Activity
-
🚀 Exciting News! New Podcast Episode Alert 🎧 Join us on the latest episode of the The Restaurant Technology Guys as I chat with Anand Karthik T.…
🚀 Exciting News! New Podcast Episode Alert 🎧 Join us on the latest episode of the The Restaurant Technology Guys as I chat with Anand Karthik T.…
Liked by Anand Karthik T.
-
We're thrilled to announce the upcoming opening of our 15th location in the vibrant city of Palo Alto. Situated just north of our first location in…
We're thrilled to announce the upcoming opening of our 15th location in the vibrant city of Palo Alto. Situated just north of our first location in…
Liked by Anand Karthik T.
-
The word is out! We're thrilled to be opening our 15th location this summer in Palo Alto, CA 🌇 https://lnkd.in/gUnS9KHZ
The word is out! We're thrilled to be opening our 15th location this summer in Palo Alto, CA 🌇 https://lnkd.in/gUnS9KHZ
Liked by Anand Karthik T.
Experience
Education
-
Birla Institute of Technology and Science
-
Activities and Societies: Professional Assistant for Computer Networks Course
-
-
Ranked 2608 among 300,000 applicants fot the IIT - Joint Entrance Examination;
Ranked 631 among 900,000 applicants for the All India Engineering Entrance Examination -
-
Activities and Societies: Prefect of the Satavahana House, Member of the School Debate Team
Publications
-
Accuracy and robustness in measuring the lexical similarity of semantic role fillers for automatic semantic MT evaluation
PACLIC-26
We present larger-scale evidence overturning previous results, showing that among the many alternative phrasal lexical similarity measures based on word vectors, the Jaccard coefficient most increases the robustness of MEANT, the recently introduced, fully-automatic, state-of-the-art semantic MT evaluation metric. MEANT critically depends on phrasal lexical similarity scores in order to automatically determine which semantic role fillers should be aligned between reference and machine…
We present larger-scale evidence overturning previous results, showing that among the many alternative phrasal lexical similarity measures based on word vectors, the Jaccard coefficient most increases the robustness of MEANT, the recently introduced, fully-automatic, state-of-the-art semantic MT evaluation metric. MEANT critically depends on phrasal lexical similarity scores in order to automatically determine which semantic role fillers should be aligned between reference and machine translations. The robustness experiments were conducted across various data sets following NIST MetricsMaTr protocols, showing higher Kendall correlation with human adequacy judgments against BLEU, METEOR (with and without synsets), WER, PER, TER and CDER. The Jaccard coefficient is shown to be more discriminative and robust than cosine similarity, the Min/Max metric with mutual information, Jensen Shannon divergence, or the Dice's coefficient. We also show that with Jaccard coefficient as the phrasal lexical similarity metric, individual word token scores are best aggregated into phrasal segment similarity scores using the geometric mean, rather than either the arithmetic mean or competitive linking style word alignments. Furthermore, we show empirically that a context window size of 5 captures the optimal amount of information for training the word vectors. The combined results suggest a new formulation of MEANT with significantly improved robustness across data sets.
-
Fully Automatic Semantic MT Evaluation
WMT '12 Proceedings of the Seventh Workshop on Statistical Machine Translation
We introduce the first fully automatic, fully semantic frame based MT evaluation metric, MEANT, that outperforms all other commonly used automatic metrics in correlating with human judgment on translation adequacy. Recent work on HMEANT, which is a human metric, indicates that machine translation can be better evaluated via semantic frames than other evaluation paradigms, requiring only minimal effort from monolingual humans to annotate and align semantic frames in the reference and machine…
We introduce the first fully automatic, fully semantic frame based MT evaluation metric, MEANT, that outperforms all other commonly used automatic metrics in correlating with human judgment on translation adequacy. Recent work on HMEANT, which is a human metric, indicates that machine translation can be better evaluated via semantic frames than other evaluation paradigms, requiring only minimal effort from monolingual humans to annotate and align semantic frames in the reference and machine translations. We propose a surprisingly effective Occam's razor automation of HMEANT that combines standard shallow semantic parsing with a simple maximum weighted bipartite matching algorithm for aligning semantic frames. The matching criterion is based on lexical similarity scoring of the semantic role fillers through a simple context vector model which can readily be trained using any publicly available large monolingual corpus. Sentence level correlation analysis, following standard NIST MetricsMATR protocol, shows that this fully automated version of HMEANT achieves significantly higher Kendall correlation with human adequacy judgments than BLEU, NIST, METEOR, PER, CDER, WER, or TER. Furthermore, we demonstrate that performing the semantic frame alignment automatically actually tends to be just as good as performing it manually. Despite its high performance, fully automated MEANT is still able to preserve HMEANT's virtues of simplicity, representational transparency, and inexpensiveness.
Patents
-
Generating Point of Interest for location orientation
Filed US UP-01227USP
-
Suggesting pickup locations for transport service coordination
Filed US UP-00902US
Courses
-
Artificial Intelligence
-
-
Data Mining
-
-
Pattern Recognition
-
Projects
-
Collectd
-
Collectd is a small daemon which collects system information periodically and provides mechanisms to store and monitor the values in a variety of ways.
-
Minnal
-
Minnal is a highly scalable and productive RESTful service framework that helps you eliminate boiler plate code and build services faster.
More activity by Anand Karthik
-
Business Development Representatives, Join our product market fit rocket ship! 🚀 Loop AI, the best-in-class delivery intelligence platform…
Business Development Representatives, Join our product market fit rocket ship! 🚀 Loop AI, the best-in-class delivery intelligence platform…
Liked by Anand Karthik T.
-
I am excited to report that this morning Tock announced that it has entered into a definitive agreement to be acquired by American Express. This…
I am excited to report that this morning Tock announced that it has entered into a definitive agreement to be acquired by American Express. This…
Liked by Anand Karthik T.
-
Excited to be part of your journey Anand Karthik T.!
Excited to be part of your journey Anand Karthik T.!
Liked by Anand Karthik T.
-
Excited to announce that I've joined Loop AI - Delivery Intelligence Platform as a Software Engineer 2. It was a great experience at Oblivious, with…
Excited to announce that I've joined Loop AI - Delivery Intelligence Platform as a Software Engineer 2. It was a great experience at Oblivious, with…
Liked by Anand Karthik T.
-
Thank you Anand Karthik T. and the Loop AI - Delivery Intelligence Platform Team for creating such a needed solution to the TPD issues… listen here…
Thank you Anand Karthik T. and the Loop AI - Delivery Intelligence Platform Team for creating such a needed solution to the TPD issues… listen here…
Liked by Anand Karthik T.
-
Congratulations Wingstop Restaurants Inc. Marisa Carona and the #WingstopTeam on the recognition
Congratulations Wingstop Restaurants Inc. Marisa Carona and the #WingstopTeam on the recognition
Liked by Anand Karthik T.
Other similar profiles
Explore collaborative articles
We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.
Explore More