Transformer is a powerful model for text understanding. However, it is inefficient due to its quadratic complexity to input sequence length. Although there are many methods on Transformer acceleration, they are still either inefficient on long sequences or not effective enough. In this paper, we propose Fastformer, which is an efficient Transformer model based on additive attention. In Fastformer, instead of modeling the pair-wise interactions between tokens, we first use additive attention mechanism to model global contexts, and then further transform each token representation based on its interaction with global context representations. In this way, Fastformer can achieve effective context modeling with linear complexity. Extensive experiments on five datasets show that Fastformer is much more efficient than many existing Transformer models and can meanwhile achieve comparable or even better long text modeling performance.
News recommendation is often modeled as a sequential recommendation task, which assumes that there are rich short-term dependencies over historical clicked news. However, in news recommendation scenarios users usually have strong preferences on the temporal diversity of news information and may not tend to click similar news successively, which is very different from many sequential recommendation scenarios such as e-commerce recommendation. In this paper, we study whether news recommendation can be regarded as a standard sequential recommendation problem. Through extensive experiments on two real-world datasets, we find that modeling news recommendation as a sequential recommendation problem is suboptimal. To handle this challenge, we further propose a temporal diversity-aware news recommendation method that can promote candidate news that are diverse from recently clicked news, which can help predict future clicks more accurately. Experiments show that our approach can consistently improve various news recommendation methods.
Personalized news recommendation is an important technique to help users find their interested news information and alleviate their information overload. It has been extensively studied over decades and has achieved notable success in improving users' news reading experience. However, there are still many unsolved problems and challenges that need to be further studied. To help researchers master the advances in personalized news recommendation over the past years, in this paper we present a comprehensive overview of personalized news recommendation. Instead of following the conventional taxonomy of news recommendation methods, in this paper we propose a novel perspective to understand personalized news recommendation based on its core problems and the associated techniques and challenges. We first review the techniques for tackling each core problem in a personalized news recommender system and the challenges they face. Next, we introduce the public datasets and evaluation methods for personalized news recommendation. We then discuss the key points on improving the responsibility of personalized news recommender systems. Finally, we raise several research directions that are worth investigating in the future. This paper can provide up-to-date and comprehensive views to help readers understand the personalized news recommendation field. We hope this paper can facilitate research on personalized news recommendation and as well as related fields in natural language processing and data mining.
News recommendation is important for improving news reading experience of users. Users' news click behaviors are widely used for inferring user interests and predicting future clicks. However, click behaviors are heavily affected by the biases brought by the positions of news displayed on the webpage. It is important to eliminate the effect of position biases on the recommendation model to accurately target user interests. In this paper, we propose a news recommendation method named DebiasGAN that can effectively eliminate the effect of position biases via adversarial learning. We use a bias-aware click model to capture the influence of position bias on click behaviors, and we use a bias-invariant click model with random candidate news positions to estimate the ideally unbiased click scores. We apply adversarial learning techniques to the hidden representations learned by the two models to help the bias-invariant click model capture the bias-independent interest of users on news. Experimental results on two real-world datasets show that DebiasGAN can effectively improve the accuracy of news recommendation by eliminating position biases.
Personalized news recommendation methods are widely used in online news services. These methods usually recommend news based on the matching between news content and user interest inferred from historical behaviors. However, these methods usually have difficulties in making accurate recommendations to cold-start users, and tend to recommend similar news with those users have read. In general, popular news usually contain important information and can attract users with different interests. Besides, they are usually diverse in content and topic. Thus, in this paper we propose to incorporate news popularity information to alleviate the cold-start and diversity problems for personalized news recommendation. In our method, the ranking score for recommending a candidate news to a target user is the combination of a personalized matching score and a news popularity score. The former is used to capture the personalized user interest in news. The latter is used to measure time-aware popularity of candidate news, which is predicted based on news content, recency, and real-time CTR using a unified framework. Besides, we propose a popularity-aware user encoder to eliminate the popularity bias in user behaviors for accurate interest modeling. Experiments on two real-world datasets show our method can effectively improve the accuracy and diversity for news recommendation.
User interest modeling is critical for personalized news recommendation. Existing news recommendation methods usually learn a single user embedding for each user from their previous behaviors to represent their overall interest. However, user interest is usually diverse and multi-grained, which is difficult to be accurately modeled by a single user embedding. In this paper, we propose a news recommendation method with hierarchical user interest modeling, named HieRec. Instead of a single user embedding, in our method each user is represented in a hierarchical interest tree to better capture their diverse and multi-grained interest in news. We use a three-level hierarchy to represent 1) overall user interest; 2) user interest in coarse-grained topics like sports; and 3) user interest in fine-grained topics like football. Moreover, we propose a hierarchical user interest matching framework to match candidate news with different levels of user interest for more accurate user interest targeting. Extensive experiments on two real-world datasets validate our method can effectively improve the performance of user modeling for personalized news recommendation.
Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interactive Transformer (Hi-Transformer) for efficient and effective long document modeling. Hi-Transformer models documents in a hierarchical way, i.e., first learns sentence representations and then learns document representations. It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence. More specifically, we first use a sentence Transformer to learn the representations of each sentence. Then we use a document Transformer to model the global document context from these sentence representations. Next, we use another sentence Transformer to enhance sentence modeling using the global document context. Finally, we use hierarchical pooling method to obtain document embedding. Extensive experiments on three benchmark datasets validate the efficiency and effectiveness of Hi-Transformer in long document modeling.
Pre-trained language models (PLMs) achieve great success in NLP. However, their huge model sizes hinder their applications in many practical systems. Knowledge distillation is a popular technique to compress PLMs, which learns a small student model from a large teacher PLM. However, the knowledge learned from a single teacher may be limited and even biased, resulting in low-quality student model. In this paper, we propose a multi-teacher knowledge distillation framework named MT-BERT for pre-trained language model compression, which can train high-quality student model from multiple teacher PLMs. In MT-BERT we design a multi-teacher co-finetuning method to jointly finetune multiple teacher PLMs in downstream tasks with shared pooling and prediction layers to align their output space for better collaborative teaching. In addition, we propose a multi-teacher hidden loss and a multi-teacher distillation loss to transfer the useful knowledge in both hidden states and soft labels from multiple teacher PLMs to the student model. Experiments on three benchmark datasets validate the effectiveness of MT-BERT in compressing PLMs.