scholarly journals Cross-Domain Slot Filling as Machine Reading Comprehension

2021 ◽  
Author(s):  
Mengshi Yu ◽  
Jian Liu ◽  
Yufeng Chen ◽  
Jinan Xu ◽  
Yujie Zhang
Keyword(s):  
Reading Comprehension ◽  
Large Scale ◽  
Training Data ◽  
Dialogue Systems ◽  
Domain Specific ◽  
Cross Domain ◽  
New Perspective ◽  
Task Oriented ◽  
Slot Filling ◽  
Machine Reading

With task-oriented dialogue systems being widely applied in everyday life, slot filling, the essential component of task-oriented dialogue systems, is required to be quickly adapted to new domains that contain domain-specific slots with few or no training data. Previous methods for slot filling usually adopt sequence labeling framework, which, however, often has limited ability when dealing with the domain-specific slots. In this paper, we take a new perspective on cross-domain slot filling by framing it as a machine reading comprehension (MRC) problem. Our approach firstly transforms slot names into well-designed queries, which contain rich informative prior knowledge and are very helpful for the detection of domain-specific slots. In addition, we utilize the large-scale MRC dataset for pre-training, which further alleviates the data scarcity problem. Experimental results on SNIPS and ATIS datasets show that our approach consistently outperforms the existing state-of-the-art methods by a large margin.

scholarly journals An Iterative Multi-Source Mutual Knowledge Transfer Framework for Machine Reading Comprehension

2020 ◽  
Author(s):  
Xin Liu ◽  
Kai Liu ◽  
Xiang Li ◽  
Jinsong Su ◽  
Yubin Ge ◽  
...  
Keyword(s):  
Reading Comprehension ◽  
Knowledge Transfer ◽  
Training Data ◽  
Target Domain ◽  
Domain Specific ◽  
Mutual Knowledge ◽  
Benchmark Datasets ◽  
Knowledge Distillation ◽  
The Many ◽  
Machine Reading

The lack of sufficient training data in many domains, poses a major challenge to the construction of domain-specific machine reading comprehension (MRC) models with satisfying performance. In this paper, we propose a novel iterative multi-source mutual knowledge transfer framework for MRC. As an extension of the conventional knowledge transfer with one-to-one correspondence, our framework focuses on the many-to-many mutual transfer, which involves synchronous executions of multiple many-to-one transfers in an iterative manner.Specifically, to update a target-domain MRC model, we first consider other domain-specific MRC models as individual teachers, and employ knowledge distillation to train a multi-domain MRC model, which is differentially required to fit the training data and match the outputs of these individual models according to their domain-level similarities to the target domain. After being initialized by the multi-domain MRC model, the target-domain MRC model is fine-tuned to match both its training data and the output of its previous best model simultaneously via knowledge distillation. Compared with previous approaches, our framework can continuously enhance all domain-specific MRC models by enabling each model to iteratively and differentially absorb the domain-shared knowledge from others. Experimental results and in-depth analyses on several benchmark datasets demonstrate the effectiveness of our framework.

scholarly journals UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension

2021 ◽  
Author(s):  
Samreen Ahmed ◽  
shakeel khoja
Keyword(s):  
Reading Comprehension ◽  
Machine Translation ◽  
Large Scale ◽  
Question Answering ◽  
Training Data ◽  
Significant Progress ◽  
Rule Based ◽  
Low Resource ◽  
Machine Reading ◽  
Answer Format

<p>In recent years, low-resource Machine Reading Comprehension (MRC) has made significant progress, with models getting remarkable performance on various language datasets. However, none of these models have been customized for the Urdu language. This work explores the semi-automated creation of the Urdu Question Answering Dataset (UQuAD1.0) by combining machine-translated SQuAD with human-generated samples derived from Wikipedia articles and Urdu RC worksheets from Cambridge O-level books. UQuAD1.0 is a large-scale Urdu dataset intended for extractive machine reading comprehension tasks consisting of 49k question Answers pairs in question, passage, and answer format. In UQuAD1.0, 45000 pairs of QA were generated by machine translation of the original SQuAD1.0 and approximately 4000 pairs via crowdsourcing. In this study, we used two types of MRC models: rule-based baseline and advanced Transformer-based models. However, we have discovered that the latter outperforms the others; thus, we have decided to concentrate solely on Transformer-based architectures. Using XLMRoBERTa and multi-lingual BERT, we acquire an F<sub>1</sub> score of 0.66 and 0.63, respectively.</p>

scholarly journals CrossWOZ: A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset

2020 ◽  
Vol 8 ◽  
pp. 281-295
Author(s):  
Qi Zhu ◽  
Kaili Huang ◽  
Zheng Zhang ◽  
Xiaoyan Zhu ◽  
Minlie Huang
Keyword(s):  
Large Scale ◽  
Dialogue Systems ◽  
Wizard Of Oz ◽  
Cross Domain ◽  
Large Size ◽  
User Simulation ◽  
Dialogue Acts ◽  
Dialogue Modeling ◽  
State Tracking ◽  
Task Oriented

