Abstract

Code-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages. A major contributing factor is the informal nature of these languages which makes it difficult to collect code-mixed data. In this paper, we propose our system for Task 1 of CACLS 2021 to generate a machine translation system for English to Hinglish in a supervised setting. Translating in the given direction can help expand the set of resources for several tasks by translating valuable datasets from high resource languages. We propose to use mBART, a pre-trained multilingual sequence-to-sequence model, and fully utilize the pre-training of the model by transliterating the roman Hindi words in the code-mixed sentences to Devanagri script. We evaluate how expanding the input by concatenating Hindi translations of the English sentences improves mBART’s performance. Our system gives a BLEU score of 12.22 on test set. Further, we perform a detailed error analysis of our proposed systems and explore the limitations of the provided dataset and metrics.

Abstract

–Stock rate prediction always attracts investor; it is not only because of interest but also act as a big challenge and a mystery. This problem is very complex in nature and it is quite dynamic type of problem. A lot of volatility always remains and the Global stock market makes it a more challenging and interesting job of stock prediction. Predicting stock prices is a very risky job which may have lot of errors. These errors needs & should be minimized so that financial losses in investment in stock market can be minimized. In this research paper, we have applied supervised machine learning algorithm known as moisture and evaporation decision tree (MEDT). To predict stock prices, we have applied last five years of Historical data with attributes: open high, low and close rates and volume of the particular stock. MEDT algorithm on 5 year’s stock data of (historical prices) has been taken for experiments. As we already know that the market news always affects Stock price movements. The current research we have considered positive or negative news about particular stock. If the news is positive it is called moisture and it assigned a weight between 0 and 1 based on the type and the importance of the news for that particular stock. The news is very impactful then and its moisture value maybe point 0.8, otherwise news is less impactful then its value may vary 0.1 or 0.2. If the news is impactful on the stock rate in the positive direction then its magnitude will be positive moisture value otherwise it will be a negative moisture value. Technique is seen successful in 88% cases.

Abstract

This paper presents a methodology submitted to the FinSBD-2 shared task to extract well formed sentences, lists and items from noisy unstructured financial PDF documents in English language. The proposed architecture for document structure identification, is a combination of deep learning and heuristic based approaches. We use two unidirectional Long Short-Term Memory (LSTM) encoders to get the sentence split tokens from the set of all the possible split points. Further, the outputs are passed on to an attention based LSTM network to select only the well formed sentences from all the possible sentences. These outputs are merged to ultimately produce all possible well formed sentences. Apart from the sentences, lists and items are identified using a combination of heuristics which identify patterns in the data. The final F1 score, 0.217 on this task, is obtained by comparing the start and end indices of sentences, lists and items. We have presented another parameter, which is used to evaluate the class coverage by checking the overlap between the predicted and ground truth sentences and obtained an average 40% class coverage score. This metric is more useful for industry researchers who require coverage of the content rather than character level precision. The proposed approach will empower both academia and industry researchers in their effort to handle noisy documents for various NLP tasks by providing a simple, fast and robust approach to identify structure in their documents.

Abstract

In this paper, we investigate the problem of text coherence modeling with a new perspective of learning better distributed sentence representation by incorporating document dependent and document independent features of a sentence. To this end, we propose a data-driven end-to-end novel neural coherence model that captures text coherence by exploiting the semantic and distributional aspects of the sentences in a document. The network is able to capture various document independent and document dependent features of a sentence which is imperative in assessing text coherence. Experiments on the standard Sentence Ordering task indicate that our proposed model shows significant performance gain of 1.7 percent in terms of accuracy score compared with the state-of-the-art baselines.

Abstract

Memes are steadily taking over the feeds of the public on social media. There is always the threat of malicious users on the internet posting offensive content, even through memes. Hence, the automatic detection of offensive images/memes is imperative along with detection of offensive text. However, this is a much more complex task as it involves both visual cues as well as language understanding and cultural/context knowledge. This paper describes our approach to the task of SemEval-2020 Task 8: Memotion Analysis. We chose to participate only in Task A which dealt with Sentiment Classification, which we formulated as a text classification problem. Through our experiments, we explored multiple training models to evaluate the performance of simple text classification algorithms on the raw text obtained after running OCR on meme images. Our submitted model achieved an accuracy of 72.69% and exceeded the existing baseline’s Macro F1 score by 8% on the official test dataset. Apart from describing our official submission, we shall elucidate how different classification models respond to this task.

Abstract

Discourse relations between two textual spans in a document attempt to capture the coherent structure which emerges in language use. Automatic classification of these relations remains a challenging task especially in case of implicit discourse relations, where there is no explicit textual cue which marks the discourse relation. In low resource languages, this motivates the exploration of transfer learning approaches, more particularly the cross-lingual techniques towards discourse relation classification. In this work, we explore various cross-lingual transfer techniques on Hindi Discourse Relation Bank (HDRB), a Penn Discourse Treebank styled dataset for discourse analysis in Hindi and observe performance gains in both zero shot and finetuning settings on the Hindi Discourse Relation Classification task. This is the first effort towards exploring transfer learning for Hindi Discourse relation classification to the best of our knowledge.

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.