Abstract

The real-world data is often susceptible to label noise, which might constrict the effectiveness of the existing state of the art algorithms for ordinal regression. Existing works on ordinal regression do not take label noise into account. We propose a theoretically grounded approach for class conditional label noise in ordinal regression problems. We present a deep learning implementation of two commonly used loss functions for ordinal regression that is both-1) robust to label noise, and 2) rank consistent for a good ranking rule. We verify these properties of the algorithm empirically and show robustness to label noise on real data and rank consistency. To the best of our knowledge, this is the first approach for robust ordinal regression models.

Abstract

The phenomenon of mixing the vocabulary and syntax of multiple languages within the same utterance is called Code-Mixing. This is more evident in multilingual societies. In this paper, we have developed a system for SemEval 2020: Task 9 on Sentiment Analysis for Code-Mixed Social Media Text. Our system first generates two types of embeddings for the social media text. In those, the first one is character level embeddings to encode the character level information and to handle the out-of-vocabulary entries and the second one is FastText word embeddings for capturing morphology and semantics. These two embeddings were passed to the LSTM network and the system outperformed the baseline model.

Abstract

Sentiment analysis is a widely researched NLP problem with state-of-the-art solutions capable of attaining human-like accuracies for various languages. However, these methods rely heavily on large amounts of labeled data or sentiment weighted language-specific lexical resources that are unavailable for low-resource languages. Our work attempts to tackle this data scarcity issue by introducing a neural architecture for language invariant sentiment analysis capable of leveraging various monolingual datasets for training without any kind of cross-lingual supervision. The proposed architecture attempts to learn language agnostic sentiment features via adversarial training on multiple resource-rich languages which can then be leveraged for inferring sentiment information at a sentence level on a low resource language. Our model outperforms the current state-of-the-art methods on the Multilingual Amazon Review Text Classification dataset [REF] and achieves significant performance gains over prior work on the low resource Sentiraama corpus [REF]. A detailed analysis of our research highlights the ability of our architecture to perform significantly well in the presence of minimal amounts of training data for low resource languages.

Abstract

Humor research is a multifaceted field that has led to a better understanding of humor’s psychological effects and the development of different theories of humor. This paper’s main objective is to develop a hierarchical schema for a fine-grained annotation of Conversational Humor. Based on the Benign Violation Theory, the benignity or non-benignity of the interlocutor’s intentions is included within the framework. Under the categories mentioned above, in addition to different types of humor, the techniques utilized by these types are identified. Furthermore, a prominent play from Telugu, Kanyasulkam, is annotated to substantiate the work across cultures at multiple levels. The inter-annotator agreement is calculated to assess the accuracy and validity of the dataset. An in-depth analysis of the disagreement is performed to understand the subjectivity of humor better.

Abstract

While extensive popularity of online social media platforms has made information dissemination faster, it has also resulted in widespread online abuse of different types like hate speech, offensive language, sexist and racist opinions, etc. Detection and curtailment of such abusive content is critical for avoiding its psychological impact on victim communities, and thereby preventing hate crimes. Previous works have focused on classifying user posts into various forms of abusive behavior. But there has hardly been any focus on estimating the severity of abuse and the target. In this paper, we present a first of the kind dataset with 7601 posts from Gab which looks at online abuse from the perspective of presence of abuse, severity and target of abusive behavior. We also propose a system to address these tasks, obtaining an accuracy of~ 80% for abuse presence,~ 82% for abuse target detection, and~ 64% for abuse severity detection.

Abstract

We propose MEE, an approach for automatic Machine Translation (MT) evaluation which leverages the similarity between embeddings of words in candidate and reference sentences to assess translation quality. Unigrams are matched based on their surface forms, root forms and meanings which aids to capture lexical, morphological and semantic equivalence. We perform experiments for MT from English to four Indian Languages (Telugu, Marathi, Bengali and Hindi) on a robust dataset comprising simple and complex sentences with good and bad translations. Further, it is observed that the proposed metric correlates better with human judgements than the existing widely used metrics.

Abstract

Spoken dialogue systems typically use one or several (top-N) ASR sequence(s) for inferring the semantic meaning and tracking the state of the dialogue. However, ASR graphs, such as confusion networks (confnets), provide a compact representation of a richer hypothesis space than a top-N ASR list. In this paper, we study the benefits of using confusion networks with a neural dialogue state tracker (DST). We encode the 2-dimensional confnet into a 1-dimensional sequence of embed-dings using a confusion network encoder which can be used with any DST system. Our confnet encoder is plugged into the 'Global-locally Self-Attentive Dialogue State Tacker' (GLAD) model for DST and obtains significant improvements in both accuracy and inference time compared to using top-N ASR hypotheses .

Abstract

One-anaphora has figured prominently in theoretical linguistic literature, but computational linguistics research on the phenomenon is sparse. Not only that, the long standing linguistic controversy between the determinative and the nominal anaphoric element one has propagated in the limited body of computational work on one-anaphora resolution, making this task harder than it is. In the present paper, we resolve this by drawing from an adequate linguistic analysis of the word one in different syntactic environments-once again highlighting the significance of linguistic theory in Natural Language Processing (NLP) tasks. We prepare an annotated corpus marking actual instances of one-anaphora with their textual antecedents, and use the annotations to experiment with state-of-the art neural models for one-anaphora resolution. Apart from presenting a strong neural baseline for this task, we contribute a gold-standard corpus, which is, to the best of our knowledge, the biggest resource on one-anaphora till date.

Abstract

In this paper, we describe our submissions for Similar Language Translation Shared Task 2020. We built 12 systems in each direction for Hindi⇐⇒ Marathi language pair. This paper outlines initial baseline experiments with various tokenization schemes to train statistical models. Using optimal tokenization scheme among these we created synthetic source side text with back translation. And prune synthetic text with language model scores. This synthetic data was then used along with training data in various settings to build translation models. We also report configuration of the submitted systems and results produced by them.

Abstract

Emotion prediction is a critical task in the field of Natural Language Processing (NLP). There has been a significant amount of work done in emotion prediction for resource-rich languages. There has been work done on code-mixed social media corpus but not on emotion prediction of Kannada-English code-mixed Twitter data. In this paper, we analyze the problem of emotion prediction on corpus obtained from code-mixed Kannada-English extracted from Twitter annotated with their respective ‘Emotion’for each tweet. We experimented with machine learning prediction models using features like Character N-Grams, Word N-Grams, Repetitive characters, and others on SVM and LSTM on our corpus, which resulted in an accuracy of 30% and 32% respectively.