Lan Du


pdf bib
Re-weighting Tokens: A Simple and Effective Active Learning Strategy for Named Entity Recognition
Haocheng Luo | Wei Tan | Ngoc Nguyen | Lan Du
Findings of the Association for Computational Linguistics: EMNLP 2023

Active learning, a widely adopted technique for enhancing machine learning models in text and image classification tasks with limited annotation resources, has received relatively little attention in the domain of Named Entity Recognition (NER). The challenge of data imbalance in NER has hindered the effectiveness of active learning, as sequence labellers lack sufficient learning signals. To address these challenges, this paper presents a novel re-weighting-based active learning strategy that assigns dynamic smoothing weights to individual tokens. This adaptable strategy is compatible with various token-level acquisition functions and contributes to the development of robust active learners. Experimental results on multiple corpora demonstrate the substantial performance improvement achieved by incorporating our re-weighting strategy into existing acquisition functions, validating its practical efficacy. We will release our implementation upon the publication of this paper.


pdf bib
Hardness-guided domain adaptation to recognise biomedical named entities under low-resource scenarios
Ngoc Dang Nguyen | Lan Du | Wray Buntine | Changyou Chen | Richard Beare
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Domain adaptation is an effective solution to data scarcity in low-resource scenarios. However, when applied to token-level tasks such as bioNER, domain adaptation methods often suffer from the challenging linguistic characteristics that clinical narratives possess, which leads to unsatsifactory performance. In this paper, we present a simple yet effective hardness-guided domain adaptation framework for bioNER tasks that can effectively leverage the domain hardness information to improve the adaptability of the learnt model in the low-resource scenarios. Experimental results on biomedical datasets show that our model can achieve significant performance improvement over the recently published state-of-the-art (SOTA) MetaNER model.

pdf bib
Learning Semantic Textual Similarity via Topic-informed Discrete Latent Variables
Erxin Yu | Lan Du | Yuan Jin | Zhepei Wei | Yi Chang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Recently, discrete latent variable models have received a surge of interest in both Natural Language Processing (NLP) and Computer Vision (CV), attributed to their comparable performance to the continuous counterparts in representation learning, while being more interpretable in their predictions. In this paper, we develop a topic-informed discrete latent variable model for semantic textual similarity, which learns a shared latent space for sentence-pair representation via vector quantization. Compared with previous models limited to local semantic contexts, our model can explore richer semantic information via topic modeling. We further boost the performance of semantic similarity by injecting the quantized representation into a transformer-based language model with a well-designed semantic-driven attention mechanism. We demonstrate, through extensive experiments across various English language datasets, that our model is able to surpass several strong neural baselines in semantic textual similarity tasks.


pdf bib
Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help?
Fahimeh Saleh | Wray Buntine | Gholamreza Haffari | Lan Du
Findings of the Association for Computational Linguistics: EMNLP 2021

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages. Learning a single model can enhance the low-resource translation by leveraging data from multiple languages. However, the performance of an MNMT model is highly dependent on the type of languages used in training, as transferring knowledge from a diverse set of languages degrades the translation performance due to negative transfer. In this paper, we propose a Hierarchical Knowledge Distillation (HKD) approach for MNMT which capitalises on language groups generated according to typological features and phylogeny of languages to overcome the issue of negative transfer. HKD generates a set of multilingual teacher-assistant models via a selective knowledge distillation mechanism based on the language groups, and then distills the ultimate multilingual model from those assistants in an adaptive way. Experimental results derived from the TED dataset with 53 languages demonstrate the effectiveness of our approach in avoiding the negative transfer effect in MNMT, leading to an improved translation performance (about 1 BLEU score in average) compared to strong baselines.

pdf bib
Transformer over Pre-trained Transformer for Neural Text Segmentation with Enhanced Topic Coherence
Kelvin Lo | Yuan Jin | Weicong Tan | Ming Liu | Lan Du | Wray Buntine
Findings of the Association for Computational Linguistics: EMNLP 2021

This paper proposes a transformer over transformer framework, called Transformerˆ2, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level transformer-based segmentation model based on the sentence embeddings. The bottom-level component transfers the pre-trained knowledge learnt from large external corpora under both single and pair-wise supervised NLP tasks to model the sentence embeddings for the documents. Given the sentence embeddings, the upper-level transformer is trained to recover the segmentation boundaries as well as the topic labels of each sentence. Equipped with a multi-task loss and the pre-trained knowledge, Transformerˆ2 can better capture the semantic coherence within the same segments. Our experiments show that (1) Transformerˆ2$manages to surpass state-of-the-art text segmentation models in terms of a commonly-used semantic coherence measure; (2) in most cases, both single and pair-wise pre-trained knowledge contribute to the model performance; (3) bottom-level sentence encoders pre-trained on specific languages yield better performance than those pre-trained on specific domains.

pdf bib
Leveraging Information Bottleneck for Scientific Document Summarization
Jiaxin Ju | Ming Liu | Huan Yee Koh | Yuan Jin | Lan Du | Shirui Pan
Findings of the Association for Computational Linguistics: EMNLP 2021

