This paper studies the advertisers from whom the search engine may increase the revenue by offering an advanced sponsored search service. We divide them into head and tail advertisers according to ...their contributions to the search engine revenue. Data analysis shows that some tail advertisers have large amount of budgets and low budget usage ratios, who aimed to achieve the planned campaign goals (e.g., a large number of clicks), but they finally failed in doing so due to wrongly-selected bid keywords, inappropriate bid prices, and/or low-quality ad creatives. In this paper, we conduct a deep analysis on these advertisers. Specially, we define the measures to distinguish potential head advertisers from tail advertisers, and then run simulation experiments on the potential head advertisers by applying different improvements. Encouraging results have been achieved by our diagnosing approaches. We also show that a decision tree model can be implemented for a better improvement to those advertisers.
This paper is concerned with actively predicting search intent from user browsing behavior data. In recent years, great attention has been paid to predicting user search intent. However, the ...prediction was mostly passive because it was performed only after users submitted their queries to search engines. It is not considered why users issued these queries, and what triggered their information needs. According to our study, many information needs of users were actually triggered by what they have browsed. That is, after reading a page, if a user found something interesting or unclear, he/she might have the intent to obtain further information and accordingly formulate a search query. Actively predicting such search intent can benefit both search engines and their users. In this paper, we propose a series of technologies to fulfill this task. First, we extract all the queries that users issued after reading a given page from user browsing behavior data. Second, we learn a model to effectively rank these queries according to their likelihoods of being triggered by the page. Third, since search intents can be quite diverse even if triggered by the same page, we propose an optimization algorithm to diversify the ranked list of queries obtained in the second step, and then suggest the list to users. We have tested our approach on large-scale user browsing behavior data obtained from a commercial search engine. The experimental results have shown that our approach can predict meaningful queries for a given page, and the search performance for these queries can be significantly improved by using the triggering page as contextual information.
Teaching is critical to human society: it is with teaching that prospective students are educated and human civilization can be inherited and advanced. A good teacher not only provides his/her ...students with qualified teaching materials (e.g., textbooks), but also sets up appropriate learning objectives (e.g., course projects and exams) considering different situations of a student. When it comes to artificial intelligence, treating machine learning models as students, the loss functions that are optimized act as perfect counterparts of the learning objective set by the teacher. In this work, we explore the possibility of imitating human teaching behaviors by dynamically and automatically outputting appropriate loss functions to train machine learning models. Different from typical learning settings in which the loss function of a machine learning model is predefined and fixed, in our framework, the loss function of a machine learning model (we call it student) is defined by another machine learning model (we call it teacher). The ultimate goal of teacher model is cultivating the student to have better performance measured on development dataset. Towards that end, similar to human teaching, the teacher, a parametric model, dynamically outputs different loss functions that will be used and optimized by its student model at different training stages. We develop an efficient learning method for the teacher model that makes gradient based optimization possible, exempt of the ineffective solutions such as policy optimization. We name our method as "learning to teach with dynamic loss functions" (L2T-DLF for short). Extensive experiments on real world tasks including image classification and neural machine translation demonstrate that our method significantly improves the quality of various student models.
In this paper, we study a new learning paradigm for Neural Machine Translation (NMT). Instead of maximizing the likelihood of the human translation as in previous works, we minimize the distinction ...between human translation and the translation given by an NMT model. To achieve this goal, inspired by the recent success of generative adversarial networks (GANs), we employ an adversarial training architecture and name it as Adversarial-NMT. In Adversarial-NMT, the training of the NMT model is assisted by an adversary, which is an elaborately designed Convolutional Neural Network (CNN). The goal of the adversary is to differentiate the translation result generated by the NMT model from that by human. The goal of the NMT model is to produce high quality translations so as to cheat the adversary. A policy gradient method is leveraged to co-train the NMT model and the adversary. Experimental results on English\(\rightarrow\)French and German\(\rightarrow\)English translation tasks show that Adversarial-NMT can achieve significantly better translation quality than several strong baselines.
In many applications, we need to cluster large-scale data objects. However, some recently proposed clustering algorithms such as spectral clustering can hardly handle large-scale applications due to ...the complexity issue, although their effectiveness has been demonstrated in previous work. In this paper, we propose a fast solver for spectral clustering. In contrast to traditional spectral clustering algorithms that first solve an eigenvalue decomposition problem, and then employ a clustering heuristic to obtain labels for the data points, our new approach sequentially decides the labels of relatively well-separated data points. Because the scale of the problem shrinks quickly during this process, it can be much faster than the traditional methods. Experiments on both synthetic data and a large collection of product records show that our algorithm can achieve significant improvement in speed as compared to traditional spectral clustering algorithms.
