Neural Keyphrase Generation via Reinforcement Learning with Adaptive Rewards

Abstract

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. Document: DCE MRI data analysis for cancer area classification. The paper aims at improving the support of medical researchers in the context of in-vivo cancer imaging… The proposed approach is based on a three-step procedure: i) robust feature extraction from raw time-intensity curves, ii) voxel segmentation, and iii) voxel classification based on a learning-by-example approach… Finally, in the third step, a support vector machine (SVM) is trained to classify voxels according to the labels obtained by the clustering phase…

One Size Does Not Fit All: Generating and Evaluating Variable Number of Keyphrases

“…We acknowledge that F1@O scores ofChan et al (2019) andChen et al (2019a) might be not completely comparable with ours. This is due to additional post-processing and filtering methods might have been applied in different work.…”

“…Chen et al (2018b); Ye and Wang (2018) proposed to use structure information (e.g., title of source text) to improve keyphrase generation performance. Chan et al (2019) introduced RL to the keyphrase generation task. Chen et al (2019a) retrieved similar documents from training data to help producing more accurate keyphrases.…”

“…We include a set of existing models (Meng et al, 2017;Chen et al, 2018a;Chan et al, 2019;Zhao and Zhang, 2019;Chen et al, 2019a) as baselines, they all share same behavior of abstractive keyphrase generation with our proposed model. Specially for computing existing model's scores with our proposed new metrics (F 1 @O and F 1 @M), we implemented our own version of CopyRNN (Meng et al, 2017) based on their open sourced code, denoted as CopyRNN*.…”

“…Our first dataset consists of a collection of scientific publication datasets, namely KP20K, IN S P E C, KR A P I V I N, NUS, and SE MEV A L, that have been widely used in existing literature (Meng et al, 2017;Chen et al, 2018a;Ye and Wang, 2018;Chen et al, 2018b;Chan et al, 2019;Zhao and Zhang, 2019;Chen et al, 2019a;Sun et al, 2019). KP20K, for example, was introduced by Meng et al (2017) and comprises more than half a million scientific publications.…”

Keyphrase Generation: A Multi-Aspect Survey

“…Given that the above catSeq model tends to generate fewer keywords than the ground-truth, authors of [79] reformulate it from the RL (Reinforcement Learning) perspective which has also been applied recently in several text summarization works like [80], [81] or [82] and similar seq2seq applications described in [82]. The model is stimulated to generate enough keyphrases employing an adaptive reward function that is based on recall (not penalized by incorrect predictions) in undergeneration scenarios and F 1 (penalized by more incorrect predictions) in overgeneration scenarios.…”