Lakshya Kumar

Efficient search is a critical component for an e-commerce platform with an innumerable number of products. Every day millions of users search for products pertaining to their needs. Thus, showing the relevant products on the top will enhance the user experience. In this work, we propose a novel approach of fusing a transformer-based model with various listwise loss functions for ranking e-commerce products, given a user query. We pre-train a RoBERTa model over a fashion e-commerce corpus and… Show more

Efficient search is a critical component for an e-commerce platform with an innumerable number of products. Every day millions of users search for products pertaining to their needs. Thus, showing the relevant products on the top will enhance the user experience. In this work, we propose a novel approach of fusing a transformer-based model with various listwise loss functions for ranking e-commerce products, given a user query. We pre-train a RoBERTa model over a fashion e-commerce corpus and fine-tune it using different listwise loss functions. Our experiments indicate that the RoBERTa model fine-tuned with an NDCG based surrogate loss function(approxNDCG) achieves an NDCG improvement of 13.9% compared to other popular listwise loss functions like ListNET and ListMLE. The approxNDCG based RoBERTa model also achieves an NDCG improvement of 20.6% compared to the pairwise RankNet based RoBERTa model. We call our methodology of directly optimizing the RoBERTa model in an end-to-end manner with a listwise surrogate loss function as ListBERT. Since there is a low latency requirement in a real-time search setting, we show how these models can be easily adopted by using a knowledge distillation technique to learn a representation-focused student model that can be easily deployed and leads to ~10 times lower ranking latency. Show less

Typical e-commerce platforms contain millions of products in the catalog. Users visit these platforms and enter search queries to retrieve their desired products. Therefore, showing the relevant products at the top is essential for the success of e-commerce plat- forms. We approach this problem by learning low dimension repre- sentations for queries and product descriptions by leveraging user click-stream data as our main source of signal for product relevance. Starting from GRU-based… Show more

Typical e-commerce platforms contain millions of products in the catalog. Users visit these platforms and enter search queries to retrieve their desired products. Therefore, showing the relevant products at the top is essential for the success of e-commerce plat- forms. We approach this problem by learning low dimension repre- sentations for queries and product descriptions by leveraging user click-stream data as our main source of signal for product relevance. Starting from GRU-based architectures as our baseline model, we move towards a more advanced transformer-based architecture. This helps the model to learn contextual representations of queries and products to serve better search results and understand the user intent in an efficient manner. We perform experiments related to pre-training of the Transformer based RoBERTa model using a fash- ion corpus and fine-tuning it over the triplet loss. Our experiments on the product ranking task show that the RoBERTa model is able to give an improvement of 7.8% in Mean Reciprocal Rank(MRR), 15.8% in Mean Average Precision(MAP) and 8.8% in Normal- ized Discounted Cumulative Gain(NDCG), thus outperforming our GRU based baselines. For the product retrieval task, RoBERTa model is able to outperform other two models with an improvement of 164.7% in Precision@50 and 145.3% in Recall@50. In order to highlight the importance of pre-training RoBERTa for fashion domain, we qualitatively compare already pre-trained RoBERTa on standard datasets with our custom pre-trained RoBERTa over a fashion corpus for the query token prediction task. Finally, we also show a qualitative comparison between GRU and RoBERTa results for product retrieval task for some test queries. RoBERTa model can be utilized for improving the product search task and act as a good baseline that can be fine-tuned for various information retrieval tasks like query recommendations, query re-formulation, etc. Show less

E-commerce customers in developing nations like India tend to follow no fixed format while entering shipping addresses. Parsing such addresses is challenging because of a lack of inherent structure or hierarchy. It is imperative to understand the language of addresses, so that shipments can be routed without delays. In this paper, we propose a novel approach towards understanding customer addresses by deriving motivation from recent advances in Natural Language Processing (NLP). We also… Show more

E-commerce customers in developing nations like India tend to follow no fixed format while entering shipping addresses. Parsing such addresses is challenging because of a lack of inherent structure or hierarchy. It is imperative to understand the language of addresses, so that shipments can be routed without delays. In this paper, we propose a novel approach towards understanding customer addresses by deriving motivation from recent advances in Natural Language Processing (NLP). We also formulate different pre-processing steps for addresses using a combination of edit distance and phonetic algorithms. Then we approach the task of creating vector representations for addresses using Word2Vec with TF-IDF, Bi-LSTM and BERT based approaches. We compare these approaches with respect to sub-region classification task for North and South Indian cities. Through experiments, we demonstrate the effectiveness of generalized RoBERTa model, pre-trained over a large address corpus for language modelling task. Our proposed RoBERTa model achieves a classification accuracy of around 90% with minimal text preprocessing for sub-region classification task outperforming all other approaches. Once pre-trained, the RoBERTa model can be fine-tuned for various downstream tasks in supply chain like pincode suggestion and geo-coding. The model generalizes well for such tasks even with limited labelled data. To the best of our knowledge, this is the first of its kind research proposing a novel approach of understanding customer addresses in e-commerce domain by pre-training language models and fine-tuning them for different purposes. Show less

