Knowledge editing techniques, aiming to efficiently modify a minor proportion of knowledge in large language models (LLMs) without negatively impacting performance across other inputs, have garnered widespread attention. However, existing methods predominantly rely on memorizing the updated knowledge, impeding LLMs from effectively combining the new knowledge with their inherent knowledge when answering questions. To this end, we propose a Learning to Edit (LTE) framework, focusing on teaching LLMs to apply updated knowledge into input questions, inspired by the philosophy of “Teach a man to fish.” LTE features a two-phase process: (i) the Alignment Phase, which fine-tunes LLMs on a meticulously curated parallel dataset to make reliable, in-scope edits while preserving out-of-scope information and linguistic proficiency; and (ii) the Inference Phase, which employs a retrieval-based mechanism for real-time and mass knowledge editing. By comparing our approach with seven advanced baselines across four popular knowledge editing benchmarks and two LLM architectures, we demonstrate LTE’s superiority in knowledge editing performance, robustness in both batch and sequential editing, minimal interference on general tasks, and rapid editing speeds. The data and code are publicly available at https://github.com/YJiangcm/LTE.

Effectively finetuning pretrained language models (PLMs) is critical for their success in downstream tasks. However, PLMs may have risks in overfitting the pretraining tasks and data, which usually have gap with the target downstream tasks. Such gap may be difficult for existing PLM finetuning methods to overcome and lead to suboptimal performance. In this paper, we propose a very simple yet effective method named NoisyTune to help better finetune PLMs on downstream tasks by adding some noise to the parameters of PLMs before fine-tuning. More specifically, we propose a matrix-wise perturbing method which adds different uniform noises to different parameter matrices based on their standard deviations. In this way, the varied characteristics of different types of parameters in PLMs can be considered. Extensive experiments on both GLUE English benchmark and XTREME multilingual benchmark show NoisyTune can consistently empower the finetuning of different PLMs on different downstream tasks.

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.

News recommendation is a widely adopted technique to provide personalized news feeds for the user. Recently, pre-trained language models (PLMs) have demonstrated the great capability of natural language understanding and benefited news recommendation via improving news modeling. However, most existing works simply finetune the PLM with the news recommendation task, which may suffer from the known domain shift problem between the pre-training corpus and downstream news texts. Moreover, PLMs usually contain a large volume of parameters and have high computational overhead, which imposes a great burden on low-latency online services. In this paper, we propose Tiny-NewsRec, which can improve both the effectiveness and the efficiency of PLM-based news recommendation. We first design a self-supervised domain-specific post-training method to better adapt the general PLM to the news domain with a contrastive matching task between news titles and news bodies. We further propose a two-stage knowledge distillation method to improve the efficiency of the large PLM-based news recommendation model while maintaining its performance. Multiple teacher models originated from different time steps of our post-training procedure are used to transfer comprehensive knowledge to the student model in both its post-training stage and finetuning stage. Extensive experiments on two real-world datasets validate the effectiveness and efficiency of our method.

Recall and ranking are two critical steps in personalized news recommendation. Most existing news recommender systems conduct personalized news recall and ranking separately with different models. However, maintaining multiple models leads to high computational cost and poses great challenges to meeting the online latency requirement of news recommender systems. In order to handle this problem, in this paper we propose UniRec, a unified method for recall and ranking in news recommendation. In our method, we first infer user embedding for ranking from the historical news click behaviors of a user using a user encoder model. Then we derive the user embedding for recall from the obtained user embedding for ranking by using it as the attention query to select a set of basis user embeddings which encode different general user interests and synthesize them into a user embedding for recall. The extensive experiments on benchmark dataset demonstrate that our method can improve both efficiency and effectiveness for recall and ranking in news recommendation.

