Related papers: Natural language understanding for task oriented d…
As a crucial component in task-oriented dialog systems, the Natural Language Generation (NLG) module converts a dialog act represented in a semantic form into a response in natural language. The success of traditional template-based or…
Pretrained language models have served as important backbones for natural language processing. Recently, in-domain pretraining has been shown to benefit various domain-specific downstream tasks. In the biomedical domain, natural language…
Natural Language Understanding (NLU) is a core component of dialog systems. It typically involves two tasks - intent classification (IC) and slot labeling (SL), which are then followed by a dialogue management (DM) component. Such NLU…
Learning intents and slot labels from user utterances is a fundamental step in all spoken language understanding (SLU) and dialog systems. State-of-the-art neural network based methods, after deployment, often suffer from performance…
This work investigates the use of natural language to enable zero-shot model adaptation to new tasks. We use text and metadata from social commenting platforms as a source for a simple pretraining task. We then provide the language model…
Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E)…
This work investigates spoken language understanding (SLU) systems in the scenario when the semantic information is extracted directly from the speech signal by means of a single end-to-end neural network model. Two SLU tasks are…
This paper introduces a natural language understanding (NLU) framework for argumentative dialogue systems in the information-seeking and opinion building domain. The proposed framework consists of two sub-models, namely intent classifier…
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance. Natural language prompting has recently lead to improved zero-shot generalization…
The few-shot natural language understanding (NLU) task has attracted much recent attention. However, prior methods have been evaluated under a disparate set of protocols, which hinders fair comparison and measuring progress of the field. To…
Background: Biomedical entity normalization is critical to biomedical research because the richness of free-text clinical data, such as progress notes, can often be fully leveraged only after translating words and phrases into structured…
Spoken language understanding (SLU) tasks involve mapping from speech audio signals to semantic labels. Given the complexity of such tasks, good performance might be expected to require large labeled datasets, which are difficult to collect…
Automated evaluation of open domain natural language generation (NLG) models remains a challenge and widely used metrics such as BLEU and Perplexity can be misleading in some cases. In our paper, we propose to evaluate natural language…
For natural language understanding (NLU) technology to be maximally useful, both practically and as a scientific object of study, it must be general: it must be able to process language in a way that is not exclusively tailored to any one…
Objective: Few-shot learning (FSL) methods require small numbers of labeled instances for training. As many medical topics have limited annotated textual data in practical settings, FSL-based natural language processing (NLP) methods hold…
Medical consultation dialogues contain critical clinical information, yet their unstructured nature hinders effective utilization in diagnosis and treatment. Traditional methods, relying on rule-based or shallow machine learning techniques,…
We present NLU++, a novel dataset for natural language understanding (NLU) in task-oriented dialogue (ToD) systems, with the aim to provide a much more challenging evaluation environment for dialogue NLU models, up to date with the current…
It is expensive and difficult to obtain the large number of sentence-level intent and token-level slot label annotations required to train neural network (NN)-based Natural Language Understanding (NLU) components of task-oriented dialog…
Using Large Language Models (LLMs) to generate synthetic data for model training has become increasingly popular in recent years. While LLMs are capable of producing realistic training data, the effectiveness of data generation is…
There is growing interest in the automated extraction of relevant information from clinical dialogues. However, it is difficult to collect and construct large annotated resources for clinical dialogue tasks. Recent developments in natural…