Abstract

Social media platforms have democratized the publication process resulting into easy and viral propagation of information. However, spread of rumors via such media often results into undesired and extremely impactful political, economic, social, psychological and criminal consequences. Several manual as well as automated efforts have been undertaken in the past to solve this critical problem. Existing automated methods are text based, user credibility based or use signals from the tweet propagation tree. We aim at using the text, user, propagation tree and temporal information jointly for rumor detection on Twitter. This involves several challenges like how to handle text variations on Twitter, what signals from user profile could be useful, how to best encode the propagation tree information, and how to incorporate the temporal signal. Our novel architecture, T 3N (Text and Temporal Tree Network), leverages deep learning based architectures to encode text, user and tree information in a temporal-aware manner. Our extensive comparisons show that our proposed methods outperform the state-of-the-art techniques by ∼7 and ∼6 percent points respectively on two popular benchmark datasets, and also lead to better early detection results.

Abstract

Semantics play an important role when it comes to automated systems using text or language and it is different for different domains. In this paper, we tackle the FinSim 2020 shared task at IJCAIPRICAI 2020. The task deals with designing a semantic model which can automatically classify short phrases/terms from financial domain into the most relevant hypernym (or top-level) concept in an external ontology. We perform several experiments using different kinds of word and phrase level embeddings to solve the problem in an unsupervised manner. We also explore the use of a supplementary financial domain data; either to learn better concept representation or generate more training samples. We discuss both the positive and negative results that we observed while applying these approaches.

Abstract

Identifying adverse and hostile content on the web and more particularly, on social media, has become a problem of paramount interest in recent years. With their ever increasing popularity, fine-tuning of pretrained Transformer-based encoder models with a classifier head are gradually becoming the new baseline for natural language classification tasks. In our work, we explore the gains attributed to Task Adaptive Pretraining (TAPT) prior to fine-tuning of Transformer-based architectures. We specifically study two problems, namely,(a) Coarse binary classification of Hindi Tweets into Hostile or Not, and (b) Fine-grained multi-label classification of Tweets into four categories: hate, fake, offensive, and defamation. Building up on an architecture which takes emojis and segmented hashtags into consideration for classification, we are able to experimentally showcase the performance upgrades due to TAPT. Our system (with team name'iREL IIIT') ranked first in the'Hostile Post Detection in Hindi'shared task with an F1 score of 97.16% for coarse-grained detection and a weighted F1 score of 62.96% for fine-grained multi-label classification on the provided blind test corpora.

Abstract

Detecting and classifying instances of hate in social media text has been a problem of interest in NaturalLanguage Processing in the recent years. Our work leverages state of the art Transformer languagemodels to identify hate speech in a multilingual setting. Capturing the intent of a post or a comment onsocial media involves careful evaluation of the language style, semantic content and additional pointerssuch as hashtags and emojis. In this paper, we look at the problem of identifying whether a Twitterpost is hateful and offensive or not. We further discriminate the detected toxic content into one of thefollowing three classes: (a) Hate Speech (HATE), (b) Offensive (OFFN) and (c) Profane (PRFN). With apre-trained multilingual Transformer-based text encoder at the base, we are able to successfully identifyand classify hate speech from multiple languages. On the provided testing corpora, we achieve MacroF1 scores of 90.29, 81.87 and 75.40 for English, German and Hindi respectively while performing hatespeech detection and of 60.70, 53.28 and 49.74 during fine-grained classification. In our experiments, weshow the efficacy of Perspective API features for hate speech classification and the effects of exploitinga multilingual training scheme. A feature selection study is provided to illustrate impacts of specificfeatures upon the architecture’s classification head.

Abstract

Automatic text summarization has been widely studied as an important task in natural language processing. Traditionally, various feature engineering and machine learning based systems have been proposed for extractive as well as abstractive text summarization. Recently, deep learning based, specifically Transformer-based systems have been immensely popular. Summarization is a cognitively challenging task-extracting summary worthy sentences is laborious, and expressing semantics in brief when doing abstractive summarization is complicated. In this paper, we specifically look at the problem of summarizing scientific research papers from multiple domains. We differentiate between two types of summaries, namely,(a) LaySumm: A very short summary that captures the essence of the research paper in layman terms restricting overtly specific technical jargon and (b) LongSumm: A much longer detailed summary aimed at providing specific insights into various ideas touched upon in the paper. While leveraging latest Transformer-based models, our systems are simple, intuitive and based on how specific paper sections contribute to human summaries of the two types described above. Evaluations against gold standard summaries using ROUGE metrics prove the effectiveness of our approach. On blind test corpora, our system ranks first and third for the LongSumm and LaySumm tasks respectively.

