Anil Nelakanti

Prabhakar Gupta, Ridha Juneja, Anil Nelakanti et al.

We present a novel approach to detecting over and under translations (OT/UT) as part of adequacy error checks in translation evaluation. We do not restrict ourselves to machine translation (MT) outputs and specifically target applications with human generated translation pipeline. The goal of our system is to identify OT/UT errors from human translated video subtitles with high error recall. We achieve this without reference translations by learning a model on synthesized training data. We compare various classification networks that we trained on embeddings from pre-trained language model with our best hybrid network of GRU + CNN achieving 89.3% accuracy on high-quality human-annotated evaluation data in 8 languages.

Prabhakar Gupta, Anil Nelakanti

Quality estimation (QE) for tasks involving language data is hard owing to numerous aspects of natural language like variations in paraphrasing, style, grammar, etc. There can be multiple answers with varying levels of acceptability depending on the application at hand. In this work, we look at estimating quality of translations for video subtitles. We show how existing QE methods are inadequate and propose our method DeepSubQE as a system to estimate quality of translation given subtitles data for a pair of languages. We rely on various data augmentation strategies for automated labelling and synthesis for training. We create a hybrid network which learns semantic and syntactic features of bilingual data and compare it with only-LSTM and only-CNN networks. Our proposed network outperforms them by significant margin.

Syed Ashar Javed, Anil Kumar Nelakanti

Convolutional Neural Networks (CNNs) have been used extensively for computer vision tasks and produce rich feature representation for objects or parts of an image. But reasoning about scenes requires integration between the low-level feature representations and the high-level semantic information. We propose a deep network architecture which models the semantic context of scenes by capturing object-level information. We use Long Short Term Memory(LSTM) units in conjunction with object proposals to incorporate object-object relationship and object-scene relationship in an end-to-end trainable manner. We evaluate our model on the LSUN dataset and achieve results comparable to the state-of-art. We further show visualization of the learned features and analyze the model with experiments to verify our model's ability to model context.

C Ravindranath Chowdary, Anil Kumar Singh, Anil Nelakanti

Retrieval and content management are assumed to be mutually exclusive. In this paper we suggest that they need not be so. In the usual information retrieval scenario, some information about queries leading to a website (due to `hits' or `visits') is available to the server administrator of the concerned website. This information can used to better present the content on the website. Further, we suggest that some more information can be shared by the retrieval system with the content provider. This will enable the content provider (any website) to have a more dynamic presentation of the content that is in tune with the query trends, without violating the privacy of the querying user. The result will be a better synchronization between retrieval systems and content providers, with the purpose of improving the user's web search experience. This will also give the content provider a say in this process, given that the content provider is the one who knows much more about the content than the retrieval system. It also means that the content presentation may change in response to a query. In the end, the user will be able to find the relevant content more easily and quickly.