Search Results for author:
Found 11 papers, 8 papers with code
A Systematic Study of Performance Disparities in Multilingual Task-Oriented Dialogue Systems
Achieving robust language technologies that can perform well across the world's many languages is a central goal of multilingual NLP.
Multi3WOZ: A Multilingual, Multi-Domain, Multi-Parallel Dataset for Training and Evaluating Culturally Adapted Task-Oriented Dialog Systems
Creating high-quality annotated data for task-oriented dialog (ToD) is known to be notoriously difficult, and the challenges are amplified when the goal is to create equitable, culturally adapted, and large-scale ToD datasets for multiple languages.
PanGu-Coder: Program Synthesis with Function-Level Language Modeling
We present PanGu-Coder, a pretrained decoder-only language model adopting the PanGu-Alpha architecture for text-to-code generation, i. e. the synthesis of programming language solutions given a natural language problem description.
CrossAligner & Co: Zero-Shot Transfer Methods for Task-Oriented Cross-lingual Natural Language Understanding
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language.
Natural Language Understanding
Zero-Shot Cross-Lingual Transfer
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
For small Natural Language Inference (NLI) datasets, language modelling is typically followed by pretraining on a large (labelled) NLI dataset before fine-tuning with each NLI subtask.
XeroAlign: Zero-Shot Cross-lingual Transformer Alignment
The introduction of pretrained cross-lingual language models brought decisive improvements to multilingual NLP tasks.
Conversation Graph: Data Augmentation, Training and Evaluation for Non-Deterministic Dialogue Management
We propose the Conversation Graph (ConvGraph), a graph-based representation of dialogues that can be exploited for data augmentation, multi-reference training and evaluation of non-deterministic agents.
A Comparison of Techniques for Sentiment Classification of Film Reviews
We undertake the task of comparing lexicon-based sentiment classification of film reviews with machine learning approaches.
A Pragmatic Guide to Geoparsing Evaluation
Empirical methods in geoparsing have thus far lacked a standard evaluation framework describing the task, metrics and data used to compare state-of-the-art systems.
Which Melbourne? Augmenting Geocoding with Maps
The purpose of text geolocation is to associate geographic information contained in a document with a set (or sets) of coordinates, either implicitly by using linguistic features and/or explicitly by using geographic metadata combined with heuristics.
Vancouver Welcomes You! Minimalist Location Metonymy Resolution
Named entities are frequently used in a metonymic manner.