To advance multi-domain (cross-domain) dialogue modeling as well as alleviate the shortage of Chinese task-oriented datasets, we propose CrossWOZ, the first large-scale Chinese Cross-Domain Wizard-of-Oz task-oriented dataset. It contains 6K dialogue sessions and 102K utterances for 5 domains, including hotel, restaurant, attraction, metro, and taxi. Moreover, the corpus contains rich annotation of dialogue states and dialogue acts on both user and system sides. About 60% of the dialogues have cross-domain user goals that favor inter-domain dependency and encourage natural transition across domains in conversation. We also provide a user simulator and several benchmark models for pipelined task-oriented dialogue systems, which will facilitate researchers to compare and evaluate their models on this corpus. The large size and rich annotation of CrossWOZ make it suitable to investigate a variety of tasks in cross-domain dialogue modeling, such as dialogue state tracking, policy learning, user simulation, etc.

scholarly journals UQuAD1.0: Development of an Urdu Question Answering Training Data for Machine Reading Comprehension

2021 ◽  
Author(s):  
Samreen Ahmed ◽  
shakeel khoja
Keyword(s):  
Reading Comprehension ◽  
Machine Translation ◽  
Large Scale ◽  
Question Answering ◽  
Training Data ◽  
Significant Progress ◽  
Rule Based ◽  
Low Resource ◽  
Machine Reading ◽  
Answer Format

<p>In recent years, low-resource Machine Reading Comprehension (MRC) has made significant progress, with models getting remarkable performance on various language datasets. However, none of these models have been customized for the Urdu language. This work explores the semi-automated creation of the Urdu Question Answering Dataset (UQuAD1.0) by combining machine-translated SQuAD with human-generated samples derived from Wikipedia articles and Urdu RC worksheets from Cambridge O-level books. UQuAD1.0 is a large-scale Urdu dataset intended for extractive machine reading comprehension tasks consisting of 49k question Answers pairs in question, passage, and answer format. In UQuAD1.0, 45000 pairs of QA were generated by machine translation of the original SQuAD1.0 and approximately 4000 pairs via crowdsourcing. In this study, we used two types of MRC models: rule-based baseline and advanced Transformer-based models. However, we have discovered that the latter outperforms the others; thus, we have decided to concentrate solely on Transformer-based architectures. Using XLMRoBERTa and multi-lingual BERT, we acquire an F<sub>1</sub> score of 0.66 and 0.63, respectively.</p>

scholarly journals Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset

2020 ◽  
Vol 34 (05) ◽  
pp. 8689-8696
Author(s):  
Abhinav Rastogi ◽  
Xiaoxue Zang ◽  
Srinivas Sunkara ◽  
Raghav Gupta ◽  
Pranav Khaitan
Keyword(s):  
Large Scale ◽  
Training Data ◽  
Conversational Agents ◽  
Dialogue System ◽  
Conversational Interface ◽  
State Tracking ◽  
Public Datasets ◽  
Multiple Domains ◽  
Task Oriented ◽  
Slot Filling

Virtual assistants such as Google Assistant, Alexa and Siri provide a conversational interface to a large number of services and APIs spanning multiple domains. Such systems need to support an ever-increasing number of services with possibly overlapping functionality. Furthermore, some of these services have little to no training data available. Existing public datasets for task-oriented dialogue do not sufficiently capture these challenges since they cover few domains and assume a single static ontology per domain. In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains. Our dataset exceeds the existing task-oriented dialogue corpora in scale, while also highlighting the challenges associated with building large-scale virtual assistants. It provides a challenging testbed for a number of tasks including language understanding, slot filling, dialogue state tracking and response generation. Along the same lines, we present a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots, provided as input, using their natural language descriptions. This allows a single dialogue system to easily support a large number of services and facilitates simple integration of new services without requiring additional training data. Building upon the proposed paradigm, we release a model for dialogue state tracking capable of zero-shot generalization to new APIs, while remaining competitive in the regular setting.

scholarly journals Investigating Prior Knowledge for Challenging Chinese Machine Reading Comprehension

2020 ◽  
Vol 8 ◽  
pp. 141-155
Author(s):  
Kai Sun ◽  
Dian Yu ◽  
Dong Yu ◽  
Claire Cardie
Keyword(s):  
Reading Comprehension ◽  
Prior Knowledge ◽  
Data Augmentation ◽  
Multiple Choice ◽  
Model Performance ◽  
Free Form ◽  
World Knowledge ◽  
Domain Specific ◽  
Significant Performance ◽  
Machine Reading

