6,910 research outputs found
Simple Data Augmentation for Multilingual NLU in Task Oriented Dialogue Systems
No full textData augmentation has shown potential in alleviating data scarcity for Natural Language Understanding (e.g. slot filling and intent classification) in task-oriented dialogue systems. As prior work has been mostly experimented on English datasets, we focus on five different languages, and consider a setting where limited data are available. We investigate the effectiveness of non-gradient based augmentation methods, involving simple text span substitutions and syntactic manipulations. Our experiments show that (i) augmentation is effective in all cases, particularly for slot filling; and (ii) it is beneficial for a joint intent-slot model based on multilingual BERT, both for limited data settings and when full training data is used
From General to Specific: Leveraging Named Entity Recognition for Slot Filling in Conversational Language Understanding
No full textSlot filling techniques are often adopted in language understanding components for task-oriented dialogue systems. In recent approaches, neural models for slot filling are trained on domain-specific datasets, making it difficult porting to similar domains when few or no training data are available. In this paper we use multi-task learning to leverage general knowledge of a task, namely Named Entity Recognition (NER), to improve slot filling performance on a semantically similar domain-specific task. Our experiments show that, for some datasets, transfer learning from NER can achieve competitive performance compared with the state-of-the-art and can also help slot filling in low resource scenarios.Molti sistemi di dialogo taskoriented utilizzano tecniche di slot-filling per la comprensione degli enunciati. Gli approcci piú recenti si basano su modelli neurali addestrati su dataset specializzati per un certo dominio, rendendo difficile la portabilitá su dominii simili, quando pochi o nessun dato di addestramento é disponibile. In questo contributo usiamo multitask learning per sfruttare la conoscenza generale proveniente da un task, precisamente Named Entity Recognition (NER), per migliorare le prestazioni di slot filling su dominii specifici e semanticamente simili. I nostri esperimenti mostrano che transfer learning da NER aiuta lo slot filling in dominii con poche risorse e raggiunge risultati competitivi con lo stato dell’arte
Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey
No full textIn recent years, fostered by deep learning technologies and by the high demand for conversational AI, various approaches have been proposed that address the capacity to elicit and understand user’s needs in task-oriented dialogue systems. We focus on two core tasks, slot filling (SF) and intent classification (IC), and survey how neural based models have rapidly evolved to address natural language understanding in dialogue systems. We introduce three neural architectures: independent models, which model SF and IC separately, joint models, which exploit the mutual benefit of the two tasks simultaneously, and transfer learning models, that scale the model to new domains. We discuss the current state of the research in SF and IC, and highlight challenges that still require attention
How Far Can We Go with Data Selection? A Case Study on Semantic Sequence Tagging Tasks
No full textAlthough several works have addressed the role of data selection to improve transfer learning for various NLP tasks, there is no consensus about its real benefits and, more generally, there is a lack of shared practices on how it can be best applied. We propose a systematic approach aimed at evaluating data selection in scenarios of increasing complexity. Specifically, we compare the case in which source and target tasks are the same while source and target domains are different, against the more
challenging scenario where both tasks and domains are different. We run a number of experiments on semantic sequence tagging tasks, which are relatively less investigated in data selection, and conclude that data selection has more benefit on the scenario when the tasks are the same, while in case of different (although related) tasks from distant domains, a combination of data selection and multi-task learning is ineffective for most cases
Exploring Named Entity Recognition As an Auxiliary Task for Slot Filling in Conversational Language Understanding
No full textSlot filling is a crucial task in the Natural Language Understanding (NLU) component of a dialogue system. Most approaches for this task rely solely on the domain-specific datasets for training. We propose a joint model of slot filling and Named Entity Recognition (NER) in a multi-task learning (MTL) setup. Our experiments on three slot filling datasets show that using NER as an auxiliary task improves slot filling performance and achieve competitive performance compared with state-of-the art. In particular, NER is effective when supervised at the lower layer of the model. For low-resource scenarios, we found that MTL is
effective for one dataset
Simple is Better! Lightweight Data Augmentation for Low Resource Slot Filling and Intent Classification
No full textNeural-based models have achieved outstanding performance on slot filling and intent classification, when fairly large in-domain training data are available. However, as new domains are frequently added, creating sizeable data is expensive. We show that lightweight augmentation, a set of augmentation methods involving word span and sentence level operations, alleviates data scarcity problems. Our experiments on limited data settings show that lightweight augmentation yields significant performance improvement on slot filling on the ATIS and SNIPS datasets, and achieves competitive performance with respect to more
complex, state-of-the-art, augmentation approaches. Furthermore, lightweight augmentation is also beneficial when combined with
pre-trained LM-based models, as it improves BERT-based joint intent and slot filling models
Leveraging Non-Conversational Tasks for Low Resource Slot Filling: Does it help?
No full textSlot filling is a core operation for utterance understanding in task-oriented dialogue systems. Slots are typically domain-specific, and adding new domains to a dialogue system involves data and time-intensive processes. A popular technique to address the problem is transfer learning, where it is assumed the availability of a large slot filling dataset for the
source domain, to be used to help slot filling on the target domain, with fewer data. In this work, instead, we propose to leverage source tasks based on semantically related
non-conversational resources (e.g., semantic sequence tagging datasets), as they are both cheaper to obtain and reusable to several slot filling domains. We show that using auxiliary
non-conversational tasks in a multi-task learning setup consistently improves low resource slot filling performance
Investigating Continued pretraining for Zero-Shot Cross-Lingual Spoken Language Understanding
No full textSpoken Language Understanding (SLU) in task-oriented dialogue systems involves both intent classification (IC) and slot filling (SF) tasks. The de facto method for zero-shot cross-lingual SLU consists of fine-tuning a pretrained multilingual model on English labeled data before evaluating the model on unseen languages. However, recent studies show that adding a second pretraining stage (continued pretraining) can improve performance in certain settings. This paper investigates the effectiveness of continued pretraining on unlabeled spoken language data for zero-shot cross-lingual SLU. We demonstrate that this relatively simple approach benefits either SF and IC task across 8 target languages, especially the ones written in Latin script. We also find that discrepancy between languages used during pretraining and fine-tuning may introduce training instability, which can be alleviated through code-switching
Samuel Dorris Dickinson papers
No full textThe Samuel Dorris Dickinson papers contain the professional and personal records of archaeologist, journalist, and author Samuel Dorris Dickinson
Portrait of author David Foster at the National Library of Australia, Canberra, 8 June 2011 /
No full textTitle from acquisitions documentation.; Part of the collection: Portraits of author David Foster at the National Library of Australia, Canberra, 8 June 2011.; Acquired in digital format; access copy available online.; Mode of access: Online.; Photographed by a staff member of the National Library of Australia
- …
