AMIT GOYAL

Contact:

Amit Goyal
Dept. of Computer Science, Room #3126
AV Williams Building, University of Maryland
College Park, Maryland - 20742

Email: amit AT umiacs DOT umd DOT edu

I am a Research Scientist at Yahoo! Labs. I work with Web Mining and Search group. I completed my PhD in Computer Science in May 2013 from the Dept. of Computer Science, University of Maryland. My advisor was Hal Daumé III. My research interests are into Natural Language Processing (NLP), algorithms, machine learning (semi-supervised, online and large-scale learning), search, and web mining. My PhD dissertation was about designing and exploiting approximate memory and time efficient streaming and sketch algorithms to address large-scale NLP problems. I interned at Raytheon BBN Technologies for a year, and worked on metaphor identification, meta clustering, and disease outbreak prediction from Twitter data. During JHU summer workshop, I worked on learning the relationships between visually descriptive text and images. I have also worked on narrative text understanding with Ellen Riloff. I am interested in automatically learning world knowledge from large data that can be useful for many NLP applications. Besides, I have also worked on information extraction using pattern-based approach with Siddharth Patwardhan.

I did my Bachelors with Honors in Computer Science and Engineering from IIIT, Hyderabad , India. I have worked with Rajeev Sangal on clause boundary identification, named-entity recognition and studied parsing for my undergraduate thesis.

Publications

Fast Large-Scale Approximate Graph Construction for NLP [PDF]
Amit Goyal, Hal Daume III and Raul D. Guerra
EMNLP-CONLL 2012

Sketch Algorithms for Estimating Point Queries in NLP [PDF]
Amit Goyal, Hal Daume III and Graham Cormode
EMNLP-CONLL 2012

Detecting Visual Text [PDF]
Jesse Dodge, Amit Goyal, Xufeng Han, Alyssa Mensch, Margaret Mitchell, Karl Sratos, Kota Yamaguchi, Yejin Choi, Hal Daume III, Alex Berg, and Tamara L. Berg
Accepted at North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL 2012

Midge: Generating Image Descriptions From Computer Vision Detections [PDF]
Margaret Mitchell, Jesse Dodge, Amit Goyal, Kota Yamaguchi, Karl Sratos, Xufeng Han, Alysssa Mensch, Alex Berg, Tamara L. Berg and Hal Daume III
European Chapter of the Association for computational Linguistics, EACL 2012

Understanding and Predicting Importance in Images [PDF]
Karl Sratos, Aneesh Sood, Alyssa Mensch, Xufeng Han, Margaret Mitchell, Kota Yamaguchi, Jesse Dodge, Amit Goyal, Hal Daume III , Alex Berg, and Tamara L. Berg
Accepted at Computer Vision and Pattern Recognition, CVPR 2012

Multiple Hash Functions for Learning
Amit Goyal and Piyush Rai and Hal Daumé III.
NIPS Workshop on Big Learning: Algorithms, Systems, and Tools for Learning at Scale, 2011

Approximate Scalable Bounded Space Sketch for Large Data NLP [PDF]
Amit Goyal and Hal Daumé III.
Empirical Methods in Natural Language Processing (EMNLP) 2011

Generating Semantic Orientation Lexicon using Large Data and Thesaurus.
Amit Goyal and Hal Daumé III.
Accepted at the workshop WASSA-11 (in conjunction with ACL 2011)

Lossy Conservative Update (LCU) sketch: Succinct approximate count storage. [PDF]
Amit Goyal and Hal Daumé III.
Accepted at the Twenty-Fifth AAAI Conference on Artificial Intelligeince (AAAI-11)

Lossy Conservative Update sketch. [PDF]
Amit Goyal and Hal Daumé III.
The Learning Workshop 2011

Segmenting low-level instructions into high-level instructions [PDF]
Amit Goyal and Jiarong Jiang and Hal Daumé III.
The Learning Workshop 2011

A Computational Model for Plot Units.
Amit Goyal, Ellen Riloff, and Hal Daumé III. Computational Intelligence Journal (Accepted for publication) [DATA]

Automatically Producing Plot Unit Representations for Narrative Text [PDF] [BIB] [DATA]
Amit Goyal, Ellen Riloff, and Hal Daumé III.
EMNLP 2010

Sketch Techniques for Scaling Distributional Similarity to the Web [PDF]
Amit Goyal, Jagadeesh Jagarlamudi, Hal Daumé III and Suresh Venkatasubramanian.
GEometrical Models of Natural Language Semantics (in conjunction with ACL 2010)

Toward Plot Units: Automatic Affect State Analysis [PDF] [SLIDES]
Amit Goyal, Ellen Riloff, Hal Daumé III and Nathan Gilbert.
Workshop on Computational Approaches to Analysis and Generation of Emotion in Text (in conjunction with NAACL-HLT 2010)

Sketching Techniques for Large Scale NLP [PDF] [SLIDES] [BIB]
Amit Goyal, Jagadeesh Jagarlamudi, Hal Daumé III and Suresh Venkatasubramanian.
6th Web as Corpus Workshop (in conjunction with NAACL-HLT 2010)

Streaming for Large Scale NLP: Language Modeling [PDF] [SLIDES] [BIB]
Amit Goyal, Hal Daumé III and Suresh Venkatasubramanian.
North American Association for Computational Linguistics 2009