Projects on NTU-NLP

GlobalWoZ: Globalizing MultiWoZ to Develop Multilingual Task-Oriented Dialogue Systems

Sun, 15 May 2022 00:00:00 +0800

Multilingual ToD

Straight to the Gradient: Learning to Use Novel Tokens for Neural Text Generation

Wed, 30 Mar 2022 00:00:00 +0000

A novel training objective for text generation

LFPT5: A Unified Framework for Lifelong Few-shot Language Learning Based on Prompt Tuning of T5

Thu, 10 Mar 2022 00:00:00 +0000

a unified framework for LFLL based on prompt tuning of T5

Rethinking Self-Supervision Objectives for Generalizable Coherence Modeling

Thu, 10 Mar 2022 00:00:00 +0000

We show empirically that increasing the density of negative samples improves the basic model, and using a global negative queue further improves and stabilizes the model while training with hard negative samples.

A Unified Speaker Adaptation Approach for ASR

Thu, 09 Sep 2021 00:00:00 +0000

A unified speaker adaptation approach consisting of feature adaptation and model adaptation for ASR.

MulDA: A Multilingual Data Augmentation Framework for Low-Resource Cross-Lingual NER

Wed, 04 Aug 2021 00:00:00 +0000

A data augmentation method for NER.

RST Parsing from Scratch

Sat, 01 May 2021 00:00:00 +0000

A novel top-down end-to-end formulation of document level discourse parsing in the Rhetorical Structure Theory (RST) framework.

UXLA: A Robust Unsupervised Data Augmentation Framework for Zero-Resouce Cross-Lingual NLP

Wed, 28 Apr 2021 00:00:00 +0000

We propose UXLA, a novel data augmentation framework for self-supervised learning in zero-resource transfer learning scenarios.

Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks

Fri, 16 Apr 2021 00:00:00 +0000

Coherence models are typically evaluated only on synthetic tasks, which may not be representative of their performance in downstream applications. To investigate how representative the synthetic tasks are of downstream use cases, we conduct experiments on benchmarking well-known traditional and neural coherence models on synthetic sentence ordering tasks, and contrast this with their performance on three downstream applications: coherence evaluation for MT and summarization, and next utterance prediction in retrieval-based dialog.

DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

Wed, 24 Feb 2021 00:00:00 +0800

Data augmentation for low resource tagging.

Evaluating Pronominal Anaphora in Machine Translation: An Evaluation Measure and a Test-suite

Wed, 30 Oct 2019 00:00:00 +0000

An extensive, targeted dataset that can be used as a test suite for pronoun translation, covering multiple source languages and different pronoun errors drawn from real system translations, for English

A Unified Neural Coherence Model

Mon, 28 Oct 2019 00:00:00 +0000

A unified coherence model that incorporates sentence grammar, inter-sentence coherence relations, and global coherence patterns into a common neural framework.

Hierarchical Pointer Net Parsing

Tue, 24 Sep 2019 00:00:00 +0000

A hierarchical pointer network parsers applied to dependency and sentence-level discourse parsing tasks.

Discourse Processing and Its Applications --- Tutoral at ACL-2019

Mon, 15 Jul 2019 00:00:00 +0800

Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many NLP applications.

Unsupervised Word Translation

Thu, 04 Apr 2019 00:00:00 +0000

Adversarial Autoencoder with Cycle Consistency and Improved Training

Malay-English Neural Machine Translation System.

Fri, 07 Sep 2018 00:00:00 +0000

A demo of malay english Machine translation system.

Discourse Processing and Its Applications in Text Mining --- Tutoral at ICDM-2018

Fri, 07 Sep 2018 00:00:00 +0800

Discourse processing is a suite of Natural Language Processing (NLP) tasks to uncover linguistic structures from texts at several levels, which can support many text mining applications.

Coherence Modeling of Asynchronus Conversations

Sat, 28 Apr 2018 00:00:00 +0000

A neural approach for modeling coherence of asynchronus conversation

A Unified Linear-Time Framework for Sentence-Level Discourse Parsing