Search

Your search keyword '"Narasimhan, Karthik"' showing total 26 results
Start Over Author "Narasimhan, Karthik" Publisher association for computational linguistics

Refine your results

more »

26 results on '"Narasimhan, Karthik"'

4. C-STS: Conditional Semantic Textual Similarity

Author

Deshpande, Ameet, primary, Jimenez, Carlos, additional, Chen, Howard, additional, Murahari, Vishvak, additional, Graf, Victoria, additional, Rajpurohit, Tanmay, additional, Kalyan, Ashwin, additional, Chen, Danqi, additional, and Narasimhan, Karthik, additional

Published
2023
Full Text
View/download PDF

7. CARETS: A Consistency And Robustness Evaluative Test Suite for VQA

Author

Jimenez, Carlos E., Russakovsky, Olga, and Narasimhan, Karthik

Subjects
FOS: Computer and information sciences, Computer Science - Computation and Language, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Computation and Language (cs.CL)
Abstract

We introduce CARETS, a systematic test suite to measure consistency and robustness of modern VQA models through a series of six fine-grained capability tests. In contrast to existing VQA test sets, CARETS features balanced question generation to create pairs of instances to test models, with each pair focusing on a specific capability such as rephrasing, logical symmetry or image obfuscation. We evaluate six modern VQA systems on CARETS and identify several actionable weaknesses in model comprehension, especially with concepts such as negation, disjunction, or hypernym invariance. Interestingly, even the most sophisticated models are sensitive to aspects such as swapping the order of terms in a conjunction or varying the number of answer choices mentioned in the question. We release CARETS to be used as an extensible tool for evaluating multi-modal model robustness., ACL 2022

Published
2022
Full Text
View/download PDF

17. Language Understanding for Text-based Games using Deep Reinforcement Learning

Author

Narasimhan, Karthik Rajagopal, Kulkarni, Tejas Dattatraya, Barzilay, Regina, Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Kulkarni, Tejas Dattatraya, and Barzilay, Regina

Subjects
ComputingMilieux_PERSONALCOMPUTING
Abstract

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations., Leventhal Fellowship, MIT Center for Brains, Minds and Machines

Published
2015

21. Language Understanding for Text-based Games using Deep Reinforcement Learning

Author

Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Kulkarni, Tejas Dattatraya, Barzilay, Regina, Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Kulkarni, Tejas Dattatraya, and Barzilay, Regina

Abstract

In this paper, we consider the task of learning control policies for text-based games. In these games, all interactions in the virtual world are through text and the underlying state is not observed. The resulting language barrier makes such environments challenging for automatic game players. We employ a deep reinforcement learning framework to jointly learn state representations and action policies using game rewards as feedback. This framework enables us to map text descriptions into vector representations that capture the semantics of the game states. We evaluate our approach on two game worlds, comparing against baselines using bag-of-words and bag-of-bigrams for state representations. Our algorithm outperforms the baselines on both worlds demonstrating the importance of learning expressive representations., Leventhal Fellowship, MIT Center for Brains, Minds and Machines

Published
2015

22. An unsupervised method for uncovering morphological chains

Author

Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Barzilay, Regina, Jaakkola, Tommi S., Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science, Narasimhan, Karthik Rajagopal, Barzilay, Regina, and Jaakkola, Tommi S.

Abstract

Most state-of-the-art systems today produce morphological analysis based only on orthographic patterns. In contrast, we propose a model for unsupervised morphological analysis that integrates orthographic and semantic views of words. We model word formation in terms of morphological chains, from base words to the observed words, breaking the chains into parent-child relations. We use log-linear models with morpheme and word-level features to predict possible parents, including their modifications, for each word. The limited set of candidate parents for each word render contrastive estimation feasible. Our model consistently matches or outperforms five state-of-the-art systems on Arabic, English and Turkish., United States. Intelligence Advanced Research Projects Activity (United States. Dept. of Defense/U.S. Army Research Laboratory Contract W911NF-12-C-0013)

Published
2015

26. Nonparametric Spherical Topic Modeling with Word Embeddings.

Author

Batmanghelich K, Saeedi A, Narasimhan K, and Gershman S

Abstract

Traditional topic models do not account for semantic regularities in language. Recent distributional representations of words exhibit semantic consistency over directional metrics such as cosine similarity. However, neither categorical nor Gaussian observational distributions used in existing topic models are appropriate to leverage such correlations. In this paper, we propose to use the von Mises-Fisher distribution to model the density of words over a unit sphere. Such a representation is well-suited for directional data. We use a Hierarchical Dirichlet Process for our base topic model and propose an efficient inference algorithm based on Stochastic Variational Inference. This model enables us to naturally exploit the semantic structures of word embeddings while flexibly discovering the number of topics. Experiments demonstrate that our method outperforms competitive approaches in terms of topic coherence on two different text corpora while offering efficient inference.

Published
2016
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results