Abstract

Keywords of a document are a representative of its content, and it helps to have meaningful words to facilitate search and organization of documents. Hence, finding methods that can automatically identify keywords in a document is very important as manual processes for this is very cumbersome and error-prone. If this task is accomplished for song lyrics, it has varied applications such as recommendation systems and digital music library management. This work proposes and compares methods to identify keywords from lyrics of Bollywood songs. We use a collection of lyrics of 1055 Bollywood songs, all written in the Devanagari script. Experiments include looking at the spatial distribution of the terms, their occurrence in a certain context or position, and using WordNet to generate keywords not present in the document. Validation was done by human annotators by providing a score to each method based on the results obtained on a subset of the data. We also used Latent Dirichlet Allocation and Latent Semantic Indexing to validate the results, as further explained in the paper.

Abstract

Many methods have been developed for various sentence classification tasks for English, which usually exploit linguistic resources like parsers or rely on the large amount of annotated or unannotated data, making it difficult to adapt them to other languages. In this paper, we present an evaluation of popular deep learning methods for sentence classification on the morphologically rich Indian languages, specifically, Hindi and Telugu. For this purpose, we also created a question classification dataset for Hindi, by translating the TREC-UIUC dataset. We show that character based input can enhance the performance of current classification systems for morphologically rich languages. Finally, we show that our multiInput-CNN variant is able to perform better than our baselines in two out of three tasks in Hindi and Telugu, while giving comparable results for others.

Abstract

Movie ratings play an important role in tasks such as user movie recommendations, verifying the relationship between usersubmitted reviews and ratings etc. The ability to predict the rating of a movie would be useful considering these aspects. In this work, firstly, we propose methods to predict the movie rating based on its summary. We then set out to use priors that are generally available with movie summaries in order to improve the accuracy. In order to achieve this, we consider the associated movie reviews as well while predicting the rating and provide insights on why this helps our models perform better. We use the review based sentiment along with the summary in order to predict the rating more accurately since the sentiment captures a lot of essential information that can aid rating prediction. We experiment with various deep learning architectures and the results show a significant accuracy boost of around 2% in most of the models which show the generalizability of our approach.

Abstract

The paper presents the development of a phonetically balanced read speech corpus of code-mixed Hindi-English. Phonetic balance in the corpus has been created by selecting sentences that contained triphones lower in frequency than a predefined threshold. The assumption with a compulsory inclusion of such rare units was that the high frequency triphones will inevitably be included. Using this metric, the Pearson’s correlation coefficient of the phonetically balanced corpus with a large code-mixed reference corpus was recorded to be 0.996. The data for corpus creation has been extracted from selected sections of Hindi newspapers. These sections contain frequent English insertions in a matrix of Hindi sentence. Statistics on the phone and triphone distribution have been presented, to graphically display the phonetic likeness between the reference corpus and the corpus sampled through our method.

Abstract

Contextual knowledge is the most important element in understanding language. By contextual knowledge we mean both general knowledge and discourse knowledge i.e. knowledge of the situational context, background knowledge and the co-textual context [10]. In this paper, we will discuss the importance of contextual knowledge in understanding the humor present in the cartoon based Amul advertisements in India. In the process, we will analyze these advertisements and also see if humor is an effective tool for advertising and thereby, for marketing. These bilingual advertisements also expect the audience to have the appropriate linguistic knowledge which includes knowledge of English and Hindi vocabulary, morphology and syntax. Different techniques like punning, portmanteaus and parodies of popular proverbs, expressions, acronyms, famous dialogues, songs etc are employed to convey the message in a humorous way. The present study will concentrate on these linguistic cues and the required context for understanding wit and humor.