Abstract

Memes are steadily taking over the feeds of the public on social media. There is always the threat of malicious users on the internet posting offensive content, even through memes. Hence, the automatic detection of offensive images/memes is imperative along with detection of offensive text. However, this is a much more complex task as it involves both visual cues as well as language understanding and cultural/context knowledge. This paper describes our approach to the task of SemEval-2020 Task 8: Memotion Analysis. We chose to participate only in Task A which dealt with Sentiment Classification, which we formulated as a text classification problem. Through our experiments, we explored multiple training models to evaluate the performance of simple text classification algorithms on the raw text obtained after running OCR on meme images. Our submitted model achieved an accuracy of 72.69% and exceeded the existing baseline’s Macro F1 score by 8% on the official test dataset. Apart from describing our official submission, we shall elucidate how different classification models respond to this task.

Abstract

With the rise of social networking platforms, everyone now has free access to information from around the work. Anyone from anywhere can now share context with the entire world. This allows for more connectivity around the world and more transparency. However, this also allows for the spread of misinformation and fake news often resulting in undesired and extremely impactful political, economic, social, psychological and criminal consequences. Identifying the fake news spreaders is as important as identifying the fake news itself. We put forward a method to utilize content analysis and more user modelling to capture who is more likely to share fake news. We use TF-IDF as our text transformation method coupled with algorithms simple classification algorithm Logistic Regression and achieve an accuracy of 71.5% and 70% in identifying fake news spreaders in both the English as well as Spanish test set respectively.

Abstract

We consider the task of Medical Concept Normalization (MCN) which aims to map informal medical phrases such as “loosing weight” to formal medical concepts, such as “Weight loss”. Deep learning models have shown high performance across various MCN datasets containing small number of target concepts along with adequate number of training examples per concept. However, scaling these models to millions of medical concepts entails the creation of much larger datasets which is cost and effort intensive. Recent works have shown that training MCN models using automatically labeled examples extracted from medical knowledge bases partially alleviates this problem. We extend this idea by computationally creating a distant dataset from patient discussion forums. We extract informal medical phrases and medical concepts from these forums using a synthetically trained classifier and an off-the-shelf medical entity linker respectively. We use pretrained sentence encoding models to find the k-nearest phrases corresponding to each medical concept. These mappings are used in combination with the examples obtained from medical knowledge bases to train an MCN model. Our approach outperforms the previous state-of-the-art by 15.9% and 17.1% classification accuracy across two datasets while avoiding manual labeling.

Abstract

Automatic text summarization has been widely studied as an important task in natural language processing. Traditionally, various feature engineering and machine learning based systems have been proposed for extractive as well as abstractive text summarization. Recently, deep learning based, specifically Transformer-based systems have been immensely popular. Summarization is a cognitively challenging task–extracting summary worthy sentences is laborious, and expressing semantics in brief when doing abstractive summarization is complicated. In this paper, we specifically look at the problem of summarizing scientific research papers from multiple domains. We differentiate between two types of summaries, namely,(a) LaySumm: A very short summary that captures the essence of the research paper in layman terms restricting overtly specific technical jargon and (b) LongSumm: A much longer detailed summary aimed at providing specific insights into various ideas touched upon in the paper. While leveraging latest Transformer-based models, our systems are simple, intuitive and based on how specific paper sections contribute to human summaries of the two types described above. Evaluations against gold standard summaries using ROUGE (Lin, 2004) metrics prove the effectiveness of our approach. On blind test corpora, our system ranks first and third for the LongSumm and LaySumm tasks respectively.

Abstract

In recent years, the fields of NLP and information retrieval have made tremendous progress thanks to deep learning models like RNNs and LSTMs, and Transformer[35] based models like BERT[9]. But these models are humongous in size. Real world applications however demand small model size, low response times and low computational power wattage. We will discuss six different types of methods (pruning, quantization, knowledge distillation, parameter sharing, matrix decomposition, and other Transformer based methods) for compression of such models to enable their deployment in real industry NLP projects. Given the critical need of building applications with efficient and small models, and the large amount of recently published work in this area, we believe that this tutorial is very timely. We will organize related work done by the 'deep learning for NLP' community in the past few years and present it as a coherent story.