Click behaviors are widely used for learning news recommendation models, but they are heavily affected by the biases brought by the news display positions. It is important to remove position biases to train unbiased recommendation model and capture unbiased user interest. In this paper, we propose a news recommendation method named DebiasGAN that can effectively alleviate position biases via adversarial learning. The core idea is modeling the personalized effect of position bias on click behaviors in a candidate-aware way, and learning debiased candidate-aware user embeddings from which the position information cannot be discriminated. More specifically, we use a bias-aware click model to capture the effect of position bias on click behaviors, and use a bias-invariant click model with random candidate positions to estimate the ideally unbiased click scores. We apply adversarial learning to the embeddings learned by the two models to help the bias-invariant click model capture debiased user interest. Experimental results on two real-world datasets show that DebiasGAN effectively improves news recommendation by eliminating position biases.

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.

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.

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.

Transformer has achieved great success in the NLP field by composing various advanced models like BERT and GPT. However, Transformer and its existing variants may not be optimal in capturing token distances because the position or distance embeddings used by these methods usually cannot keep the precise information of real distances, which may not be beneficial for modeling the orders and relations of contexts. In this paper, we propose DA-Transformer, which is a distance-aware Transformer that can exploit the real distance. We propose to incorporate the real distances between tokens to re-scale the raw self-attention weights, which are computed by the relevance between attention query and key. Concretely, in different self-attention heads the relative distance between each pair of tokens is weighted by different learnable parameters, which control the different preferences on long- or short-term information of these heads. Since the raw weighted real distances may not be optimal for adjusting self-attention weights, we propose a learnable sigmoid function to map them into re-scaled coefficients that have proper ranges. We first clip the raw self-attention weights via the ReLU function to keep non-negativity and introduce sparsity, and then multiply them with the re-scaled coefficients to encode real distance information into self-attention. Extensive experiments on five benchmark datasets show that DA-Transformer can effectively improve the performance of many tasks and outperform the vanilla Transformer and its several variants.

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.

Pre-trained language models (PLMs) like BERT have made great progress in NLP. News articles usually contain rich textual information, and PLMs have the potentials to enhance news text modeling for various intelligent news applications like news recommendation and retrieval. However, most existing PLMs are in huge size with hundreds of millions of parameters. Many online news applications need to serve millions of users with low latency tolerance, which poses great challenges to incorporating PLMs in these scenarios. Knowledge distillation techniques can compress a large PLM into a much smaller one and meanwhile keeps good performance. However, existing language models are pre-trained and distilled on general corpus like Wikipedia, which has gaps with the news domain and may be suboptimal for news intelligence. In this paper, we propose NewsBERT, which can distill PLMs for efficient and effective news intelligence. In our approach, we design a teacher-student joint learning and distillation framework to collaboratively learn both teacher and student models, where the student model can learn from the learning experience of the teacher model. In addition, we propose a momentum distillation method by incorporating the gradients of teacher model into the update of student model to better transfer the knowledge learned by the teacher model. Thorough experiments on two real-world datasets with three tasks show that NewsBERT can empower various intelligent news applications with much smaller models.

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.

Personalized news recommendation is important for online news services. Many news recommendation methods recommend news based on their relevance to users’ historical browsed news, and the recommended news usually have similar sentiment with browsed news. However, if browsed news is dominated by certain kinds of sentiment, the model may intensively recommend news with the same sentiment orientation, making it difficult for users to receive diverse opinions and news events. In this paper, we propose a sentiment diversity-aware neural news recommendation approach, which can recommend news with more diverse sentiment. In our approach, we propose a sentiment-aware news encoder, which is jointly trained with an auxiliary sentiment prediction task, to learn sentiment-aware news representations. We learn user representations from browsed news representations, and compute click scores based on user and candidate news representations. In addition, we propose a sentiment diversity regularization method to penalize the model by combining the overall sentiment orientation of browsed news as well as the click and sentiment scores of candidate news. Extensive experiments on real-world dataset show that our approach can effectively improve the sentiment diversity in news recommendation without performance sacrifice.

