This blog refers to our technical paper accepted at Interspeech 2021, Czechia. The problem at hand Automatic Speech Recognition (ASR) systems fail to transcribe real-life calls with 100% accuracy. …

Based on 6 years experience in ML — Disclaimer: 2 yrs of academic + 4 yrs of professional experience. I don’t claim to be a mentor/coach nor do I claim myself to having an extraordinary track record. …

A document can contain information regarding multiple topics viz., sports and politics. A simple summarization method would present this document in a concise format (single summary). How about a setup that can regard topics present in the document to generate summary considering that topic (topic based summary)? A method as published in “Generating topic oriented summaries using neural network” in NAACL, 2018.

How to generate word vectors depending on the context that can cater to challenge of polysemy along with capturing information regarding its syntactic and semantic characteristics. A method as published in “Deep Contextualized Word Representations” in NAACL, 2018. — Authors: Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer Problem at hand?

How to automatically determine the stance in a piece of text and extract relevant information identified in support of the detected stance? A method as published in “Automatic Stance Detection Using End-to-End Memory Networks” in NAACL, 2018. — Authors: Mitra Mohtarami, Ramy Baly, James Glass, Preslav Nakov, Lluis Marquez, Alessandro Moschitti Problem at hand? To identify relative perspective of a text with respect to a given claim under categories such as agree, disagree, discuss and unrelated.

How to integrate information that comes from existing lexicons to word vectors? A method as published in “Retrofitting Word Vectors to Semantic Lexicons” in NAACL, 2015. — Authors: Manaal Faruqui, Jesse Dodge, Sujay K. Jauhar, Chris Dyer, Eduard Hovy, Noah A. Smith Problem at hand? To bind the information present in semantic lexicons to word vectors. Say a lexicon L has representation that informs words: ‘good’, ‘brilliant’, ‘exceptional’, ‘great’ and ‘superb’ are connected to each other.

Neural Attention Model as published in “An Unsupervised Neural Attention Model for Aspect Extraction” in ACL 2017. — Authors: Ruidan He, Wee Sun Lee, Hwee Tou Ng, Daniel Dahlmeier Problem at hand? To extract aspect terms mentioned in a given piece of text, usually reviews. We had champagne and caviar and felt like princesses. Aspect terms: champagne, caviar & Aspect category: food This place is usually very crowded because of its…