RUC AI Box 每周論文推薦 （10.8~10.14上）

來自專欄 RUC智能情報站

下面論文列表為本小組同學推薦和整理，關於論文細節請聯繫論文作者。

推薦系統

Explainable Recommendation via Multi-Task Learning in Opinionated Text Data

#SIGIR 2018

摘要：Explaining automatically generated recommendations allows users to make more informed and accurate decisions about which results to utilize, and therefore improves their satisfaction. In this work, we develop a multi-task learning solution for explainable recommendation. Two companion learning tasks of user preference modeling for recommendation and opinionated content modeling for explanation are integrated via a joint tensor factorization. As a result, the algorithm predicts not only a user』s preference over a list of items, i.e., recommendation, but also how the user would appreciate a particular item at the feature level, i.e., opinionated textual explanation. Extensive experiments on two large collections of Amazon and Yelp reviews confirmed the effectiveness of our solution in both recommendation and explanation tasks, compared with several existing recommendation algorithms. And our extensive user study clearly demonstrates the practical value of the explainable recommendations generated by our algorithm.

推薦理由：通過joint tensor factorization將用戶，產品，特徵，和觀點短語映射到同一表示空間。

Fusing Diversity in Recommendations in Heterogeneous Information Networks

#WSDM 2018

摘要：In the past, hybrid recommender systems have shown the power of exploiting relationships amongst objects which directly or indirectly effect the recommendation task. However, the effect of all relations is not equal, and choosing their right balance for a recommendation problem at hand is non-trivial. We model these interactions using a Heterogeneous Information Network, and propose a systematic framework for learning their influence weights for a given recommendation task. Further, we address the issue of redundant results, which is very much prevalent in recommender systems. To alleviate redundancy in recommendations we use Vertex Reinforced Random Walk (a non-Markovian random walk) over a heterogeneous graph. It works by boosting the transitions to the influential nodes, while simultaneously shrinking the weights of others. This helps in discouraging recommendation of multiple influential nodes which lie in close proximity of each other, thus ensuring diversity. Finally, we demonstrate the effectiveness of our approach by experimenting on real world datasets. We find that, with the weights of relations learned using the proposed non-Markovian random walk based framework, the results consistently improve over the baselines.

推薦理由：本文使用異構信息網路對對象之間直接或者間接關係進行建模，來學習它們對推薦任務的影響權重，並使用非馬爾科夫隨機遊動來減少推薦中的冗餘。

Recommendation in Heterogeneous Information Networks Based on Generalized Random Walk Model and Bayesian Personalized Ranking

#WSDM 2018

摘要：Recommendation based on heterogeneous information network(HIN) is attracting more and more attention due to its ability to emulate collaborative filtering, content-based filtering, context-aware recommendation and combinations of any of these recommendation semantics. Random walk based methods are usually used to mine the paths, weigh the paths, and compute the closeness or relevance between two nodes in a HIN. A key for the success of these methods is how to properly set the weights of links in a HIN. In existing methods, the weights of links are mostly set heuristically. In this paper, we propose a Bayesian Personalized Ranking(BPR) based machine learning method, called HeteLearn, to learn the weights of links in a HIN. In order to model user preferences for personalized recommendation, we also propose a generalized random walk with restart model on HINs. We evaluate the proposed method in a personalized recommendation task and a tag recommendation task. Experimental results show that our method performs significantly better than both the traditional collaborative filtering and the state-of-the-art HIN-based recommendation methods.

推薦理由：本文提出HeteLearn，一種基於BPR的機器學習方法，來學習異構信息網路中連接兩個結點的各種link的權重，並輔助推薦。

Learning from History and Present: Next-item Recommendation via Discriminatively Exploiting User Behaviors

#SIGKDD 2018

摘要：In the modern e-commerce, the behaviors of customers contain rich information, e.g., consumption habits, the dynamics of preferences. Recently, session-based recommendations are becoming popular to explore the temporal characteristics of customers』 interactive behaviors. However, existing works mainly exploit the short-term behaviors without fully taking the customers』 long-term stable preferences and evolutions into account. In this paper, we propose a novel Behavior-Intensive Neural Network (BINN) for next-item recommendation by incorporating both users』 historical stable preferences and present consumption motivations. Specifically, BINN contains two main components, i.e., Neural Item Embedding, and Discriminative Behaviors Learning. Firstly, a novel item embedding method based on user interactions is developed for obtaining an unified representation for each item. Then, with the embedded items and the interactive behaviors over item sequences, BINN discriminatively learns the historical preferences and present motivations of the target users. Thus, BINN could better perform recommendations of the next items for the target users. Finally, for evaluating the performances of BINN, we conduct extensive experiments on two real-world datasets, i.e., Tianchi and JD. The experimental results clearly demonstrate the effectiveness of BINN compared with several state-of-the-art methods.