Abstract

Understanding the polarity or sentiment of a text is an important task in many application scenarios. Sentiment Analysis of a text can be used to answer various questions such as election prediction, favouredness towards any product etc. But the sentiment analysis task becomes challenging when it comes to low resource languages because the basis of learning sentiment classifiers are annotated datasets and annotated datasets for non-English texts hardly exists. So for the development of sentiment classifiers in Telugu, we have created corpora "Sentiraama" for different domains like movie reviews, song lyrics, product reviews and book reviews in Telugu language with the text written in Telugu script. In this paper, we describe the process of creating the corpora and assigning polarities to them. After the creation of corpora, we trained the classifiers that yields good classification results. Typically a sentiment classifier is trained using data from the same domain it is intended to be tested on. But there may not be sufficient data available in the same domain and additionally using data from multiple sources and domains may help in creating a more generalized sentiment classifier which can be applied to multiple domains. So to create this generalized classifier, we used the sentiment data from the above corpus from different domains. We first tested the performance of sentiment analysis models built using single data source for both in-domain and cross-domain classification. Later, we built sentiment model using data samples from multiple domains and then tested the performance of the models based on their classification. Finally, we compared all the three approaches based on the performance of the models and discussed the best approach for sentiment analysis.

Abstract

This paper presents the design and development of IIITH Hindi-English code mixed (IIITH-HE-CM) text and corresponding speech corpus. The corpus is collected from several Hindi native speakers from different geographical parts of India. The IIITH-HE-CM corpus has phonetically balanced code mixed sentences with all the phoneme coverage of Hindi and English languages. We used triphone frequency of word internal triphone sequence, consists the language specific information, which helps in code mixed speech recognition and language modelling. The code mixed sentences are written in Devanagari script. Since computers can recognize Roman symbols, we used Indian Language Speech Sound Label (ILSL) transcription. An acoustic model is built for Hindi-English mixed language instead of language-dependent models. A large vocabulary codemixing speech recognition system is developed based on a deep neural network (DNN) architecture. The proposed code-mixed speech recognition system attains low word error rate (WER) compared to conventional system.

Abstract

Nasals and approximants consonants are often confused with each other. Despite the distinction in the production mechanism, these two sound classes exhibit a similar low frequency behavior, and lack significant high frequency content. The present study uses a spectral representation obtained using the zero time windowing (ZTW) analysis of speech, for the task of distinction between these two. The instantaneous spectral representation has good resolution at resonances, which helps to highlight the difference in the acoustic vocal tract system response for these sounds. The ZTW spectra around the regions of glottal closure instants are averaged to derive parameters for their classification in continuous speech. A set of parameters based on the dominant resonances, center of gravity, band energy ratio, and cumulative spectral sum in low frequencies, is derived from the average spectrum. The paper proposes classification using a knowledge–based approach and training a support vector machine. These classifiers are tested on utterances from different English speakers in the TIMIT dataset. The proposed methods result in an average classification accuracy of 90% between the two classes in continuous speech.

Abstract

Video games have become an integral part of most people’s lives in recent times. This led to an abundance of data related to video games being shared online. However, this comes with issues such as incorrect ratings, reviews or anything that is being shared. Recommendation systems are powerful tools that help users by providing them with meaningful recommendations. A straightforward approach would be to predict the scores of video games based on other information related to the game. It could be used as a means to validate user-submitted ratings as well as provide recommendations. This work provides a method to predict the G-Score, that defines how good a video game is, from its trailer (video) and summary (text). We first propose models to predict the G-Score based on the trailer alone (unimodal). Later on, we show that considering information from multiple modalities helps the models perform better compared to using information from videos alone. Since we couldn’t find any suitable multimodal video game dataset, we created our own dataset named VGD (Video Game Dataset) and provide it along with this work. The approach mentioned here can be generalized to other multimodal datasets such as movie trailers and summaries etc. Towards the end, we talk about the shortcomings of the work and some methods to overcome them.

Abstract

In order for our computer systems to be more human-like, with a higher emotional quotient, they need to be able to process and understand intrinsic human language phenomena like humour. In this paper, we consider a subtype of humour - puns, which are a common type of wordplay-based jokes. In particular, we consider code-mixed puns which have become increasingly mainstream on social media, in informal conversations and advertisements and aim to build a system which can automatically identify the pun location and recover the target of such puns. We first study and classify code-mixed puns into two categories namely intra-sentential and intra-word, and then propose a four-step algorithm to recover the pun targets for puns belonging to the intra-sentential category. Our algorithm uses language models, and phonetic similarity-based features to get the desired results. We test our approach on a small set of code-mixed punning advertisements, and observe that our system is successfully able to recover the targets for 67% of the puns.