Named entity recognition is a critical task in the natural language processing field. Most existing methods for this task can only exploit contextual information within a sentence. However, their performance on recognizing entities in limited or ambiguous sentence-level contexts is usually unsatisfactory. Fortunately, other sentences in the same document can provide supplementary document-level contexts to help recognize these entities. In addition, words themselves contain word-level contextual information since they usually have different preferences of entity type and relative position from named entities. In this paper, we propose a unified framework to incorporate multi-level contexts for named entity recognition. We use TagLM as our basic model to capture sentence-level contexts. To incorporate document-level contexts, we propose to capture interactions between sentences via a multi-head self attention network. To mine word-level contexts, we propose an auxiliary task to predict the type of each word to capture its type preference. We jointly train our model in entity recognition and the auxiliary classification task via multi-task learning. The experimental results on several benchmark datasets validate the effectiveness of our method.

Pooling is an important technique for learning text representations in many neural NLP models. In conventional pooling methods such as average, max and attentive pooling, text representations are weighted summations of the L1 or L∞ norm of input features. However, their pooling norms are always fixed and may not be optimal for learning accurate text representations in different tasks. In addition, in many popular pooling methods such as max and attentive pooling some features may be over-emphasized, while other useful ones are not fully exploited. In this paper, we propose an Attentive Pooling with Learnable Norms (APLN) approach for text representation. Different from existing pooling methods that use a fixed pooling norm, we propose to learn the norm in an end-to-end manner to automatically find the optimal ones for text representation in different tasks. In addition, we propose two methods to ensure the numerical stability of the model training. The first one is scale limiting, which re-scales the input to ensure non-negativity and alleviate the risk of exponential explosion. The second one is re-formulation, which decomposes the exponent operation to avoid computing the real-valued powers of the input and further accelerate the pooling operation. Experimental results on four benchmark datasets show that our approach can effectively improve the performance of attentive pooling.

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.

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.

Named entity recognition (NER) is an important task in the natural language processing field. Existing NER methods heavily rely on labeled data for model training, and their performance on rare entities is usually unsatisfactory. Entity dictionaries can cover many entities including both popular ones and rare ones, and are useful for NER. However, many entity names are context-dependent and it is not optimal to directly apply dictionaries without considering the context. In this paper, we propose a neural NER approach which can exploit dictionary knowledge with contextual information. We propose to learn context-aware dictionary knowledge by modeling the interactions between the entities in dictionaries and their contexts via context-dictionary attention. In addition, we propose an auxiliary term classification task to predict the types of the matched entity names, and jointly train it with the NER model to fuse both contexts and dictionary knowledge into NER. Extensive experiments on the CoNLL-2003 benchmark dataset validate the effectiveness of our approach in exploiting entity dictionaries to improve the performance of various NER models.

Clickbait is a form of web content designed to attract attention and entice users to click on specific hyperlinks. The detection of clickbaits is an important task for online platforms to improve the quality of web content and the satisfaction of users. Clickbait detection is typically formed as a binary classification task based on the title and body of a webpage, and existing methods are mainly based on the content of title and the relevance between title and body. However, these methods ignore the stylistic patterns of titles, which can provide important clues on identifying clickbaits. In addition, they do not consider the interactions between the contexts within title and body, which are very important for measuring their relevance for clickbait detection. In this paper, we propose a clickbait detection approach with style-aware title modeling and co-attention. Specifically, we use Transformers to learn content representations of title and body, and respectively compute two content-based clickbait scores for title and body based on their representations. In addition, we propose to use a character-level Transformer to learn a style-aware title representation by capturing the stylistic patterns of title, and we compute a title stylistic score based on this representation. Besides, we propose to use a co-attention network to model the relatedness between the contexts within title and body, and further enhance their representations by encoding the interaction information. We compute a title-body matching score based on the representations of title and body enhanced by their interactions. The final clickbait score is predicted by a weighted summation of the aforementioned four kinds of scores. Extensive experiments on two benchmark datasets show that our approach can effectively improve the performance of clickbait detection and consistently outperform many baseline methods.

