Search Results for author: Hwee Tou Ng

Found 79 papers, 38 papers with code

Frustratingly Easy System Combination for Grammatical Error Correction

1 code implementation NAACL 2022 Muhammad Qorib, Seung-Hoon Na, Hwee Tou Ng

In this paper, we formulate system combination for grammatical error correction (GEC) as a simple machine learning task: binary classification.

Binary Classification Grammatical Error Correction

Grammatical Error Correction: Are We There Yet?

no code implementations COLING 2022 Muhammad Reza Qorib, Hwee Tou Ng

There has been much recent progress in natural language processing, and grammatical error correction (GEC) is no exception.

Grammatical Error Correction

Does BERT Know that the IS-A Relation Is Transitive?

1 code implementation ACL 2022 Ruixi Lin, Hwee Tou Ng

The success of a natural language processing (NLP) system on a task does not amount to fully understanding the complexity of the task, typified by many deep learning models.

On the Robustness of Question Rewriting Systems to Questions of Varying Hardness

1 code implementation ACL 2022 Hai Ye, Hwee Tou Ng, Wenjuan Han

In conversational question answering (CQA), the task of question rewriting (QR) in context aims to rewrite a context-dependent question into an equivalent self-contained question that gives the same answer.

Question Rewriting

Grammatical Error Correction with Contrastive Learning in Low Error Density Domains

1 code implementation Findings (EMNLP) 2021 Hannan Cao, Wenmian Yang, Hwee Tou Ng

Although grammatical error correction (GEC) has achieved good performance on texts written by learners of English as a second language, performance on low error density domains where texts are written by English speakers of varying levels of proficiency can still be improved.

Contrastive Learning Grammatical Error Correction

Improved Word Sense Disambiguation with Enhanced Sense Representations

1 code implementation Findings (EMNLP) 2021 Yang song, Xin Cai Ong, Hwee Tou Ng, Qian Lin

Current state-of-the-art supervised word sense disambiguation (WSD) systems (such as GlossBERT and bi-encoder model) yield surprisingly good results by purely leveraging pre-trained language models and short dictionary definitions (or glosses) of the different word senses.

Word Sense Disambiguation

Class-Adaptive Self-Training for Relation Extraction with Incompletely Annotated Training Data

1 code implementation16 Jun 2023 Qingyu Tan, Lu Xu, Lidong Bing, Hwee Tou Ng

We conducted experiments on document-level and biomedical relation extraction datasets, and the results showed that our proposed self-training framework consistently outperforms existing competitive methods on the Re-DocRED and ChemDisgene datasets when the training data are incompletely annotated.

Relation Extraction

Towards Benchmarking and Improving the Temporal Reasoning Capability of Large Language Models

1 code implementation15 Jun 2023 Qingyu Tan, Hwee Tou Ng, Lidong Bing

In this paper, we introduce a comprehensive probing dataset \tempreason to evaluate the temporal reasoning capability of large language models.

Benchmarking Question Answering

Multi-Source Test-Time Adaptation as Dueling Bandits for Extractive Question Answering

1 code implementation11 Jun 2023 Hai Ye, Qizhe Xie, Hwee Tou Ng

In this work, we study multi-source test-time model adaptation from user feedback, where K distinct models are established for adaptation.

Decision Making Extractive Question-Answering +1

Unlocking Temporal Question Answering for Large Language Models Using Code Execution

1 code implementation24 May 2023 Xingxuan Li, Liying Cheng, Qingyu Tan, Hwee Tou Ng, Shafiq Joty, Lidong Bing

Our preliminary experiments show that generating intermediate reasoning steps does not always boost the performance of complex temporal question-answering tasks.

Logical Reasoning Question Answering

Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation

1 code implementation Findings (ACL) 2022 Qingyu Tan, Ruidan He, Lidong Bing, Hwee Tou Ng

Our model consistently outperforms strong baselines and its performance exceeds the previous SOTA by 1. 36 F1 and 1. 46 Ign_F1 score on the DocRED leaderboard.

Document-level Relation Extraction Knowledge Distillation

A Semi-supervised Learning Approach with Two Teachers to Improve Breakdown Identification in Dialogues

1 code implementation22 Feb 2022 Qian Lin, Hwee Tou Ng

We leverage unlabeled data to improve classification in student training where we employ two teachers to refine the labeling of unlabeled data through teacher-student learning in a bootstrapping manner.

Data Augmentation

System Combination for Grammatical Error Correction Based on Integer Programming

1 code implementation RANLP 2021 Ruixi Lin, Hwee Tou Ng

In this paper, we propose a system combination method for grammatical error correction (GEC), based on nonlinear integer programming (IP).

