Abstract

Developers need to comprehend a program before modifying it. In such cases,developers use cues to establish the relevance of a piece of information with a task. Beingfamiliar with different kinds of cues will help the developers to comprehend a programfaster. But unlike the experienced developers, novice developers fail to recognize therelevant cues, because (a) there are many cues and (b) they might be unfamiliar with theartifacts. However, not much is known about the developers’ choice of cue. Hence, weconducted two independent studies to understand the kind of cues used by the developersand how a tool influences their cue selection. First, from our user study on two commoncomprehension tasks, we found that developers actively seek the cues and their cue sourcechoices are similar but task dependent. In our second exploratory study, we investigatedwhether an integrated development environment (IDE) influences a developer’s cuechoices. By observing their interaction history while fixing bugs in Eclipse IDE, we foundthat the IDE’s influence on their cue choices was not statistically significant. Finally, as acase in point, we propose a novel task-specific program summarization approach to aidnovice developers in comprehending an unfamiliar program. Our approach used devel-opers cue choices to synthesize the summaries. A comparison of the synthesized sum-maries with the summaries recorded by the developers shows both had similar content.This promising result encourages us to explore task-specific cue models, which can aidnovice developers to accomplish complex comprehension tasks faster

Abstract

Hate speech detection on Twitter is critical for applications like controversial event extraction, building AI chatterbots, content recommendation, and sentiment analysis. We define this task as being able to classify a tweet as racist, sexist or neither. The complexity of the natural language constructs makes this task very challenging. We perform extensive experiments with multiple deep learning architectures to learn semantic word embeddings to handle this complexity. Our experiments on a benchmark dataset of 16K annotated tweets show that such deep learning methods outperform state-of-the-art char/word n-gram methods by~ 18 F1 points.

Abstract

Scientific article recommendation problem deals with recommending similar scientific articles given a query article. It can be categorized as a content based similarity system. Recent advancements in representation learning methods have proven to be effective in modeling distributed representations in different modalities like images, languages, speech, networks etc. The distributed representations obtained using such techniques in turn can be used to calculate similarities. In this paper, we address the problem of scientific paper recommendation through a novel method which aims to combine multimodal distributed representations, which in this case are: 1. distributed representations of paper's content, and 2. distributed representation of the graph constructed from the bibliographic network. Through experiments we demonstrate that our method outperforms the state-of-the-art distributed representation methods in text and graph, by 29.6% and 20.4%, both in terms of precision and mean-average-precision respectively.

Abstract

Research in analysis of microblogging platforms is experiencing a renewed surge with a large number of works applying representation learning models for applications like sentiment analysis, semantic textual similarity computation, hashtag prediction, etc. Although the performance of the representation learning models has been better than the traditional baselines for such tasks, little is known about the elementary properties of a tweet encoded within these representations, or why particular representations work better for certain tasks. Our work presented here constitutes the first step in opening the black-box of vector embeddings for tweets.

Abstract

Inferring trust relations between social media users is critical for a number of applications wherein users seek credible information. The fact that available trust relations are scarce and skewed makes trust prediction a challenging task. To the best of our knowledge, this is the first work on exploring representation learning for trust prediction. We propose an approach that uses only a small amount of binary user-user trust relations to simultaneously learn user embeddings and a model to predict trust between user pairs. We empirically demonstrate that for trust prediction, our approach outperforms classifier-based approaches which use state-of-the-art representation learning methods like DeepWalk and LINE as features. We also conduct experiments which use embeddings pre-trained with DeepWalk and LINE each as an input to our model, resulting in further performance improvement. Experiments with a dataset of ~356K user pairs show that the proposed method can obtain a high F-score of 92.65%.

Abstract

Identifying medical persona from a social media post is of paramount importance for drug marketing and pharmacovigilance. In this work, we propose multiple approaches to infer the medical persona associated with a social media post. We pose this as a supervised multi-label text classification problem. The main challenge is to identify the hidden cues in a post that are indicative of a particular persona. We first propose a large set of manually engineered features for this task. Further, we propose multiple neural network based architectures to extract useful features from these posts using pre-trained word embeddings. Our experiments on thousands of blogs and tweets show that the proposed approach results in 7% and 5% gain in F-measure over manual feature engineering based approach for blogs and tweets respectively.

Abstract

Deep neural networks have yielded immense success in speech recognition, computer vision and natural language processing. However, the exploration of deep neural networks for recommender systems has received a relatively little introspection. Also, different recommendation scenarios have their own issues which creates the need for different approaches for recommendation. Specifically in news recommendation a major problem is that of varying user interests. In this work, we use deep neural networks with attention to tackle the problem of news recommendation. The key factor in user-item based collaborative filtering is to identify the interaction between user and item features. Matrix factorization is one of the most common approaches for identifying this interaction. It maps both the users and the items into a joint latent factor space such that user-item interactions in that space can be modeled as inner products in that space. Some recent work has used deep neural networks with the motive to learn an arbitrary function instead of the inner product that is used for capturing the user-item interaction. However, directly adapting it for the news domain does not seem to be very suitable. This is because of the dynamic nature of news readership where the interests of the users keep changing with time. Hence, it becomes challenging for recommendation systems to model both user preferences as well as account for the interests which keep changing over time. We present a deep neural model, where a non-linear mapping of users and item features are learnt first. For learning a non-linear mapping for the users we use an attention-based recurrent t layer in combination with fully connected layers. For learning the mappings for the items we use only fully connected layers. We then use a ranking based objective function to learn the parameters of the network. We also use the content of the news articles as features for our model. Extensive experiments on a real-world dataset show a significant improvement of our proposed model over the state-of-the-art by 4.7% (Hit Ratio@10). Along with this, we also show the effectiveness of our model to handle the user cold-start and item cold-start problems.

Abstract

Existing work for abstractive multidocument summarization utilise existing phrase structures directly extracted from input documents to generate summary sentences. These methods can suffer from lack of consistence and coherence in merging phrases. We introduce a novel approach for abstractive multidocument summarization through partial dependency tree extraction, recombination and linearization. The method entrusts the summarizer to generate its own topically coherent sequential structures from scratch for effective communication. Results on TAC 2011, DUC-2004 and 2005 show that our system gives competitive results compared with state of the art abstractive summarization approaches in the literature. We also achieve competitive results in linguistic quality assessed by human evaluators.

Abstract

Ideally a metric evaluating an abstract system summary should represent the extent to which the system-generated summary approximates the semantic inference conceived by the reader using a human-written reference summary. Most of the previous approaches relied upon word or syntactic sub-sequence overlap to evaluate system-generated summaries. Such metrics cannot evaluate the summary at semantic inference level. Through this work we introduce the metric of Semantic Similarity for Abstractive Summarization (SSAS), which leverages natural language inference and paraphrasing techniques to frame a novel approach to evaluate system summaries at semantic inference level. SSAS is based upon a weighted composition of quantities representing the level of agreement, contradiction, independence, paraphrasing, and optionally ROUGE score between a system-generated and a human-written summary.

Abstract

Extractive text summarization has been an extensive research problem in the field of natural language understanding. While the conventional approaches rely mostly on manually compiled features to generate the summary, few attempts have been made in developing data-driven systems for extractive summarization. To this end, we present a fully data-driven end-to-end deep network which we call as Hybrid MemNet for single document summarization task. The network learns the continuous unified representation of a document before generating its summary. It jointly captures local and global sentential information along with the notion of summary worthy sentences. Experimental results on two different corpora confirm that our model shows significant performance gains compared with the state-of-the-art baselines