With the development of the Internet, dialog systems are widely used in online platforms to provide personalized services for their users. It is important to understand the emotions through conversations to improve the quality of dialog systems. To facilitate the researches on dialog emotion recognition, the SemEval-2019 Task 3 named EmoContext is proposed. This task aims to classify the emotions of user utterance along with two short turns of dialogues into four categories. In this paper, we propose an attentional LSTM-CNN model to participate in this shared task. We use a combination of convolutional neural networks and long-short term neural networks to capture both local and long-distance contextual information in conversations. In addition, we apply attention mechanism to recognize and attend to important words within conversations. Besides, we propose to use ensemble strategies by combing the variants of our model with different pre-trained word embeddings via weighted voting. Our model achieved 0.7542 micro-F1 score in the final test data, ranking 15ˆth out of 165 teams.

First name: Tao Last name: Qi Email: taoqi.qt@gmail.com Affiliation: Department of Electronic Engineering, Tsinghua University First name: Suyu Last name: Ge Email: gesy17@mails.tsinghua.edu.cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Chuhan Last name: Wu Email: wuch15@mails.tsinghua.edu.cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Yubo Last name: Chen Email: chen-yb18@mails.tsinghua.edu.cn Affiliation: Department of Electronic Engineering, Tsinghua University First name: Yongfeng Last name: Huang Email: yfhuang@mail.tsinghua.edu.cn Affiliation: Department of Electronic Engineering, Tsinghua University Toponym resolution is an important and challenging task in the neural language processing field, and has wide applications such as emergency response and social media geographical event analysis. Toponym resolution can be roughly divided into two independent steps, i.e., toponym detection and toponym disambiguation. In order to facilitate the study on toponym resolution, the SemEval 2019 task 12 is proposed, which contains three subtasks, i.e., toponym detection, toponym disambiguation and toponym resolution. In this paper, we introduce our system that participated in the SemEval 2019 task 12. For toponym detection, in our approach we use TagLM as the basic model, and explore the use of various features in this task, such as word embeddings extracted from pre-trained language models, POS tags and lexical features extracted from dictionaries. For toponym disambiguation, we propose a heuristics rule-based method using toponym frequency and population. Our systems achieved 83.03% strict macro F1, 74.50 strict micro F1, 85.92 overlap macro F1 and 78.47 overlap micro F1 in toponym detection subtask.

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.

Utilizing reviews to learn user and item representations is useful for recommender systems. Existing methods usually merge all reviews from the same user or for the same item into a long document. However, different reviews, sentences and even words usually have different informativeness for modeling users and items. In this paper, we propose a hierarchical user and item representation model with three-tier attention to learn user and item representations from reviews for recommendation. Our model contains three major components, i.e., a sentence encoder to learn sentence representations from words, a review encoder to learn review representations from sentences, and a user/item encoder to learn user/item representations from reviews. In addition, we incorporate a three-tier attention network in our model to select important words, sentences and reviews. Besides, we combine the user and item representations learned from the reviews with user and item embeddings based on IDs as the final representations to capture the latent factors of individual users and items. Extensive experiments on four benchmark datasets validate the effectiveness of our approach.

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.

This paper describes our system for the first and second shared tasks of the fourth Social Media Mining for Health Applications (SMM4H) workshop. We enhance tweet representation with a language model and distinguish the importance of different words with Multi-Head Self-Attention. In addition, transfer learning is exploited to make up for the data shortage. Our system achieved competitive results on both tasks with an F1-score of 0.5718 for task 1 and 0.653 (overlap) / 0.357 (strict) for task 2.

Metaphors are figurative languages widely used in daily life and literatures. It’s an important task to detect the metaphors evoked by texts. Thus, the metaphor shared task is aimed to extract metaphors from plain texts at word level. We propose to use a CNN-LSTM model for this task. Our model combines CNN and LSTM layers to utilize both local and long-range contextual information for identifying metaphorical information. In addition, we compare the performance of the softmax classifier and conditional random field (CRF) for sequential labeling in this task. We also incorporated some additional features such as part of speech (POS) tags and word cluster to improve the performance of model. Our best model achieved 65.06% F-score in the all POS testing subtask and 67.15% in the verbs testing subtask.

