Search

Most Twitter search systems generally treat a tweet as a plain text when modeling relevance. However, a series of conventions allows users to tweet in structural ways using combination of different blocks of texts.These blocks include plain texts, hashtags, links, mentions, etc. Each block encodes a variety of communicative intent and sequence of these blocks captures changing discourse. Previous work shows that exploiting the structural information can improve the structured document (e.g., web pages) retrieval. In this paper we utilize the structure of tweets, induced by these blocks, for Twitter retrieval. A set of features, derived from the blocks of text and their combinations, is used into a learning-to-rank scenario. We show that structuring tweets can achieve state-of-the-art performance. Our approach does not rely upon social media features, but when we do add this additional information, performance improves significantly.

We consider the problem of finding opinionated tweets about a given topic. We automatically construct opinionated lexica from sets of tweets matching specific patterns indicative of opinionated messages. When incorporated into a learning-to-rank approach, results show that this automatically opinionated information yields retrieval performance comparable with a manual method. Finally, topic-related specific structured tweet sets can help improve query-dependent opinion retrieval.

Charge prediction which aims to determine appropriate charges for criminal cases based on textual fact descriptions, is an important technology in the field of AI&Law. Previous works focus on improving prediction accuracy, ignoring the interpretability, which limits the methods’ applicability. In this work, we propose a deep neural framework to extract short but charge-decisive text snippets – rationales – from input fact description, as the interpretation of charge prediction. To solve the scarcity problem ofrationale annotatedcorpus, rationalesare extractedinareinforcement stylewiththe only supervision in the form of charge labels. We further propose a dynamic rationale attention mechanism to better utilize the information in extracted rationales and predict the charges. Experimental results show that besides providing charge prediction interpretation, our approach can also capture subtle details to help charge prediction.

In this paper, we focus on the task of automatic argument quality assessment. Prior empirical methods largely ignore the syntax structure in one argument or depend on handcrafted features that have shallow representation ability. In contrast, we proposed a method that directly models syntax and topic coherence. Our method can acquire both topic coherence and syntactic information from an argument that explicitly utilizes various types of relationships among words, thus can help with argument quality assessment. Experimental results suggest that our method significantly outperforms the previous state-of-the-art method and strongly indicates syntax and coherence correlate with argument quality.

We study the task of on-line scientific resource profiling, which aims at better understanding and summarizing on-line scientific resources to promote resource search and recommendation systems. To this end we propose to exploit the resource citation information in scientific literature by extracting the fine-grained relations between the cited on-line resources and other resource-related scientific terms. In this paper we create a dataset (SciResTR) and develop a framework (SciResTR-IE) which jointly extracts all the related scientific terms and the resource-term relations. Extensive experiments demonstrate that our framework outperforms other baselines significantly, by around 5% in scientific information extraction tasks absolutely. We further show that our proposed system can automatically construct several on-line-resource-centered networks from a large corpus of scientific articles, which is a first step towards utilizing resource citation information in the literature to improve on-line scientific resource profiling.

Knowledge base provides a potential way to improve the intelligence of information retrieval (IR) systems, for that knowledge base has numerous relations between entities which can help the IR systems to conduct inference from one entity to another entity. Relation extraction is one of the fundamental techniques to construct a knowledge base. Distant supervision is a semi-supervised learning method for relation extraction which learns with labeled and unlabeled data. However, this approach suffers the problem of relation overlapping in which one entity tuple may have multiple relation facts. We believe that relation types can have latent connections, which we call class ties, and can be exploited to enhance relation extraction. However, this property between relation classes has not been fully explored before. In this paper, to exploit class ties between relations to improve relation extraction, we propose a general ranking based multi-label learning framework combined with convolutional neural networks, in which ranking based loss functions with regularization technique are introduced to learn the latent connections between relations. Furthermore, to deal with the problem of class imbalance in distant supervision relation extraction, we further adopt cost-sensitive learning to rescale the costs from the positive and negative labels. Extensive experiments on a widely used dataset show the effectiveness of our model to exploit class ties and to relieve class imbalance problem., Preprint submitted to Journal of Information Processing and Management. arXiv admin note: text overlap with arXiv:1612.07602

In this paper, we introduce the task of resource citation classification for scientific literature using a context-based framework. This task is to analyze the purpose of citing an on-line resource in scientific text by modeling the role and function of each resource citation. It can be incorporated into resource indexing and recommendation systems to help better understand and classify on-line resources in scientific literature. We propose a new annotation scheme for this task and develop a dataset of 3,088 manually annotated resource citations. We adopt a neural-based model to build the classifiers and apply them on the large ARC dataset to examine the revolution of scientific resources from trends in their function over time.

With the growth in popularity and size of social media, there is an urgent need for systems that can recognize the coreference relation between two event mentions in texts from social media. In existing event coreference resolution research, a rich set of linguistic features derived from pre-existing NLP tools and various knowledge bases is often required. This kind of methods restricts domain scalability and leads to the propagation of errors. In this paper, we present a novel selective expression approach based on event trigger to explore the coreferential relationship in high-volume Twitter texts. Firstly, we exploit a bidirectional Long Short Term Memory (Bi-LSTM) to extract the sentence level and mention level features. Then, to selectively express the essential parts of generated features, we apply a gate on sentence level features. Next, to integrate the time information of event mention pairs, we design an auxiliary feature based on triggers and time attributes of the two event mentions. Finally, all these features are concatenated and fed into a classifier to predict the binary coreference relationship between the event mention pair. To evaluate our method, we publish a new dataset EventCoreOnTweet (ECT)1 that annotates the coreferential relationship between event mentions and event trigger of each event mention. The experimental results demonstrate that our approach achieves significant performance in the ECT dataset.