To determine how close two language models (e.g., n-grams models) are, we can use several distance measures. If we can represent the models as distributions, then the similarity is basically the similarity of distributions. And a number of measures are based on information theoretic approach. In this paper we present some experiments on using such similarity measures for an old Natural Language Processing (NLP) problem. One of the measures considered is perhaps a novel one, which we have called mutual cross entropy. Other measures are either well known or based on well known measures, but the results obtained with them vis-avis one-another might help in gaining an insight into how similarity measures work in practice.The first step in processing a text is to identify the language and encoding of its contents. This is a practical problem since for many languages, there are no universally followed text encoding standards. The method we have used in this paper for language and encoding identification uses pruned character n-grams, alone as well augmented with word n-grams. This method seems to give results comparable to other methods.

This paper describes the best performing system for the shared task on Named Entity Recognition (NER) on code-switched data for the language pair Spanish-English (ENG-SPA). We introduce a gated neural architecture for the NER task. Our final model achieves an F1 score of 63.76%, outperforming the baseline by 10%.

An accurate language identification tool is an absolute necessity for building complex NLP systems to be used on code-mixed data. Lot of work has been recently done on the same, but there's still room for improvement. Inspired from the recent advancements in neural network architectures for computer vision tasks, we have implemented multichannel neural networks combining CNN and LSTM for word level language identification of code-mixed data. Combining this with a Bi-LSTM-CRF context capture module, accuracies of 93.28% and 93.32% is achieved on our two testing sets.

The contrast between the contextual and general meaning of a word serves as an important clue for detecting its metaphoricity. In this paper, we present a deep neural architecture for metaphor detection which exploits this contrast. Additionally, we also use cost-sensitive learning by re-weighting examples, and baseline features like concreteness ratings, POS and WordNet-based features. The best performing system of ours achieves an overall F1 score of 0.570 on All POS category and 0.605 on the Verbs category at the Metaphor Shared Task 2018.

Quantitative measurement of inter-language distance is a useful technique for studying diachronic and synchronic relations between languages. Such measures have been used successfully for purposes like deriving language taxonomies and language reconstruction, but they have mostly been applied to handcrafted word lists. Can we instead use corpus based measures for comparative study of languages? In this paper we try to answer this question. We use three corpus based measures and present the results obtained from them and show how these results relate to linguistic and historical knowledge. We argue that the answer is yes and that such studies can provide or validate linguistic and computational insights.