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.

Detecting irony is an important task to mine fine-grained information from social web messages. Therefore, the Semeval-2018 task 3 is aimed to detect the ironic tweets (subtask A) and their ironic types (subtask B). In order to address this task, we propose a system based on a densely connected LSTM network with multi-task learning strategy. In our dense LSTM model, each layer will take all outputs from previous layers as input. The last LSTM layer will output the hidden representations of texts, and they will be used in three classification task. In addition, we incorporate several types of features to improve the model performance. Our model achieved an F-score of 70.54 (ranked 2/43) in the subtask A and 49.47 (ranked 3/29) in the subtask B. The experimental results validate the effectiveness of our system.

Traditional sentiment analysis approaches mainly focus on classifying the sentiment polarities or emotion categories of texts. However, they can’t exploit the sentiment intensity information. Therefore, the SemEval-2018 Task 1 is aimed to automatically determine the intensity of emotions or sentiment of tweets to mine fine-grained sentiment information. In order to address this task, we propose a system based on an attention CNN-LSTM model. In our model, LSTM is used to extract the long-term contextual information from texts. We apply attention techniques to selecting this information. A CNN layer with different size of kernels is used to extract local features. The dense layers take the pooled CNN feature maps and predict the intensity scores. Our system reaches average Pearson correlation score of 0.722 (ranked 12/48) in emotion intensity regression task, and 0.810 in valence regression task (ranked 15/38). It indicates that our system can be further extended.

Emojis are widely used by social media and social network users when posting their messages. It is important to study the relationships between messages and emojis. Thus, in SemEval-2018 Task 2 an interesting and challenging task is proposed, i.e., predicting which emojis are evoked by text-based tweets. We propose a residual CNN-LSTM with attention (RCLA) model for this task. Our model combines CNN and LSTM layers to capture both local and long-range contextual information for tweet representation. In addition, attention mechanism is used to select important components. Besides, residual connection is applied to CNN layers to facilitate the training of neural networks. We also incorporated additional features such as POS tags and sentiment features extracted from lexicons. Our model achieved 30.25% macro-averaged F-score in the first subtask (i.e., emoji prediction in English), ranking 7th out of 48 participants.

Existing semantic models are capable of identifying the semantic similarity of words. However, it’s hard for these models to discriminate between a word and another similar word. Thus, the aim of SemEval-2018 Task 10 is to predict whether a word is a discriminative attribute between two concepts. In this task, we apply a multilayer perceptron (MLP)-convolutional neural network (CNN) model to identify whether an attribute is discriminative. The CNNs are used to extract low-level features from the inputs. The MLP takes both the flatten CNN maps and inputs to predict the labels. The evaluation F-score of our system on the test set is 0.629 (ranked 15th), which indicates that our system still needs to be improved. However, the behaviours of our system in our experiments provide useful information, which can help to improve the collective understanding of this novel task.

Predicting valence-arousal ratings for words and phrases is very useful for constructing affective resources for dimensional sentiment analysis. Since the existing valence-arousal resources of Chinese are mainly in word-level and there is a lack of phrase-level ones, the Dimensional Sentiment Analysis for Chinese Phrases (DSAP) task aims to predict the valence-arousal ratings for Chinese affective words and phrases automatically. In this task, we propose an approach using a densely connected LSTM network and word features to identify dimensional sentiment on valence and arousal for words and phrases jointly. We use word embedding as major feature and choose part of speech (POS) and word clusters as additional features to train the dense LSTM network. The evaluation results of our submissions (1st and 2nd in average performance) validate the effectiveness of our system to predict valence and arousal dimensions for Chinese words and phrases.