This paper presents an unsupervised extractive approach to summarize scientific long documents based on the Information Bottleneck principle. Inspired by previous work which uses the Information Bottleneck principle for sentence compression, we extend it to document level summarization with two separate steps. In the first step, we use signal(s) as queries to retrieve the key content from the source document. Then, a pre-trained language model conducts further sentence search and edit to return the final extracted summaries. Importantly, our work can be flexibly extended to a multi-view framework by different signals. Automatic evaluation on three scientific document datasets verifies the effectiveness of the proposed framework. The further human evaluation suggests that the extracted summaries cover more content aspects than previous systems.

pdf bib
Neural Attention-Aware Hierarchical Topic Model
Yuan Jin | He Zhao | Ming Liu | Lan Du | Wray Buntine
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Neural topic models (NTMs) apply deep neural networks to topic modelling. Despite their success, NTMs generally ignore two important aspects: (1) only document-level word count information is utilized for the training, while more fine-grained sentence-level information is ignored, and (2) external semantic knowledge regarding documents, sentences and words are not exploited for the training. To address these issues, we propose a variational autoencoder (VAE) NTM model that jointly reconstructs the sentence and document word counts using combinations of bag-of-words (BoW) topical embeddings and pre-trained semantic embeddings. The pre-trained embeddings are first transformed into a common latent topical space to align their semantics with the BoW embeddings. Our model also features hierarchical KL divergence to leverage embeddings of each document to regularize those of their sentences, paying more attention to semantically relevant sentences. Both quantitative and qualitative experiments have shown the efficacy of our model in 1) lowering the reconstruction errors at both the sentence and document levels, and 2) discovering more coherent topics from real-world datasets.


pdf bib
Multi-label Few/Zero-shot Learning with Knowledge Aggregated from Multiple Label Graphs
Jueqing Lu | Lan Du | Ming Liu | Joanna Dipnall
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples. It becomes more difficult in multi-label classification, where each instance is labelled with more than one class. In this paper, we present a simple multi-graph aggregation model that fuses knowledge from multiple label graphs encoding different semantic label relationships in order to study how the aggregated knowledge can benefit multi-label zero/few-shot document classification. The model utilises three kinds of semantic information, i.e., the pre-trained word embeddings, label description, and pre-defined label relations. Experimental results derived on two large clinical datasets (i.e., MIMIC-II and MIMIC-III ) and the EU legislation dataset show that methods equipped with the multi-graph knowledge aggregation achieve significant performance improvement across almost all the measures on few/zero-shot labels.


pdf bib
Leveraging Meta Information in Short Text Aggregation
He Zhao | Lan Du | Guanfeng Liu | Wray Buntine
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Short texts such as tweets often contain insufficient word co-occurrence information for training conventional topic models. To deal with the insufficiency, we propose a generative model that aggregates short texts into clusters by leveraging the associated meta information. Our model can generate more interpretable topics as well as document clusters. We develop an effective Gibbs sampling algorithm favoured by the fully local conjugacy in the model. Extensive experiments demonstrate that our model achieves better performance in terms of document clustering and topic coherence.


pdf bib
Unsupervised Text Segmentation Based on Native Language Characteristics
Shervin Malmasi | Mark Dras | Mark Johnson | Lan Du | Magdalena Wolska
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Most work on segmenting text does so on the basis of topic changes, but it can be of interest to segment by other, stylistically expressed characteristics such as change of authorship or native language. We propose a Bayesian unsupervised text segmentation approach to the latter. While baseline models achieve essentially random segmentation on our task, indicating its difficulty, a Bayesian model that incorporates appropriately compact language models and alternating asymmetric priors can achieve scores on the standard metrics around halfway to perfect segmentation.


pdf bib
Improving Topic Models with Latent Feature Word Representations
Dat Quoc Nguyen | Richard Billingsley | Lan Du | Mark Johnson
Transactions of the Association for Computational Linguistics, Volume 3

Probabilistic topic models are widely used to discover latent topics in document collections, while latent feature vector representations of words have been used to obtain high performance in many NLP tasks. In this paper, we extend two different Dirichlet multinomial topic models by incorporating latent feature vector representations of words trained on very large corpora to improve the word-topic mapping learnt on a smaller corpus. Experimental results show that by using information from the external corpora, our new models produce significant improvements on topic coherence, document clustering and document classification tasks, especially on datasets with few or short documents.

pdf bib
Using Entity Information from a Knowledge Base to Improve Relation Extraction
Lan Du | Anish Kumar | Mark Johnson | Massimiliano Ciaramita
Proceedings of the Australasian Language Technology Association Workshop 2015

pdf bib
A Computationally Efficient Algorithm for Learning Topical Collocation Models
Zhendong Zhao | Lan Du | Benjamin Börschinger | John K Pate | Massimiliano Ciaramita | Mark Steedman | Mark Johnson
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)


pdf bib
Topic Segmentation with a Structured Topic Model
Lan Du | Wray Buntine | Mark Johnson
Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies


pdf bib
Modelling Sequential Text with an Adaptive Topic Model
Lan Du | Wray Buntine | Huidong Jin
Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning