The past several years have witnessed Variational Auto-Encoder’s superiority in various text generation tasks. However, due to the sequential nature of the text, auto-regressive decoders tend to ignore latent variables and then reduce to simple language models, known as the KL vanishing problem, which would further deteriorate when VAE is combined with Transformer-based structures. To ameliorate this problem, we propose Della, a novel variational Transformer framework. Della learns a series of layer-wise latent variables with each inferred from those of lower layers and tightly coupled with the hidden states by low-rank tensor product. In this way, Della forces these posterior latent variables to be fused deeply with the whole computation path and hence incorporate more information. We theoretically demonstrate that our method can be regarded as entangling latent variables to avoid posterior information decrease through layers, enabling Della to get higher non-zero KL values even without any annealing or thresholding tricks. Experiments on four unconditional and three conditional generation tasks show that Della could better alleviate KL vanishing and improve both quality and diversity compared to several strong baselines.

Sentence summarization shortens given texts while maintaining core contents of the texts. Unsupervised approaches have been studied to summarize texts without ground-truth summaries. However, recent unsupervised models are extractive, which remove words from texts and thus they are less flexible than abstractive summarization. In this work, we devise an abstractive model based on reinforcement learning without ground-truth summaries. We formulate the unsupervised summarization based on the Markov decision process with rewards representing the summary quality. To further enhance the summary quality, we develop a multi-summary learning mechanism that generates multiple summaries with varying lengths for a given text, while making the summaries mutually enhance each other. Experimental results show that the proposed model substantially outperforms both abstractive and extractive models, yet frequently generating new words not contained in input texts.

Variational Auto-Encoder (VAE) has been widely adopted in text generation. Among many variants, recurrent VAE learns token-wise latent variables with each conditioned on the preceding ones, which captures sequential variability better in the era of RNN. However, it is unclear how to incorporate such recurrent dynamics into the recently dominant Transformer due to its parallelism. In this work, we propose TRACE, a Transformer-based recurrent VAE structure. TRACE imposes recurrence on segment-wise latent variables with arbitrarily separated text segments and constructs the posterior distribution with residual parameterization. Besides, we design an acceleration method by approximating idempotent matrices, which allows parallelism while maintaining the conditional dependence of latent variables. We demonstrate that TRACE could deduce a non-zero lower bound of the KL term and enhance the entanglement of each segment and preceding latent variables, providing a theoretical guarantee of generation diversity. Experiments on two unconditional and one conditional generation task show that TRACE achieves significantly improved diversity while maintaining satisfactory generation quality.

Query-aware webpage snippet extraction is widely used in search engines to help users better understand the content of the returned webpages before clicking. The extracted snippet is expected to summarize the webpage in the context of the input query. Existing snippet extraction methods mainly rely on handcrafted features of overlapping words, which cannot capture deep semantic relationships between the query and webpages. Another idea is to extract the sentences which are most relevant to queries as snippets with existing text matching methods. However, these methods ignore the contextual information of webpages, which may be sub-optimal. In this paper, we propose an effective query-aware webpage snippet extraction method named DeepQSE. In DeepQSE, the concatenation of title, query and each candidate sentence serves as an input of query-aware sentence encoder, aiming to capture the fine-grained relevance between the query and sentences. Then, these query-aware sentence representations are modeled jointly through a document-aware relevance encoder to capture contextual information of the webpage. Since the query and each sentence are jointly modeled in DeepQSE, its online inference may be slow. Thus, we further propose an efficient version of DeepQSE, named Efficient-DeepQSE, which can significantly improve the inference speed of DeepQSE without affecting its performance. The core idea of Efficient-DeepQSE is to decompose the query-aware snippet extraction task into two stages, i.e., a coarse-grained candidate sentence selection stage where sentence representations can be cached, and a fine-grained relevance modeling stage. Experiments on two datasets validate the effectiveness and efficiency of our methods.

The bloom of the Internet and the recent breakthroughs in deep learning techniques open a new door to AI for E-commence, with a trend of evolving from using a few financial factors such as liquidity and profitability to using more advanced AI techniques to process complex and multi-modal data. In this paper, we tackle the practical problem of restaurant survival prediction. We argue that traditional methods ignore two essential respects, which are very helpful for the task: 1) modeling customer reviews and 2) jointly considering status prediction and result explanation. Thus, we propose a novel joint learning framework for explainable restaurant survival prediction based on the multi-modal data of user-restaurant interactions and users’ textual reviews. Moreover, we design a graph neural network to capture the high-order interactions and design a co-attention mechanism to capture the most informative and meaningful signal from noisy textual reviews. Our results on two datasets show a significant and consistent improvement over the SOTA techniques (average 6.8% improvement in prediction and 45.3% improvement in explanation).

Bilingual lexicon induction induces the word translations by aligning independently trained word embeddings in two languages. Existing approaches generally focus on minimizing the distances between words in the aligned pairs, while suffering from low discriminative capability to distinguish the relative orders between positive and negative candidates. In addition, the mapping function is globally shared by all words, whose performance might be hindered by the deviations in the distributions of different languages. In this work, we propose a novel ranking-oriented induction model RAPO to learn personalized mapping function for each word. RAPO is capable of enjoying the merits from the unique characteristics of a single word and the cross-language isomorphism simultaneously. Extensive experimental results on public datasets including both rich-resource and low-resource languages demonstrate the superiority of our proposal. Our code is publicly available in https://github.com/Jlfj345wf/RAPO.

Recently, powerful Transformer architectures have proven superior in generating high-quality sentences. Nevertheless, these models tend to produce dull high-frequency phrases, severely hurting the diversity and novelty of generated text. In this work, we dig into the intrinsic mechanism of this problem and found that sparser attention values in Transformer could improve diversity. To understand such a phenomenon, we first conduct both empirical and theoretical analysis and then attribute it to representation degeneration caused by the attentive mixture of the hidden states during training. We term this process the Trap of Mediocrity. To escape from such a trap, we introduce a novel attention regularization loss to control the sharpness of the attention distribution, which is transparent to model structures and can be easily implemented within 20 lines of python code. We prove that this method could be mathematically regarded as learning a Bayesian approximation of posterior attention. Experiments show that our method improved the diversity and novelty of the generated text while maintaining comparable quality on a variety of conditional and unconditional generation tasks.

News recommendation is critical for personalized news access. Most existing news recommendation methods rely on centralized storage of users’ historical news click behavior data, which may lead to privacy concerns and hazards. Federated Learning is a privacy-preserving framework for multiple clients to collaboratively train models without sharing their private data. However, the computation and communication cost of directly learning many existing news recommendation models in a federated way are unacceptable for user clients. In this paper, we propose an efficient federated learning framework for privacy-preserving news recommendation. Instead of training and communicating the whole model, we decompose the news recommendation model into a large news model maintained in the server and a light-weight user model shared on both server and clients, where news representations and user model are communicated between server and clients. More specifically, the clients request the user model and news representations from the server, and send their locally computed gradients to the server for aggregation. The server updates its global user model with the aggregated gradients, and further updates its news model to infer updated news representations. Since the local gradients may contain private information, we propose a secure aggregation method to aggregate gradients in a privacy-preserving way. Experiments on two real-world datasets show that our method can reduce the computation and communication cost on clients while keep promising model performance.

Product quantization (PQ) is a widely used technique for ad-hoc retrieval. Recent studies propose supervised PQ, where the embedding and quantization models can be jointly trained with supervised learning. However, there is a lack of appropriate formulation of the joint training objective; thus, the improvements over previous non-supervised baselines are limited in reality. In this work, we propose the Matching-oriented Product Quantization (MoPQ), where a novel objective Multinoulli Contrastive Loss (MCL) is formulated. With the minimization of MCL, we are able to maximize the matching probability of query and ground-truth key, which contributes to the optimal retrieval accuracy. Given that the exact computation of MCL is intractable due to the demand of vast contrastive samples, we further propose the Differentiable Cross-device Sampling (DCS), which significantly augments the contrastive samples for precise approximation of MCL. We conduct extensive experimental studies on four real-world datasets, whose results verify the effectiveness of MoPQ. The code is available at https://github.com/microsoft/MoPQ.

