• Publications
  • Influence
Harnessing Context Incongruity for Sarcasm Detection
TLDR
A computational system that harnesses context incongruity as a basis for sarcasm detection is presented and it is shown how the features can capture intersentential incongrouity. Expand
A Fall-back Strategy for Sentiment Analysis in Hindi: a Case Study
Sentiment Analysis (SA) research has gained tremendous momentum in recent times. However, there has been little work in this area for an Indian language. We propose in this paper a fall-back strategyExpand
Contextual Inter-modal Attention for Multi-modal Sentiment Analysis
TLDR
A recurrent neural network based multi-modal attention framework that leverages the contextual information for utterance-level sentiment prediction that applies attention on multi- modal multi-utterance representations and tries to learn the contributing features amongst them. Expand
The IIT Bombay English-Hindi Parallel Corpus
TLDR
The corpus has been pre-processed for machine translation, and baseline phrase-based SMT and NMT translation results on this corpus are reported, making it the largest publicly available English-Hindi parallel corpus. Expand
Sentiment Analysis in Twitter with Lightweight Discourse Analysis
TLDR
This work shows how the discourse relations like the connectives and conditionals can be used to incorporate discourse information in any bag-of-words model, to improve sentiment classification accuracy. Expand
Unsupervised Most Frequent Sense Detection using Word Embeddings
TLDR
This paper proposes an unsupervised method for MFS detection from the untagged corpora, which exploits word embeddings and obtains the predominant sense with the highest similarity. Expand
Automatic Sarcasm Detection
Automatic sarcasm detection is the task of predicting sarcasm in text. This is a crucial step to sentiment analysis, considering prevalence and challenges of sarcasm in sentiment-bearing text.Expand
Are Word Embedding-based Features Useful for Sarcasm Detection?
TLDR
A comparison of the four embeddings shows that Word2Vec and dependency weight-based features outperform LSA and GloVe, in terms of their benefit to sarcasm detection. Expand
Automatic Sarcasm Detection: A Survey
TLDR
This paper is the first known compilation of past work in automatic sarcasm detection, observing three milestones in the research so far: semi-supervised pattern extraction to identify implicit sentiment, use of hashtag-based supervision, and use of context beyond target text. Expand
Feature Specific Sentiment Analysis for Product Reviews
TLDR
A novel approach to identify feature specific expressions of opinion in product reviews with different features and mixed emotions and achieves a high accuracy across all domains and performs at par with state-of-the-art systems despite its data limitations. Expand
...
1
2
3
4
5
...