Machine reading comprehension tasks require a machine reader to answer questions relevant to the given document. In this paper, we present the first free-form multiple-Choice Chinese machine reading Comprehension dataset (C3), containing 13,369 documents (dialogues or more formally written mixed-genre texts) and their associated 19,577 multiple-choice free-form questions collected from Chinese-as-a-second-language examinations. We present a comprehensive analysis of the prior knowledge (i.e., linguistic, domain-specific, and general world knowledge) needed for these real-world problems. We implement rule-based and popular neural methods and find that there is still a significant performance gap between the best performing model (68.5%) and human readers (96.0%), especiallyon problems that require prior knowledge. We further study the effects of distractor plausibility and data augmentation based on translated relevant datasets for English on model performance. We expect C3 to present great challenges to existing systems as answering 86.8% of questions requires both knowledge within and beyond the accompanying document, and we hope that C3 can serve as a platform to study how to leverage various kinds of prior knowledge to better understand a given written or orally oriented text. C3 is available at https://dataset.org/c3/ .

scholarly journals An Evaluation of Chinese Human-Computer Dialogue Technology

2019 ◽  
Vol 1 (2) ◽  
pp. 187-200
Author(s):  
Zhengyu Zhao ◽  
Weinan Zhang ◽  
Wanxiang Che ◽  
Zhigang Chen ◽  
Yibo Zhang
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
Data Sets ◽  
Dialogue Systems ◽  
Online Testing ◽  
User Intent ◽  
Existing Problems ◽  
Intelligent Processing ◽  
Task Oriented ◽  
Important Branch

The human-computer dialogue has recently attracted extensive attention from both academia and industry as an important branch in the field of artificial intelligence (AI). However, there are few studies on the evaluation of large-scale Chinese human-computer dialogue systems. In this paper, we introduce the Second Evaluation of Chinese Human-Computer Dialogue Technology, which focuses on the identification of a user's intents and intelligent processing of intent words. The Evaluation consists of user intent classification (Task 1) and online testing of task-oriented dialogues (Task 2), the data sets of which are provided by iFLYTEK Corporation. The evaluation tasks and data sets are introduced in detail, and meanwhile, the evaluation results and the existing problems in the evaluation are discussed.

scholarly journals Neural Networks Incorporating Unlabeled and Partially-labeled Data for Cross-domain Chinese Word Segmentation

2018 ◽  
Author(s):  
Lujun Zhao ◽  
Qi Zhang ◽  
Peng Wang ◽  
Xiaoyu Liu
Keyword(s):  
Large Scale ◽  
Word Segmentation ◽  
Language Models ◽  
Cross Entropy ◽  
Chinese Word ◽  
Chinese Word Segmentation ◽  
Domain Specific ◽  
Partially Labeled Data ◽  
Cross Domain ◽  
Resource Poor

Most existing Chinese word segmentation (CWS) methods are usually supervised. Hence, large-scale annotated domain-specific datasets are needed for training. In this paper, we seek to address the problem of CWS for the resource-poor domains that lack annotated data. A novel neural network model is proposed to incorporate unlabeled and partially-labeled data. To make use of unlabeled data, we combine a bidirectional LSTM segmentation model with two character-level language models using a gate mechanism. These language models can capture co-occurrence information. To make use of partially-labeled data, we modify the original cross entropy loss function of RNN. Experimental results demonstrate that the method performs well on CWS tasks in a series of domains.

scholarly journals UniMF: A Unified Framework to Incorporate Multimodal Knowledge Bases intoEnd-to-End Task-Oriented Dialogue Systems

2021 ◽  
Author(s):  
Shiquan Yang ◽  
Rui Zhang ◽  
Sarah M. Erfani ◽  
Jey Han Lau
Keyword(s):  
Large Scale ◽  
Knowledge Bases ◽  
Language Models ◽  
Dialogue Systems ◽  
Unified Framework ◽  
Proposed Model ◽  
Multimodal Information ◽  
Task Oriented ◽  
Novel Model ◽  
Single Modality

Knowledge bases (KBs) are usually essential for building practical dialogue systems. Recently we have seen rapidly growing interest in integrating knowledge bases into dialogue systems. However, existing approaches mostly deal with knowledge bases of a single modality, typically textual information. As today's knowledge bases become abundant with multimodal information such as images, audios and videos, the limitation of existing approaches greatly hinders the development of dialogue systems. In this paper, we focus on task-oriented dialogue systems and address this limitation by proposing a novel model that integrates external multimodal KB reasoning with pre-trained language models. We further enhance the model via a novel multi-granularity fusion mechanism to capture multi-grained semantics in the dialogue history. To validate the effectiveness of the proposed model, we collect a new large-scale (14K) dialogue dataset MMDialKB, built upon multimodal KB. Both automatic and human evaluation results on MMDialKB demonstrate the superiority of our proposed framework over strong baselines.

Sign in / Sign up

Export Citation Format

Share Document