Hou Pong Chan


pdf bib
PLANET: Dynamic Content Planning in Autoregressive Transformers for Long-form Text Generation
Zhe Hu | Hou Pong Chan | Jiachen Liu | Xinyan Xiao | Hua Wu | Lifu Huang
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Despite recent progress of pre-trained language models on generating fluent text, existing methods still suffer from incoherence problems in long-form text generation tasks that require proper content control and planning to form a coherent high-level logical flow. In this work, we propose PLANET, a novel generation framework leveraging autoregressive self-attention mechanism to conduct content planning and surface realization dynamically. To guide the generation of output sentences, our framework enriches the Transformer decoder with latent representations to maintain sentence-level semantic plans grounded by bag-of-words. Moreover, we introduce a new coherence-based contrastive learning objective to further improve the coherence of output. Extensive experiments are conducted on two challenging long-form text generation tasks including counterargument generation and opinion article generation. Both automatic and human evaluations show that our method significantly outperforms strong baselines and generates more coherent texts with richer contents.

pdf bib
MOCHA: A Multi-Task Training Approach for Coherent Text Generation from Cognitive Perspective
Zhe Hu | Hou Pong Chan | Lifu Huang
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

Teaching neural models to generate narrative coherent texts is a critical problem. Recent pre-trained language models have achieved promising results, but there is still a gap between human written texts and machine-generated outputs. In this work, we propose a novel multi-task training strategy for long text generation grounded on the cognitive theory of writing, which empowers the model to learn essential subskills needed for writing including planning and reviewing besides end-to-end generation. We extensively evaluate our model on three open-ended generation tasks including story generation, news article writing and argument generation. Experiments show that our model achieves better results on both few-shot and fully-supervised settings than strong baselines, and human evaluations confirm that our model can generate more coherent outputs.


pdf bib
Controllable Summarization with Constrained Markov Decision Process
Hou Pong Chan | Lu Wang | Irwin King
Transactions of the Association for Computational Linguistics, Volume 9

Abstract We study controllable text summarization, which allows users to gain control on a particular attribute (e.g., length limit) of the generated summaries. In this work, we propose a novel training framework based on Constrained Markov Decision Process (CMDP), which conveniently includes a reward function along with a set of constraints, to facilitate better summarization control. The reward function encourages the generation to resemble the human-written reference, while the constraints are used to explicitly prevent the generated summaries from violating user-imposed requirements. Our framework can be applied to control important attributes of summarization, including length, covered entities, and abstractiveness, as we devise specific constraints for each of these aspects. Extensive experiments on popular benchmarks show that our CMDP framework helps generate informative summaries while complying with a given attribute’s requirement.1


pdf bib
Exclusive Hierarchical Decoding for Deep Keyphrase Generation
Wang Chen | Hou Pong Chan | Piji Li | Irwin King
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Keyphrase generation (KG) aims to summarize the main ideas of a document into a set of keyphrases. A new setting is recently introduced into this problem, in which, given a document, the model needs to predict a set of keyphrases and simultaneously determine the appropriate number of keyphrases to produce. Previous work in this setting employs a sequential decoding process to generate keyphrases. However, such a decoding method ignores the intrinsic hierarchical compositionality existing in the keyphrase set of a document. Moreover, previous work tends to generate duplicated keyphrases, which wastes time and computing resources. To overcome these limitations, we propose an exclusive hierarchical decoding framework that includes a hierarchical decoding process and either a soft or a hard exclusion mechanism. The hierarchical decoding process is to explicitly model the hierarchical compositionality of a keyphrase set. Both the soft and the hard exclusion mechanisms keep track of previously-predicted keyphrases within a window size to enhance the diversity of the generated keyphrases. Extensive experiments on multiple KG benchmark datasets demonstrate the effectiveness of our method to generate less duplicated and more accurate keyphrases.


pdf bib
An Integrated Approach for Keyphrase Generation via Exploring the Power of Retrieval and Extraction
Wang Chen | Hou Pong Chan | Piji Li | Lidong Bing | Irwin King
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

In this paper, we present a novel integrated approach for keyphrase generation (KG). Unlike previous works which are purely extractive or generative, we first propose a new multi-task learning framework that jointly learns an extractive model and a generative model. Besides extracting keyphrases, the output of the extractive model is also employed to rectify the copy probability distribution of the generative model, such that the generative model can better identify important contents from the given document. Moreover, we retrieve similar documents with the given document from training data and use their associated keyphrases as external knowledge for the generative model to produce more accurate keyphrases. For further exploiting the power of extraction and retrieval, we propose a neural-based merging module to combine and re-rank the predicted keyphrases from the enhanced generative model, the extractive model, and the retrieved keyphrases. Experiments on the five KG benchmarks demonstrate that our integrated approach outperforms the state-of-the-art methods.

pdf bib
Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards
Hou Pong Chan | Wang Chen | Lu Wang | Irwin King
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

Generating keyphrases that summarize the main points of a document is a fundamental task in natural language processing. Although existing generative models are capable of predicting multiple keyphrases for an input document as well as determining the number of keyphrases to generate, they still suffer from the problem of generating too few keyphrases. To address this problem, we propose a reinforcement learning (RL) approach for keyphrase generation, with an adaptive reward function that encourages a model to generate both sufficient and accurate keyphrases. Furthermore, we introduce a new evaluation method that incorporates name variations of the ground-truth keyphrases using the Wikipedia knowledge base. Thus, our evaluation method can more robustly evaluate the quality of predicted keyphrases. Extensive experiments on five real-world datasets of different scales demonstrate that our RL approach consistently and significantly improves the performance of the state-of-the-art generative models with both conventional and new evaluation methods.

pdf bib
Topic-Aware Neural Keyphrase Generation for Social Media Language
Yue Wang | Jing Li | Hou Pong Chan | Irwin King | Michael R. Lyu | Shuming Shi
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

A huge volume of user-generated content is daily produced on social media. To facilitate automatic language understanding, we study keyphrase prediction, distilling salient information from massive posts. While most existing methods extract words from source posts to form keyphrases, we propose a sequence-to-sequence (seq2seq) based neural keyphrase generation framework, enabling absent keyphrases to be created. Moreover, our model, being topic-aware, allows joint modeling of corpus-level latent topic representations, which helps alleviate data sparsity widely exhibited in social media language. Experiments on three datasets collected from English and Chinese social media platforms show that our model significantly outperforms both extraction and generation models without exploiting latent topics. Further discussions show that our model learns meaningful topics, which interprets its superiority in social media keyphrase generation.


pdf bib
Thread Popularity Prediction and Tracking with a Permutation-invariant Model
Hou Pong Chan | Irwin King
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

The task of thread popularity prediction and tracking aims to recommend a few popular comments to subscribed users when a batch of new comments arrive in a discussion thread. This task has been formulated as a reinforcement learning problem, in which the reward of the agent is the sum of positive responses received by the recommended comments. In this work, we propose a novel approach to tackle this problem. First, we propose a deep neural network architecture to model the expected cumulative reward (Q-value) of a recommendation (action). Unlike the state-of-the-art approach, which treats an action as a sequence, our model uses an attention mechanism to integrate information from a set of comments. Thus, the prediction of Q-value is invariant to the permutation of the comments, which leads to a more consistent agent behavior. Second, we employ a greedy procedure to approximate the action that maximizes the predicted Q-value from a combinatorial action space. Different from the state-of-the-art approach, this procedure does not require an additional pre-trained model to generate candidate actions. Experiments on five real-world datasets show that our approach outperforms the state-of-the-art.