News recommendation techniques can help users on news platforms obtain their preferred news information. Most existing news recommendation methods rely on centrally stored user behavior data to train models and serve users. However, user data is usually highly privacy-sensitive, and centrally storing them in the news platform may raise privacy concerns and risks. In this paper, we propose a unified news recommendation framework, which can utilize user data locally stored in user clients to train models and serve users in a privacy-preserving way. Following a widely used paradigm in real-world recommender systems, our framework contains a stage for candidate news generation (i.e., recall) and a stage for candidate news ranking (i.e., ranking). At the recall stage, each client locally learns multiple interest representations from clicked news to comprehensively model user interests. These representations are uploaded to the server to recall candidate news from a large news pool, which are further distributed to the user client at the ranking stage for personalized news display. In addition, we propose an interest decomposer-aggregator method with perturbation noise to better protect private user information encoded in user interest representations. Besides, we collaboratively train both recall and ranking models on the data decentralized in a large number of user clients in a privacy-preserving way. Experiments on two real-world news datasets show that our method can outperform baseline methods and effectively protect user privacy.

Recently, sponsored search has become one of the most lucrative channels for marketing. As the fundamental basis of sponsored search, relevance modeling has attracted increasing attention due to the tremendous practical value. Most existing methods solely rely on the query-keyword pairs. However, keywords are usually short texts with scarce semantic information, which may not precisely reflect the underlying advertising intents. In this paper, we investigate the novel problem of advertiser-aware relevance modeling, which leverages the advertisers’ information to bridge the gap between the search intents and advertising purposes. Our motivation lies in incorporating the unsupervised bidding behaviors as the complementary graphs to learn desirable advertiser representations. We further propose a Bidding-Graph augmented Triple-based Relevance model BGTR with three towers to deeply fuse the bidding graphs and semantic textual data. Empirically, we evaluate the BGTR model over a large industry dataset, and the experimental results consistently demonstrate its superiority.

In this paper, we formulate the personalized news headline generation problem whose goal is to output a user-specific title based on both a user’s reading interests and a candidate news body to be exposed to her. To build up a benchmark for this problem, we publicize a large-scale dataset named PENS (PErsonalized News headlineS). The training set is collected from user impressions logs of Microsoft News, and the test set is manually created by hundreds of native speakers to enable a fair testbed for evaluating models in an offline mode. We propose a generic framework as a preparatory solution to our problem. At its heart, user preference is learned by leveraging the user behavioral data, and three kinds of user preference injections are proposed to personalize a text generator and establish personalized headlines. We investigate our dataset by implementing several state-of-the-art user modeling methods in our framework to demonstrate a benchmark score for the proposed dataset. The dataset is available at https://msnews.github.io/pens.html.

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.

News recommendation aims to display news articles to users based on their personal interest. Existing news recommendation methods rely on centralized storage of user behavior data for model training, which may lead to privacy concerns and risks due to the privacy-sensitive nature of user behaviors. In this paper, we propose a privacy-preserving method for news recommendation model training based on federated learning, where the user behavior data is locally stored on user devices. Our method can leverage the useful information in the behaviors of massive number users to train accurate news recommendation models and meanwhile remove the need of centralized storage of them. More specifically, on each user device we keep a local copy of the news recommendation model, and compute gradients of the local model based on the user behaviors in this device. The local gradients from a group of randomly selected users are uploaded to server, which are further aggregated to update the global model in the server. Since the model gradients may contain some implicit private information, we apply local differential privacy (LDP) to them before uploading for better privacy protection. The updated global model is then distributed to each user device for local model update. We repeat this process for multiple rounds. Extensive experiments on a real-world dataset show the effectiveness of our method in news recommendation model training with privacy protection.

User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pre-train user models from large-scale unlabeled user behaviors data. We propose two self-supervision tasks for user model pre-training. The first one is masked behavior prediction, which can model the relatedness between historical behaviors. The second one is next K behavior prediction, which can model the relatedness between past and future behaviors. The pre-trained user models are finetuned in downstream tasks to learn task-specific user representations. Experimental results on two real-world datasets validate the effectiveness of our proposed user model pre-training method.

Personalized news recommendation is a critical technology to improve users’ online news reading experience. The core of news recommendation is accurate matching between user’s interests and candidate news. The same user usually has diverse interests that are reflected in different news she has browsed. Meanwhile, important semantic features of news are implied in text segments of different granularities. Existing studies generally represent each user as a single vector and then match the candidate news vector, which may lose fine-grained information for recommendation. In this paper, we propose FIM, a Fine-grained Interest Matching method for neural news recommendation. Instead of aggregating user’s all historical browsed news into a unified vector, we hierarchically construct multi-level representations for each news via stacked dilated convolutions. Then we perform fine-grained matching between segment pairs of each browsed news and the candidate news at each semantic level. High-order salient signals are then identified by resembling the hierarchy of image recognition for final click prediction. Extensive experiments on a real-world dataset from MSN news validate the effectiveness of our model on news recommendation.

News recommendation is an important technique for personalized news service. Compared with product and movie recommendations which have been comprehensively studied, the research on news recommendation is much more limited, mainly due to the lack of a high-quality benchmark dataset. In this paper, we present a large-scale dataset named MIND for news recommendation. Constructed from the user click logs of Microsoft News, MIND contains 1 million users and more than 160k English news articles, each of which has rich textual content such as title, abstract and body. We demonstrate MIND a good testbed for news recommendation through a comparative study of several state-of-the-art news recommendation methods which are originally developed on different proprietary datasets. Our results show the performance of news recommendation highly relies on the quality of news content understanding and user interest modeling. Many natural language processing techniques such as effective text representation methods and pre-trained language models can effectively improve the performance of news recommendation. The MIND dataset will be available at https://msnews.github.io.

With the explosion of news information, personalized news recommendation has become very important for users to quickly find their interested contents. Most existing methods usually learn the representations of users and news from news contents for recommendation. However, they seldom consider high-order connectivity underlying the user-news interactions. Moreover, existing methods failed to disentangle a user’s latent preference factors which cause her clicks on different news. In this paper, we model the user-news interactions as a bipartite graph and propose a novel Graph Neural News Recommendation model with Unsupervised Preference Disentanglement, named GNUD. Our model can encode high-order relationships into user and news representations by information propagation along the graph. Furthermore, the learned representations are disentangled with latent preference factors by a neighborhood routing algorithm, which can enhance expressiveness and interpretability. A preference regularizer is also designed to force each disentangled subspace to independently reflect an isolated preference, improving the quality of the disentangled representations. Experimental results on real-world news datasets demonstrate that our proposed model can effectively improve the performance of news recommendation and outperform state-of-the-art news recommendation methods.

Personalized news recommendation is important to help users find their interested news and improve reading experience. A key problem in news recommendation is learning accurate user representations to capture their interests. Users usually have both long-term preferences and short-term interests. However, existing news recommendation methods usually learn single representations of users, which may be insufficient. In this paper, we propose a neural news recommendation approach which can learn both long- and short-term user representations. The core of our approach is a news encoder and a user encoder. In the news encoder, we learn representations of news from their titles and topic categories, and use attention network to select important words. In the user encoder, we propose to learn long-term user representations from the embeddings of their IDs.In addition, we propose to learn short-term user representations from their recently browsed news via GRU network. Besides, we propose two methods to combine long-term and short-term user representations. The first one is using the long-term user representation to initialize the hidden state of the GRU network in short-term user representation. The second one is concatenating both long- and short-term user representations as a unified user vector. Extensive experiments on a real-world dataset show our approach can effectively improve the performance of neural news recommendation.

News recommendation can help users find interested news and alleviate information overload. The topic information of news is critical for learning accurate news and user representations for news recommendation. However, it is not considered in many existing news recommendation methods. In this paper, we propose a neural news recommendation approach with topic-aware news representations. The core of our approach is a topic-aware news encoder and a user encoder. In the news encoder we learn representations of news from their titles via CNN networks and apply attention networks to select important words. In addition, we propose to learn topic-aware news representations by jointly training the news encoder with an auxiliary topic classification task. In the user encoder we learn the representations of users from their browsed news and use attention networks to select informative news for user representation learning. Extensive experiments on a real-world dataset validate the effectiveness of our approach.

Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence and is usually modeled as a sequence labeling problem. However, sequence labeling based methods cannot make full use of the overall meaning of the whole sentence and have the limitation in processing dependencies between labels. To tackle these problems, we first explore to formalize ATE as a sequence-to-sequence (Seq2Seq) learning task where the source sequence and target sequence are composed of words and labels respectively. At the same time, to make Seq2Seq learning suit to ATE where labels correspond to words one by one, we design the gated unit networks to incorporate corresponding word representation into the decoder, and position-aware attention to pay more attention to the adjacent words of a target word. The experimental results on two datasets show that Seq2Seq learning is effective in ATE accompanied with our proposed gated unit networks and position-aware attention mechanism.

News recommendation is important for online news platforms to help users find interested news and alleviate information overload. Existing news recommendation methods usually rely on the news click history to model user interest. However, these methods may suffer from the data sparsity problem, since the news click behaviors of many users in online news platforms are usually very limited. Fortunately, some other kinds of user behaviors such as webpage browsing and search queries can also provide useful clues of users’ news reading interest. In this paper, we propose a neural news recommendation approach which can exploit heterogeneous user behaviors. Our approach contains two major modules, i.e., news representation and user representation. In the news representation module, we learn representations of news from their titles via CNN networks, and apply attention networks to select important words. In the user representation module, we propose an attentive multi-view learning framework to learn unified representations of users from their heterogeneous behaviors such as search queries, clicked news and browsed webpages. In addition, we use word- and record-level attentions to select informative words and behavior records. Experiments on a real-world dataset validate the effectiveness of our approach.

User and item representation learning is critical for recommendation. Many of existing recommendation methods learn representations of users and items based on their ratings and reviews. However, the user-user and item-item relatedness are usually not considered in these methods, which may be insufficient. In this paper, we propose a neural recommendation approach which can utilize useful information from both review content and user-item graphs. Since reviews and graphs have different characteristics, we propose to use a multi-view learning framework to incorporate them as different views. In the review content-view, we propose to use a hierarchical model to first learn sentence representations from words, then learn review representations from sentences, and finally learn user/item representations from reviews. In addition, we propose to incorporate a three-level attention network into this view to select important words, sentences and reviews for learning informative user and item representations. In the graph-view, we propose a hierarchical graph neural network to jointly model the user-item, user-user and item-item relatedness by capturing the first- and second-order interactions between users and items in the user-item graph. In addition, we apply attention mechanism to model the importance of these interactions to learn informative user and item representations. Extensive experiments on four benchmark datasets validate the effectiveness of our approach.

News recommendation can help users find interested news and alleviate information overload. Precisely modeling news and users is critical for news recommendation, and capturing the contexts of words and news is important to learn news and user representations. In this paper, we propose a neural news recommendation approach with multi-head self-attention (NRMS). The core of our approach is a news encoder and a user encoder. In the news encoder, we use multi-head self-attentions to learn news representations from news titles by modeling the interactions between words. In the user encoder, we learn representations of users from their browsed news and use multi-head self-attention to capture the relatedness between the news. Besides, we apply additive attention to learn more informative news and user representations by selecting important words and news. Experiments on a real-world dataset validate the effectiveness and efficiency of our approach.

Recent years have witnessed a surge of interest on response generation for neural conversation systems. Most existing models are implemented by following the Encoder-Decoder framework and operate sentences of conversations at word-level. The word-level model is suffering from the Unknown Words Issue and the Preference Issue, which seriously impact the quality of generated responses, for example, generated responses may become irrelevant or too general (i.e. safe responses). To address these issues, this paper proposes a hybrid-level Encoder-Decoder model (HL-EncDec), which not only utilizes the word-level features but also character-level features. We conduct several experiments to evaluate HL-EncDec on a Chinese corpus, experimental results show our model significantly outperforms other non-word-level models in automatic metrics and human annotations and is able to generate more informative responses. We also conduct experiments with a small-scale English dataset to show the generalization ability.

This paper describes our system for the first and third shared tasks of the third Social Media Mining for Health Applications (SMM4H) workshop, which aims to detect the tweets mentioning drug names and adverse drug reactions. In our system we propose a neural approach with hierarchical tweet representation and multi-head self-attention (HTR-MSA) for both tasks. Our system achieved the first place in both the first and third shared tasks of SMM4H with an F-score of 91.83% and 52.20% respectively.