Abstract

In this paper, we provide an alternate perspective on word representations, by reinterpreting the dimensions of the vector space of a word embedding as a collection of features. In this reinterpretation, every component of the word vector is normalized against all the word vectors in the vocabulary. This idea now allows us to view each vector as an n-tuple (akin to a fuzzy set), where n is the dimensionality of the word representation and each element represents the probability of the word possessing a feature. Indeed, this representation enables the use fuzzy set theoretic operations, such as union, intersection and difference. Unlike previous attempts, we show that this representation of words provides a notion of similarity which is inherently asymmetric and hence closer to human similarity judgements. We compare the performance of this representation with various benchmarks, and explore some of the unique properties including function word detection, detection of polysemous words, and some insight into the interpretability provided by set theoretic operations.

Abstract

In this paper, we extend the task of semantic textual similarity to include sentences which contain emojis. Emojis are ubiquitous on social media today, but are often removed in the pre-processing stage of curating datasets for NLP tasks. In this paper, we qualitatively ascertain the amount of semantic information lost by discounting emojis, as well as show a mechanism of accounting for emojis in a semantic task. We create a sentence similarity dataset of 4000 pairs of tweets with emojis, which have been annotated for relatedness. The corpus contains tweets curated based on common topic as well as by replacement of emojis. The latter was done to analyze the difference in semantics associated with different emojis. We aim to provide an understanding of the information lost by removing emojis by providing a qualitative analysis of the dataset. We also aim to present a method of using both emojis and words for downstream NLP tasks beyond sentiment analysis.

Abstract

This paper describes our system (Fermi) for Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media of SemEval-2019. We participated in all the three sub-tasks within Task 6. We evaluate multiple sentence embeddings in conjunction with various supervised machine learning algorithms and evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team Fermi’s model achieved an F1-score of 64.40%, 62.00% and 62.60% for sub-task A, B and C respectively on the official leaderboard. Our model for sub-task C which uses pre-trained ELMo embeddings for transforming the input and uses SVM (RBF kernel) for training, scored third position on the official leaderboard. Through the paper we provide a detailed description of the approach, as well as the results obtained for the task.

Abstract

This paper describes our system (Fermi) for Task 5 of SemEval-2019: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter. We participated in the subtask A for English and ranked first in the evaluation on the test set. We evaluate the quality of multiple sentence embeddings and explore multiple training models to evaluate the performance of simple yet effective embedding-ML combination algorithms. Our team-Fermi’s model achieved an accuracy of 65.00% for English language in task A. Our models, which use pretrained Universal Encoder sentence embeddings for transforming the input and SVM (with RBF kernel) for classification, scored first position (among 68) in the leaderboard on the test set for Subtask A in English language. In this paper we provide a detailed description of the approach, as well as the results obtained in the task.

Abstract

Online Community Question Answering Forums (cQA) have gained massive popularity within recent years. The rise in users for such forums have led to the increase in the need for automated evaluation for question comprehension and fact evaluation of the answers provided by various participants in the forum. Our team, Fermi, participated in sub-task A of Task 8 at SemEval 2019-which tackles the first problem in the pipeline of factual evaluation in cQA forums, ie, deciding whether a posed question asks for a factual information, an opinion/advice or is just socializing. This information is highly useful in segregating factual questions from non-factual ones which highly helps in organizing the questions into useful categories and trims down the problem space for the next task in the pipeline for fact evaluation among the available answers. Our system uses the embeddings obtained from Universal Sentence Encoder combined with XGBoost for the classification sub-task A. We also evaluate other combinations of embeddings and off-the-shelf machine learning algorithms to demonstrate the efficacy of the various representations and their combinations. Our results across the evaluation test set gave an accuracy of 84% and received the first position in the final standings judged by the organizers.

Abstract

The last decade has witnessed digitization of many government organization’s data. Text summarization of the political discourse, particularly the parliamentary proceedingsis relatively a lesser explored area of research. In this paper,we investigate the role of semantics especially theory of argu-mentation in debate summarization and use it to design a semiautomatic pipeline for generating these summaries. The proposedapproach considers the topic-relevance, argumentative nature,sentiment and context features. We test our approach on thedataset of debates mined from Lok Sabha, the elected house of representatives in India. Our proposed methodology and pipelineshow significant improvement over the high performing popular systems for ROUGE-1, ROUGE-2 and ROUGE-L metrics.

Abstract

n this paper, we describe our machine translation systems submitted to LoResMT2019 Shared Task. Systems were devel-oped for Bhojpuri, Magahi, Sindhi, Lat-vian⇐⇒(English). This paper outlines preprocessing , configuration of the sub-mitted systems and the results produced using the same

Abstract

This paper introduces a gold standard event-annotated dataset of 810 Hindi news article as well as a set of comprehensive guidelines for detecting and annotating events in Hindi. We present our linguistically motivated guideline development process, with a focus on annotator friendliness, that can be replicated for event mention detection for most Indo-Aryan languages. The paper highlights the challenges of detecting event mentions in Hindi given the unique semantic constraints on the syntactic apparatus used for denoting events. Our work as a whole also establishes a language agnostic pipeline for the development of an event annotated corpora and event detection guidelines.

Abstract

Pregroup calculus has been used for the representation of free word order languages (Sanskrit and Hungarian), using a construction called precyclicity. However, restricted word order alternation has not been handled before. This paper aims at introducing and formally expressing three methods of representing word order alternation in the pregroup representation of any language. This paper describes the word order alternation patterns of Hindi, and creates a basic pregroup representation for the language. In doing so, the shortcoming of correct reductions for ungrammatical sentences due to the current apparatus is highlighted, and the aforementioned methods are invoked for a grammatically accurate representation of restricted word order alternation. The replicability of these methods is explained in the representation of adverbs and prepositional phrases in English.

Abstract

Sentiment Analysis and other semantic tasks are commonly used for social media textual analysis to gauge public opinion and make sense from the noise on social media. The language used on social media not only commonly diverges from the formal language, but is compounded by codemixing between languages, especially in large multilingual societies like India. Traditional methods for learning semantic NLP tasks have long relied on end to end task specific training, requiring expensive data creation process, even more so for deep learning methods. This challenge is even more severe for resource scarce texts like codemixed language pairs, with lack of well learnt representations as model priors, and task specific datasets can be few and small in quantities to efficiently exploit recent deep learning approaches. To address above challenges, we introduce curriculum learning strategies for semantic tasks in code-mixed Hindi-English (Hi-En) texts, and investigate various training strategies for enhancing model performance. Our method outperforms the state of the art methods for Hi-En codemixed sentiment analysis by 3.31% accuracy, and also shows better model robustness in terms of convergence, and variance in test performance.