Crossing the conversational chasm: A primer on natural language processing for multilingual task-oriented dialogue systems

E Razumovskaia, G Glavas, O Majewska… - Journal of Artificial …, 2022‏ - jair.org
In task-oriented dialogue (ToD), a user holds a conversation with an artificial agent with the
aim of completing a concrete task. Although this technology represents one of the central …

Learn to adapt for generalized zero-shot text classification

Y Zhang, C Yuan, X Wang, Z Bai… - Proceedings of the 60th …, 2022‏ - aclanthology.org
Generalized zero-shot text classification aims to classify textual instances from both
previously seen classes and incrementally emerging unseen classes. Most existing methods …

Cross-lingual dialogue dataset creation via outline-based generation

O Majewska, E Razumovskaia, EM Ponti… - Transactions of the …, 2023‏ - direct.mit.edu
Multilingual task-oriented dialogue (ToD) facilitates access to services and information for
many (communities of) speakers. Nevertheless, its potential is not fully realized, as current …

[PDF][PDF] Crossing the conversational chasm: A primer on multilingual task-oriented dialogue systems

E Razumovskaia, G Glavaš… - arxiv preprint arxiv …, 2021‏ - evgeniiaraz.github.io
Despite the fact that natural language conversations with machines represent one of the
central objectives of AI, and despite the massive increase of research and development …

Short text classification of chinese with label information assisting

Q Xu, J Peng, C Zheng, S Tan, F Yi… - ACM Transactions on …, 2023‏ - dl.acm.org
As a common language form in oral communication, short text is hard to be used in the
applications such as intent understanding, text classification and so on due to its limited …

Method and system for intent classification

C Costello - US Patent 10,832,003, 2020‏ - Google Patents
US10832003B2 - Method and system for intent classification - Google Patents US10832003B2
- Method and system for intent classification - Google Patents Method and system for intent …

BoostingBERT: Integrating multi-class boosting into BERT for NLP tasks

T Huang, Q She, J Zhang - arxiv preprint arxiv:2009.05959, 2020‏ - arxiv.org
As a pre-trained Transformer model, BERT (Bidirectional Encoder Representations from
Transformers) has achieved ground-breaking performance on multiple NLP tasks. On the …

A hybrid neural network RBERT-C based on pre-trained RoBERTa and CNN for user intent classification

Y Liu, H Liu, LP Wong, LK Lee, H Zhang… - Neural Computing for …, 2020‏ - Springer
User intent classification plays a critical role in identifying the interests of users in question-
answering and spoken dialog systems. The question texts of these systems are usually short …

A Hybrid Neural Network BERT‐Cap Based on Pre‐Trained Language Model and Capsule Network for User Intent Classification

H Liu, Y Liu, LP Wong, LK Lee, T Hao - Complexity, 2020‏ - Wiley Online Library
User intent classification is a vital component of a question‐answering system or a task‐
based dialogue system. In order to understand the goals of users' questions or discourses …