Research in sarcasm detection spans almost a decade. However a particular form of sarcasm remains unexplored: sarcasm expressed through numbers, which we estimate, forms about 11% of the sarcastic tweets in our dataset. The sentence ‘Love waking up at 3 am’ is sarcastic because of the number. In this paper, we focus on detecting sarcasm in tweets arising out of numbers. Initially, to get an insight into the problem, we implement a rule- based and a statistical machine learning-based (ML)… Show more

Research in sarcasm detection spans almost a decade. However a particular form of sarcasm remains unexplored: sarcasm expressed through numbers, which we estimate, forms about 11% of the sarcastic tweets in our dataset. The sentence ‘Love waking up at 3 am’ is sarcastic because of the number. In this paper, we focus on detecting sarcasm in tweets arising out of numbers. Initially, to get an insight into the problem, we implement a rule- based and a statistical machine learning-based (ML) classifier. The rule-based classifier conveys the crux of the numerical sarcasm problem, namely, incongruity arising out of numbers. The statistical ML classifier uncovers the indicators i.e., features of such sarcasm. The actual system in place, however, are two deep learning (DL) models, CNN and attention network that obtains an F-score of 0.93 and 0.91 on our dataset of tweets containing numbers. To the best of our knowledge, this is the first line of research investigating the phenomenon of sarcasm arising out of numbers, culminating in a detector thereof. Show less

Sarcasm occurring due to the presence of numerical portions in text has been quoted as an error made by automatic sarcasm detection approaches in the past. We present a first study in detecting sarcasm in numbers, as in the case of the sentence ‘Love waking up at 4 am’. We analyze the challenges of the problem, and present Rule-based, Machine Learning and Deep Learning approaches to detect sarcasm in numerical portions of text. Our Deep Learning approach outperforms four past works for sarcasm… Show more

Sarcasm occurring due to the presence of numerical portions in text has been quoted as an error made by automatic sarcasm detection approaches in the past. We present a first study in detecting sarcasm in numbers, as in the case of the sentence ‘Love waking up at 4 am’. We analyze the challenges of the problem, and present Rule-based, Machine Learning and Deep Learning approaches to detect sarcasm in numerical portions of text. Our Deep Learning approach outperforms four past works for sarcasm detection and Rule-based and Machine learning approaches on a dataset of tweets, obtaining an F1-score of 0.93. This shows that special attention to text containing numbers may be useful to improve state-of-the-art in sarcasm detection Show less

Producing Continous Intensity Ranking of Adjectives that belongs to Framenet using Sentiment bearing word embbeddings. These word embeddings contain both the context as well as sentiment information. Sentiment information will help to separate the words like good and bad from each other. The result of this paper is that one can successfully obtain the continous intensity scale for adjectives for both the positive and negative category. The adjectives are taken from the different semantic… Show more

Producing Continous Intensity Ranking of Adjectives that belongs to Framenet using Sentiment bearing word embbeddings. These word embeddings contain both the context as well as sentiment information. Sentiment information will help to separate the words like good and bad from each other. The result of this paper is that one can successfully obtain the continous intensity scale for adjectives for both the positive and negative category. The adjectives are taken from the different semantic categories in Framenet. Show less

Sentiment Analysis deals not only with the positive and negative sentiment detection in the text but it also considers the prevalence and challenges of sarcasm in sentiment-bearing text. Automatic Sarcasm detection deals with the detection of sarcasm in text. In the recent years,work in sarcasm detection gains popularity and has wide applicability in sentiment analysis. This paper complies the various approaches that are developed to tackle the problem of… Show more

Sentiment Analysis deals not only with the positive and negative sentiment detection in the text but it also considers the prevalence and challenges of sarcasm in sentiment-bearing text. Automatic Sarcasm detection deals with the detection of sarcasm in text. In the recent years,work in sarcasm detection gains popularity and has wide applicability in sentiment analysis. This paper complies the various approaches that are developed to tackle the problem of sarcasm detection. In this paper, we describe Rule-based, Machine Learning and Deep Learning approaches for detecting sarcasm and also describes various datasets. We also give details of different features used by various sarcasm detection approaches from past upto the present. Show less