义词典中新条目的自动学习的系统。这种学习方法通过现有的非玩具词典和自然语言生成器引导启动，将意义的表达按基本本体建立转换为自然语言句子。此学习方法已应用于学习多词表达式，其含义与智能代理语义词典中的及物动词等效。实验展示了一种融合基于知识的方法、资源、传统数据分析和大型语言模型的混合学习架构的优势。

利用 LLMs 实现内容为中心的认知代理的知识获取自动化

Automating Knowledge Acquisition for Content-Centric Cognitive Agents  Using LLMs

In this paper, we focus on generating training examples for few-shot intents
in the realistic imbalanced scenario. To build connections between existing
many-shot intents and few-shot intents, we consider an intent as a combination
of a domain and an action, and propose a composed variational natural language
generator (CLANG), a transformer-based conditional variational autoencoder.
CLANG utilizes two latent variables to represent the utterances corresponding
to two different independent parts (domain and action) in the intent, and the
latent variables are composed together to generate natural examples.
Additionally, to improve the generator learning, we adopt the contrastive
regularization loss that contrasts the in-class with the out-of-class utterance
generation given the intent. To evaluate the quality of the generated
utterances, experiments are conducted on the generalized few-shot intent
detection task. Empirical results show that our proposed model achieves
state-of-the-art performances on two real-world intent detection datasets.

本文提出了一种组合变分自然语言生成器（CLANG），它是基于变压器的条件变分自编码器，利用两个潜在变量分别表达意图中两个独立部分（领域和操作），并采取对比正则化损失来提高生成器学习，并在广义的少样本意图检测任务上进行了实验证明表明，我们的模型在两个真实世界的意图检测数据集上均达到了最先进的性能。

少样本意图的变分自然语言生成

Composed Variational Natural Language Generation for Few-shot Intents

We present a natural language generator based on the sequence-to-sequence
approach that can be trained to produce natural language strings as well as
deep syntax dependency trees from input dialogue acts, and we use it to
directly compare two-step generation with separate sentence planning and
surface realization stages to a joint, one-step approach. We were able to train
both setups successfully using very little training data. The joint setup
offers better performance, surpassing state-of-the-art with regards to
n-gram-based scores while providing more relevant outputs.

本文提出一种基于序列到序列 (S2S) 方法的自然语言生成器，可以从输入的对话行为生成自然语言字符串和深度语法依存树，并将双步生成和单步生成进行了比较，结果表明单步生成表现更优秀。