Generating syntactically and semantically valid and relevant questions from paragraphs is useful with many applications. Manual generation is a labour-intensive task, as it requires the reading, parsing and understanding of long passages of text. A number of question generation models based on sequence-to-sequence techniques have recently been proposed. Most of them generate questions from sentences only, and none of them is publicly available as an easy-to-use service. In this paper, we demonstrate ParaQG, a Web-based system for generating questions from sentences and paragraphs. ParaQG incorporates a number of novel functionalities to make the question generation process user-friendly. It provides an interactive interface for a user to select answers with visual insights on generation of questions. It also employs various faceted views to group similar questions as well as filtering techniques to eliminate unanswerable questions
Automatic question generation (QG) is a challenging problem in natural language understanding. QG systems are typically built assuming access to a large number of training instances where each instance is a question and its corresponding answer. For a new language, such training instances are hard to obtain making the QG problem even more challenging. Using this as our motivation, we study the reuse of an available large QG dataset in a secondary language (e.g. English) to learn a QG model for a primary language (e.g. Hindi) of interest. For the primary language, we assume access to a large amount of monolingual text but only a small QG dataset. We propose a cross-lingual QG model which uses the following training regime: (i) Unsupervised pretraining of language models in both primary and secondary languages and (ii) joint supervised training for QG in both languages. We demonstrate the efficacy of our proposed approach using two different primary languages, Hindi and Chinese. We also create and release a new question answering dataset for Hindi consisting of 6555 sentences.
Automatic question generation (QG) is a useful yet challenging task in NLP. Recent neural network-based approaches represent the state-of-the-art in this task, but they are not without shortcomings. Firstly, these models lack the ability to handle rare words and the word repetition problem. Moreover, all previous works optimize the cross-entropy loss, which can induce inconsistencies between training (objective) and testing (evaluation measure). In this paper, we present a novel deep reinforcement learning based framework for automatic question generation. The generator of the framework is a sequence-to-sequence model, enhanced with the copy mechanism to handle the rare-words problem and the coverage mechanism to solve the word repetition problem. The evaluator model of the framework evaluates and assigns a reward to each predicted question. The overall model is trained by learning the parameters of the generator network which maximizes the reward. Our framework allows us to directly optimize any task-specific score including evaluation measures such as BLEU, GLEU, ROUGE-L, {\em etc.}, suitable for sequence to sequence tasks such as QG. Our comprehensive evaluation shows that our approach significantly outperforms state-of-the-art systems on the widely-used SQuAD benchmark in both automatic and human evaluation.
Neural network-based methods represent the state-of-the-art in question generation from text. Existing work focuses on generating only questions from text without concerning itself with answer generation. Moreover, our analysis shows that handling rare words and generating the most appropriate question given a candidate answer are still challenges facing existing approaches. We present a novel two-stage process to generate question-answer pairs from the text. For the first stage, we present alternatives for encoding the span of the pivotal answer in the sentence using Pointer Networks. In our second stage, we employ sequence to sequence models for question generation, enhanced with rich linguistic features. Finally, global attention and answer encoding are used for generating the question most relevant to the answer. We motivate and linguistically analyze the role of each component in our framework and consider compositions of these. This analysis is supported by extensive experimental evaluations. Using standard evaluation metrics as well as human evaluations, our experimental results validate the significant improvement in the quality of questions generated by our framework over the state-of-the-art. The technique presented here represents another step towards more automated reading comprehension assessment. We also present a live system \footnote{Demo of the system is available at \url{https://www.cse.iitb.ac.in/~vishwajeet/autoqg.html}.} to demonstrate the effectiveness of our approach.
We present the Civique system for emergency detection in urban areas by monitoring micro blogs like Tweets. The system detects emergency related events, and classifies them into appropriate categories like "fire", "accident", "earthquake", etc. We demonstrate our ideas by classifying Twitter posts in real time, visualizing the ongoing event on a map interface and alerting users with options to contact relevant authorities, both online and offline. We evaluate our classifiers for both the steps, i.e., emergency detection and categorization, and obtain F-scores exceeding 70% and 90%, respectively. We demonstrate Civique using a web interface and on an Android application, in realtime, and show its use for both tweet detection and visualization.