Abstract

Usage of presuppositions in social media and news discourse can be a powerful way to influence the readers as they usually tend to not examine the truth value of the hidden or indirectly expressed information. Fairclough and Wodak (1997) discuss presupposition at a discourse level where some implicit claims are taken for granted in the explicit meaning of a text or utterance. From the Gricean perspective, the presuppositions of a sentence determine the class of contexts in which the sentence could be felicitously uttered. This paper aims to correlate the type of knowledge presupposed in a news article to the bias present in it. We propose a set of guidelines to identify various kinds of presuppositions in news articles and present a dataset consisting of 1050 articles which are annotated for bias (positive, negative or neutral) and the magnitude of presupposition. We introduce a supervised classification approach for detecting bias in political news which significantly outperforms the existing systems.

Abstract

Sarcasm detection, regarded as one of the subproblems of sentiment analysis, is a very typical task because the introduction of sarcastic words can flip the sentiment of the sentence itself. To date, many research works revolve around detecting sarcasm in one single sentence and there is very limited research to detect sarcasm resulting from multiple sentences. Current models used Long Short Term Memory (Hochreiter and Schmidhuber, 1997) (LSTM) variants with or without attention to detect sarcasm in conversations. We showed that the models using state-of-the-art Bidirectional Encoder Representations from Transformers (Devlin et al., 2018) (BERT), to capture syntactic and semantic information across conversation sentences, performed better than the current models. Based on the data analysis, we estimated that the number of sentences in the conversation that can contribute to the sarcasm and the results agrees to this estimation. We also perform a comparative study of our different versions of BERT-based model with other variants of LSTM model and XLNet (Yang et al., 2019) (both using the estimated number of conversation sentences) and find out that BERT-based models outperformed them.

Abstract

This paper presents a novel approach designed to answer questions on a reading comprehension passage. It is an end-to-end system which first focuses on comprehending the given passage wherein it converts unstructured passage into a structured data and later proceeds to answer the questions related to the passage using solely the aforementioned structured data. To the best of our knowledge, the proposed design is first of its kind which accounts for entire process of comprehending the passage and then answering the questions associated with the passage. The comprehension stage converts the passage into a Discourse Collection that comprises of the relation shared amongst logical sentences in given passage along with the key characteristics of each sentence. This design has its applications in academic domain , query comprehension in speech systems among others.

Abstract

In this paper, a dialogue system for Hospital domain in Telugu, which is a resource-poor Dravidian language, has been built. It handles various hospital and doctor related queries. The main aim of this paper is to present an approach for modelling a dialogue system in a resource-poor language by combining linguistic and domain knowledge. Focusing on the question answering aspect of the dialogue system, we identified Question Classification and Query Processing as the two most important parts of the dialogue system. Our method combines deep learning techniques for question classification and computational rule-based analysis for query processing. Human evaluation of the system has been performed as there is no automated evaluation tool for dialogue systems in Telugu. Our system achieves a high overall rating along with a significantly accurate context-capturing method as shown in the results.

Abstract

In this paper we present our work in building Natural Language Interface to Database (NLIDB) system using Intermediate query approach. This approach is demonstrated using Movie domain chatbot and can also be extended to different domains. The need of NLIDB System has increased in this fast paced world where more number of users are accessing databases through their Smart phones and web browsers. NLIDB System maps user’s Natural Language query to database query allowing user to extract information without any prior experience with databases. Results obtained are very promising and can tackle most of the user queries regarding target database.

Abstract

Estimating the intensity of emotion has gained significance as modern textual inputs in potential applications like social media, eretail markets, psychology, advertisements etc., carry a lot of emotions, feelings, expressions along with its meaning. However, the approaches of traditional sentiment analysis primarily focuses on classifying the sentiment in general (positive or negative) or at an aspect level(very positive, low negative, etc.)and cannot exploit the intensity information. Moreover, automatically identifying emotions like anger, fear, joy, sadness, disgust etc., from text introduces challenging scenarios where single tweet may contain multiple emotions with different intensities and some emotions may even co-occur in some of the tweets. In this paper, we propose an architecture, Experts Model, inspired from the standard Mixture of Experts (MoE) model. The key idea here is each expert learns different sets of features from the feature vector which helps in better emotion detection from the tweet. We compared the results of our Experts Model with both baseline results and top five performers of SemEval-2018 Task-1, Affect in Tweets (AIT). The experimental results show that our proposed approach deals with the emotion detection problem and stands at top-5 results.

Abstract

Social media sites like Facebook, Twitter, and other microblogging forums have emerged as a platform for people to express their opinions and views on different issues and events. It is often observed that people tend to take a stance; in favor, against or neutral towards a particular topic. The task of assessing the stance taken by the individual became significantly important with the emergence in the usage of online social platforms. Automatic stance detection system understands the user’s stance by analyzing the standalone texts against a target entity. Due to the limited contextual information a single sentence provides, it is challenging to solve this task effectively. In this paper, we introduce a Multi-Task Learning (MTL) based deep neural network architecture for automatically detecting stance present in the code-mixed corpus. We apply our approach on Hindi-English code-mixed corpus against the target entity - “Demonetisation.” Our best model achieved the result with a stance prediction accuracy of 63.2% which is a 4.5% overall accuracy improvement compared to the current supervised classification systems developed using the benchmark dataset for code-mixed data stance detection.

Abstract

We propose bilingual word embeddings based on word2vec and fastText models (CBOW and Skip-gram) to address the problem of Humor detection in Hindi-English code-mixed tweets in combination with deep learning architectures. We focus on deep learning approaches which are not widely used on code-mixed data and analyzed their performance by experimenting with three different neural network models. We propose convolution neural network (CNN) and bidirectional long-short term memory (biLSTM) (with and without Attention) models which take the generated bilingual embeddings as input. We make use of Twitter data to create bilingual word embeddings. All our proposed architectures outperform the state-of-the-art results, and Attention based bidirectional LSTM model achieved an accuracy of 73.6% which is an increment of more than 4% compared to the current stateof-the-art results.

Abstract

Hindi question answering systems suffer from a lack of data. To address the same, this paper presents an approach towards automatic question generation. We present a rule-based system for question generation in Hindi by formalizing question transformation methods based on karakadependency theory. We use a Hindi dependency parser to mark the karaka roles and use IndoWordNet a Hindi ontology to detect the semantic category of the karaka role heads to generate the interrogatives. We analyze how one sentence can have multiple generations from the same karaka role’s rule. The generations are manually annotated by multiple annotators on a semantic and syntactic scale for evaluation. Further, we constrain our generation with the help of various semantic and syntactic filters so as to improve the generation quality. Using these methods, we are able to generate diverse questions, significantly more than number of sentences fed to the system.

Abstract

Neural word embeddings have been able to deliver impressive results in many Natural Language Processing tasks. The quality of the word embedding determines the performance of a supervised model. However, choosing the right set of word embeddings for a given dataset is a major challenging task for enhancing the results. In this paper, we have evaluated neural word embeddings on sentiment analysis task in two steps: (i) proposed a mixture of classification experts (MoCE) model for sentiment classification task, (ii) to compare and improve the classification accuracy by different combination of word embedding as first level of features and pass it to cascade model inspired by gcForest for extracting diverse features. We argue that in the first step, each expert learns a certain positive or negative examples corresponding to its category and in the second step resulting features on a given task (polarity identification) can achieve competitive performance with state-ofthe-art methods in terms of accuracy, precision and recall using gcForest.