Grammatical Error Correction

Diversity-Driven Combination for Grammatical Error Correction

no code implementations28 Oct 2021 Wenjuan Han, Hwee Tou Ng

However, most existing state-of-the-art GEC approaches are based on similar sequence-to-sequence neural networks, so the gains are limited from combining the outputs of component systems similar to one another.

Grammatical Error Correction

A Hierarchical Entity Graph Convolutional Network for Relation Extraction across Documents

1 code implementation RANLP 2021 Tapas Nayak, Hwee Tou Ng

Distantly supervised datasets for relation extraction mostly focus on sentence-level extraction, and they cover very few relations.

Relation Extraction

A Co-Attentive Cross-Lingual Neural Model for Dialogue Breakdown Detection

1 code implementation COLING 2020 Qian Lin, Souvik Kundu, Hwee Tou Ng

One of the major challenges is that a dialogue system may generate an undesired utterance leading to a dialogue breakdown, which degrades the overall interaction quality.

Language Modelling Word Embeddings

Unsupervised Domain Adaptation of a Pretrained Cross-Lingual Language Model

1 code implementation23 Nov 2020 Juntao Li, Ruidan He, Hai Ye, Hwee Tou Ng, Lidong Bing, Rui Yan

Experimental results show that our proposed method achieves significant performance improvements over the state-of-the-art pretrained cross-lingual language model in the CLCD setting.

Language Modelling Mutual Information Estimation +1

Feature Adaptation of Pre-Trained Language Models across Languages and Domains with Robust Self-Training

2 code implementations EMNLP 2020 Hai Ye, Qingyu Tan, Ruidan He, Juntao Li, Hwee Tou Ng, Lidong Bing

To improve the robustness of self-training, in this paper we present class-aware feature self-distillation (CFd) to learn discriminative features from PrLMs, in which PrLM features are self-distilled into a feature adaptation module and the features from the same class are more tightly clustered.

Text Classification Unsupervised Domain Adaptation

Learning to Identify Follow-Up Questions in Conversational Question Answering

no code implementations ACL 2020 Souvik Kundu, Qian Lin, Hwee Tou Ng

Despite recent progress in conversational question answering, most prior work does not focus on follow-up questions.

Conversational Question Answering

Do Multi-Hop Question Answering Systems Know How to Answer the Single-Hop Sub-Questions?

no code implementations EACL 2021 Yixuan Tang, Hwee Tou Ng, Anthony K. H. Tung

Multi-hop question answering (QA) requires a model to retrieve and integrate information from different parts of a long text to answer a question.

Multi-hop Question Answering Question Answering

Effective Attention Modeling for Neural Relation Extraction

1 code implementation CONLL 2019 Tapas Nayak, Hwee Tou Ng

Relation extraction is the task of determining the relation between two entities in a sentence.

Relation Extraction

Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction

1 code implementation22 Nov 2019 Tapas Nayak, Hwee Tou Ng

A relation tuple consists of two entities and the relation between them, and often such tuples are found in unstructured text.

Joint Entity and Relation Extraction Machine Translation

Improved Word Sense Disambiguation Using Pre-Trained Contextualized Word Representations

1 code implementation IJCNLP 2019 Christian Hadiwinoto, Hwee Tou Ng, Wee Chung Gan

Contextualized word representations are able to give different representations for the same word in different contexts, and they have been shown to be effective in downstream natural language processing tasks, such as question answering, named entity recognition, and sentiment analysis.

named-entity-recognition Named Entity Recognition +5

Learning from the Experience of Doctors: Automated Diagnosis of Appendicitis Based on Clinical Notes

no code implementations WS 2019 Steven Kester Yuwono, Hwee Tou Ng, Kee Yuan Ngiam

The objective of this work is to develop an automated diagnosis system that is able to predict the probability of appendicitis given a free-text emergency department (ED) note and additional structured information (e. g., lab test results).

Feature Engineering

Improving the Robustness of Question Answering Systems to Question Paraphrasing

1 code implementation ACL 2019 Wee Chung Gan, Hwee Tou Ng

Despite the advancement of question answering (QA) systems and rapid improvements on held-out test sets, their generalizability is a topic of concern.

Data Augmentation Question Answering

Cross-Sentence Grammatical Error Correction

1 code implementation ACL 2019 Shamil Chollampatt, Weiqi Wang, Hwee Tou Ng

Automatic grammatical error correction (GEC) research has made remarkable progress in the past decade.