推薦理由：文中的模型包括一個Item Embedding和兩個RNN。Item Embedding對用戶產生的item序列運用類Skip-gram的模型，兩個RNN分別用於捕獲用戶當前偏好和歷史偏好。

自然語言處理

Multi-Granularity Hierarchical Attention Fusion Networks for Reading Comprehension and Question Answering

#ACL 2018

摘要：This paper describes a novel hierarchical attention network for reading comprehension style question answering, which aims to answer questions for a given narrative paragraph. In the proposed method, attention and fusion are conducted horizontally and vertically across layers at different levels of granularity between question and paragraph. Specifically, it first encode the question and paragraph with fine-grained language embeddings, to better capture the respective representations at semantic level. Then it proposes a multi-granularity fusion approach to fully fuse information from both global and attended representations. Finally, it introduces a hierarchical attention network to focuses on the answer span progressively with multi-level soft-alignment. Extensive experiments on the large-scale SQuAD, TriviaQA dataset validate the effectiveness of the proposed method. At the time of writing the paper, our model achieves state-of-the-art on the both SQuAD and TriviaQA Wiki leaderboard as well as two adversarial SQuAD datasets.

推薦理由：本文提出一個多粒度分層注意力融合網路，來解決機器閱讀理解及問答的任務，更好地提取文章的語義信息。

MojiTalk: Generating Emotional Responses at Scale

#ACL 2018

摘要：Generating emotional language is a key step towards building empathetic natural language processing agents. However, a major challenge for this line of research is the lack of large-scale labeled training data, and previous studies are limited to only small sets of human annotated sentiment labels. Additionally, explicitly controlling the emotion and sentiment of generated text is also difficult. In this paper, we take a more radical approach: we exploit the idea of leveraging Twitter data that are naturally labeled with emojis. More specifically, we collect a large corpus of Twitter conversations that include emojis in the response, and assume the emojis convey the underlying emotions of the sentence. We then introduce a reinforced conditional variational encoder approach to train a deep generative model on these conversations, which allows us to use emojis to control the emotion of the generated text. Experimentally, we show in our quantitative and qualitative analyses that the proposed models can successfully generate high-quality abstractive conversation responses in accordance with designated emotions.

推薦理由：本文利用twitter上包含emoji表情的文本建立了一個大規模的有標籤的情感數據集。

Multi-Source Pointer Network for Product Title Summarization

#CIKM 2018

摘要：In this paper, we study the product title summarization problem in E-commerce applications for display on mobile devices. Comparing with conventional sentence summarization, product title summarization has some extra and essential constraints. For example, factual detail errors or loss of the key information are intolerable for E-commerce applications. Therefore, we abstract two more constraints for product title summarization: (i) do not introduce irrelevant information; (ii) retain the key information ( e.g. , brand name and commodity name). To address these issues, we propose a novel multi-source pointer network by adding a new knowledge en- coder for pointer network. The first constraint is handled by pointer mechanism , generating the short title by copying words from the source title. For the second constraint, we restore the key information by copying words from the knowledge encoder with the help of the soft gating mechanism. For evaluation, we build a large collection of real-world product titles along with human-written short titles. Experimental results demonstrate that our model significantly outperforms the other baselines.Finally, online deployment of our proposed model has yielded a significant business impact, as measured by the click-through rate.

推薦理由：本文提出一種從多個源文本中應用pointer機制的網路用於商品標題生成，除了從source title，還有一些額外的品牌名稱和商品名稱中也包含重要信息，用一個soft gate來控制從原文還是關鍵信息中抽詞，生成的標題在線上點擊率測試中有很好的效果

Faithful to the Original: Fact-Aware Neural Abstractive Summarization

#AAAI 2018

摘要：Unlike extractive summarization, abstractive summarization has to fuse different parts of the source text, which inclines to create fake facts. Our preliminary study reveals nearly 30% of the outputs from a state-of-the-art neural summarization system suffer from this problem. While previous abstractive summarization approaches usually focus on the improvement of informativeness, we argue that faithfulness is also a vital prerequisite for a practical abstractive summarization system. To avoid generating fake facts in a summary, we leverage open information extraction and dependency parse technologies to extract actual fact descriptions from the source text. The dual-attention sequence-to-sequence framework is then proposed to force the generation conditioned on both the source text and the extracted fact descriptions. Experiments on the Gigaword benchmark dataset demonstrate that our model can greatly reduce fake summaries by 80%. Notably, the fact descriptions also bring significant improvement on informativeness since they often condense the meaning of the source text.

推薦理由：與之前的模型致力於提高摘要文本的信息豐富程度不同，本文旨在強調摘要文本忠實於原文這一前提。

FRAGE: Frequency-Agnostic Word Representation

#NIPS 2018

摘要：Continuous word representation (aka word embedding) is a basic building block in many neural network-based models used in natural language processing tasks. Although it is widely accepted that words with similar semantics should be close to each other in the embedding space, we find that word embeddings learned in several tasks are biased towards word frequency: the embeddings of highfrequency and low-frequency words lie in different subregions of the embedding space, and the embedding of a rare word and a popular word can be far from each other even if they are semantically similar. This makes learned word embeddings ineffective, especially for rare words, and consequently limits the performance of these neural network models. In this paper, we develop a neat, simple yet effective way to learn FRequency-AGnostic word Embedding (FRAGE) using adversarial training. We conducted comprehensive studies on ten datasets across four natural language processing tasks, including word similarity, language modeling, machine translation and text classification. Results show that with FRAGE, we achieve higher performance than the baselines in all tasks.

推薦理由：本文使用對抗訓練的方法，解決了兩個語義相近的低頻詞和高頻詞相似度低的問題。

RUC AI Box 每周論文推薦 （10.8~10.14下）