No abstract

No abstract

Neural machine translation (NMT) has recently shown promising results on publicly available benchmark datasets and is being rapidly adopted in various production systems. However, it requires high-quality large-scale parallel corpus, and it is not always possible to have sufficiently large corpus as it requires time, money, and professionals. Hence, many existing large-scale parallel corpus are limited to the specific languages and domains. In this paper, we propose an effective approach to improve an NMT system in low-resource scenario without using any additional data. Our approach aims at augmenting the original training data by means of parallel phrases extracted from the original training data itself using a statistical machine translation (SMT) system. Our proposed approach is based on the gated recurrent unit (GRU) and transformer networks. We choose the Hindi–English, Hindi–Bengali datasets for Health, Tourism, and Judicial (only for Hindi–English) domains. We train our NMT models for 10 translation directions, each using only 5–23k parallel sentences. Experiments show the improvements in the range of 1.38–15.36 BiLingual Evaluation Understudy points over the baseline systems. Experiments show that transformer models perform better than GRU models in low-resource scenarios. In addition to that, we also find that our proposed method outperforms SMT—which is known to work better than the neural models in low-resource scenarios—for some translation directions. In order to further show the effectiveness of our proposed model, we also employ our approach to another interesting NMT task, for example, old-to-modern English translation, using a tiny parallel corpus of only 2.7K sentences. For this task, we use publicly available old-modern English text which is approximately 1000 years old. Evaluation for this task shows significant improvement over the baseline NMT.

No abstract

Most social media platforms allow users to freely express their beliefs, opinions, thoughts, and intents. Twitter is one of the most popular social media platforms where users' post their intent to purchase. A purchase intent can be defined as measurement of the probability that a consumer will purchase a product or service in future. Identification of purchase intent in Twitter sphere is of utmost interest as it is one of the most long-standing and widely used measures in marketing research. In this paper, we present a supervised learning strategy to identify users' purchase intent from the language they use in Twitter. Recurrent Neural Networks (RNNs), in particular with Long Short-Term Memory (LSTM) hidden units, are powerful and increasingly popular models for text classification. They effectively encode sequences with varying length and capture long range dependencies. We present the first study to apply LSTM for purchase intent identification task. We train the LSTM network on semi-automatically created dataset. Our model achieves competent classification accuracy (F1 = 83%) over a gold-standard dataset. Further, we demonstrate the efficacy of the LSTM network by comparing its performance with different classical classification algorithms taking this purchase intent identification task into account.

No abstract

Terminology translation plays a critical role in domain-specific machine translation (MT). In this paper, we conduct a comparative qualitative evaluation on terminology translation in phrasebased statistical MT (PB-SMT) and neural MT (NMT) in two translation directions: English-to-Hindi and Hindi-to-English. For this, we select a test set from a legal domain corpus and create a gold standard for evaluating terminology translation in MT. We also propose an error typology taking the terminology translation errors into consideration. We evaluate the MT systems' performance on terminology translation, and demonstrate our findings, unraveling strengths, weaknesses, and similarities of PB-SMT and NMT in the area of term translation.

In this paper, we investigate the effectiveness of training a multimodal neural machine translation (MNMT) system with image features for a lowresource language pair, Hindi and English, using synthetic data. A threeway parallel corpus which contains bilingual texts and corresponding images is required to train a MNMT system with image features. However, such a corpus is not available for low resource language pairs. To address this, we developed both a synthetic training dataset and a manually curated development/test dataset for Hindi based on an existing English-image parallel corpus. We used these datasets to build our image description translation system by adopting state-of-theart MNMT models. Our results show that it is possible to train a MNMT system for low-resource language pairs through the use of synthetic data and that such a system can benefit from image features.