Grammatical Error Correction

A Nil-Aware Answer Extraction Framework for Question Answering

1 code implementation EMNLP 2018 Souvik Kundu, Hwee Tou Ng

However, current approaches suffer from an impractical assumption that every question has a valid answer in the associated passage.

Question Answering Reading Comprehension

Neural Quality Estimation of Grammatical Error Correction

1 code implementation EMNLP 2018 Shamil Chollampatt, Hwee Tou Ng

We also show that a state-of-the-art GEC system can be improved when quality scores are used as features for re-ranking the N-best candidates.

Grammatical Error Correction Machine Translation +1

Adaptive Semi-supervised Learning for Cross-domain Sentiment Classification

1 code implementation EMNLP 2018 Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

We consider the cross-domain sentiment classification problem, where a sentiment classifier is to be learned from a source domain and to be generalized to a target domain.

Classification General Classification +2

A Reassessment of Reference-Based Grammatical Error Correction Metrics

1 code implementation COLING 2018 Shamil Chollampatt, Hwee Tou Ng

Previous studies of the correlation of these metrics with human quality judgments were inconclusive, due to the lack of appropriate significance tests, discrepancies in the methods, and choice of datasets used.

Grammatical Error Correction Machine Translation

Upping the Ante: Towards a Better Benchmark for Chinese-to-English Machine Translation

1 code implementation LREC 2018 Christian Hadiwinoto, Hwee Tou Ng

Our goal in this paper is to propose a benchmark in evaluation setup for Chinese-to-English machine translation, such that the effectiveness of a new proposed MT approach can be directly compared to previous approaches.

Machine Translation Translation

A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction

3 code implementations26 Jan 2018 Shamil Chollampatt, Hwee Tou Ng

We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network.

Grammatical Error Correction Language Modelling +1

A Question-Focused Multi-Factor Attention Network for Question Answering

1 code implementation25 Jan 2018 Souvik Kundu, Hwee Tou Ng

Neural network models recently proposed for question answering (QA) primarily focus on capturing the passage-question relation.

Open-Domain Question Answering Reading Comprehension +1

Connecting the Dots: Towards Human-Level Grammatical Error Correction

no code implementations WS 2017 Shamil Chollampatt, Hwee Tou Ng

We build a grammatical error correction (GEC) system primarily based on the state-of-the-art statistical machine translation (SMT) approach, using task-specific features and tuning, and further enhance it with the modeling power of neural network joint models.

Grammatical Error Correction Language Modelling +2

An Unsupervised Neural Attention Model for Aspect Extraction

3 code implementations ACL 2017 Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier

Unlike topic models which typically assume independently generated words, word embedding models encourage words that appear in similar contexts to be located close to each other in the embedding space.

Aspect Extraction Domain Adaptation +2

A Dependency-Based Neural Reordering Model for Statistical Machine Translation

no code implementations15 Feb 2017 Christian Hadiwinoto, Hwee Tou Ng

In machine translation (MT) that involves translating between two languages with significant differences in word order, determining the correct word order of translated words is a major challenge.

Machine Translation Translation

Automated Anonymization as Spelling Variant Detection

no code implementations WS 2016 Steven Kester Yuwono, Hwee Tou Ng, Kee Yuan Ngiam

Personal health information (PHI) (such as name and identification number) needs to be removed so that patients cannot be identified.

To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation

no code implementations3 Aug 2016 Christian Hadiwinoto, Yang Liu, Hwee Tou Ng

Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order.

Machine Translation Translation

Exploiting N-Best Hypotheses to Improve an SMT Approach to Grammatical Error Correction

no code implementations1 Jun 2016 Duc Tam Hoang, Shamil Chollampatt, Hwee Tou Ng

Grammatical error correction (GEC) is the task of detecting and correcting grammatical errors in texts written by second language learners.

Grammatical Error Correction Machine Translation +1

Neural Network Translation Models for Grammatical Error Correction

2 code implementations1 Jun 2016 Shamil Chollampatt, Kaveh Taghipour, Hwee Tou Ng

Phrase-based statistical machine translation (SMT) systems have previously been used for the task of grammatical error correction (GEC) to achieve state-of-the-art accuracy.

Grammatical Error Correction Machine Translation +1

Improving Statistical Machine Translation for a Resource-Poor Language Using Related Resource-Rich Languages

no code implementations23 Jan 2014 Preslav Ivanov Nakov, Hwee Tou Ng

We propose a novel language-independent approach for improving machine translation for resource-poor languages by exploiting their similarity to resource-rich ones.

Translation Transliteration

Cannot find the paper you are looking for? You can Submit a new open access paper.