Q-learning is one of the most popular methods in Reinforcement Learning (RL). Transfer Learning aims to utilize the learned knowledge from source tasks to help new tasks to improve the sample ...complexity of the new tasks. Considering that data collection in RL is both more time and cost consuming and Q-learning converges slowly comparing to supervised learning, different kinds of transfer RL algorithms are designed. However, most of them are heuristic with no theoretical guarantee of the convergence rate. Therefore, it is important for us to clearly understand when and how will transfer learning help RL method and provide the theoretical guarantee for the improvement of the sample complexity. In this paper, we propose to transfer the Q-function learned in the source task to the target of the Q-learning in the new task when certain safe conditions are satisfied. We call this new transfer Q-learning method target transfer Q-Learning. The safe conditions are necessary to avoid the harm to the new tasks and thus ensure the convergence of the algorithm. We study the convergence rate of the target transfer Q-learning. We prove that if the two tasks are similar with respect to the MDPs, the optimal Q-functions in the source and new RL tasks are similar which means the error of the transferred target Q-function in new MDP is small. Also, the convergence rate analysis shows that the target transfer Q-Learning will converge faster than Q-learning if the error of the transferred target Q-function is smaller than the current Q-function in the new task. Based on our theoretical results, we design the safe condition as the Bellman error of the transferred target Q-function is less than the current Q-function. Our experiments are consistent with our theoretical founding and verified the effectiveness of our proposed target transfer Q-learning method.
In reinforcement learning (RL) , one of the key components is policy evaluation, which aims to estimate the value function (i.e., expected long-term accumulated reward) of a policy. With a good ...policy evaluation method, the RL algorithms will estimate the value function more accurately and find a better policy. When the state space is large or continuous \emph{Gradient-based Temporal Difference(GTD)} policy evaluation algorithms with linear function approximation are widely used. Considering that the collection of the evaluation data is both time and reward consuming, a clear understanding of the finite sample performance of the policy evaluation algorithms is very important to reinforcement learning. Under the assumption that data are i.i.d. generated, previous work provided the finite sample analysis of the GTD algorithms with constant step size by converting them into convex-concave saddle point problems. However, it is well-known that, the data are generated from Markov processes rather than i.i.d. in RL problems.. In this paper, in the realistic Markov setting, we derive the finite sample bounds for the general convex-concave saddle point problems, and hence for the GTD algorithms. We have the following discussions based on our bounds. (1) With variants of step size, GTD algorithms converge. (2) The convergence rate is determined by the step size, with the mixing time of the Markov process as the coefficient. The faster the Markov processes mix, the faster the convergence. (3) We explain that the experience replay trick is effective by improving the mixing property of the Markov process. To the best of our knowledge, our analysis is the first to provide finite sample bounds for the GTD algorithms in Markov setting.
Word embedding, which refers to low-dimensional dense vector representations of natural words, has demon-strated its power in many natural language processing tasks. However, it may suffer from the ...inaccurate and incomplete information contained in the free text corpus as training data. To tackle this challenge, there have been quite a few studies that leverage knowledge graphs as an additional information source to improve the quality of word embedding. Although these studies have achieved certain success, they have neglected some important facts about knowledge graphs: 1) many relationships in knowledge graphs are many-to-one, one-to-many or even many-to-many, rather than simply one-to-one; 2) most head entities and tail entities in knowledge graphs come from very different semantic spaces. To address these issues, in this paper, we propose a new algorithm named ProjectNet. ProjectNet models the relationships between head and tail entities after transforming them with different low-rank projection matrices. The low-rank projection can allow non one-to-one relationships between entities, while different projection matrices for head and tail entities allow them to originate in different semantic spaces. The experimental results demonstrate that ProjectNet yields more accurate word embedding than previous studies, and thus leads to clear improvements in various natural language processing tasks.
Grapheme-to-phoneme (G2P) conversion is an important task in automatic speech recognition and text-to-speech systems. Recently, G2P conversion is viewed as a sequence to sequence task and modeled by ...RNN or CNN based encoder-decoder framework. However, previous works do not consider the practical issues when deploying G2P model in the production system, such as how to leverage additional unlabeled data to boost the accuracy, as well as reduce model size for online deployment. In this work, we propose token-level ensemble distillation for G2P conversion, which can (1) boost the accuracy by distilling the knowledge from additional unlabeled data, and (2) reduce the model size but maintain the high accuracy, both of which are very practical and helpful in the online production system. We use token-level knowledge distillation, which results in better accuracy than the sequence-level counterpart. What is more, we adopt the Transformer instead of RNN or CNN based models to further boost the accuracy of G2P conversion. Experiments on the publicly available CMUDict dataset and an internal English dataset demonstrate the effectiveness of our proposed method. Particularly, our method achieves 19.88% WER on CMUDict dataset, outperforming the previous works by more than 4.22% WER, and setting the new state-of-the-art results.