Prof. Yoav Goldberg

Natural language processing, syntactic processing and parsing, machine translation, Hebrew NLP, machine learning and structured prediction

 

http://www.cs.biu.ac.il/~yogo/

ABOUT MY WORK

I am interested in syntactic parsing, structured-prediction models, learning for greedy decoding algorithms, multilingual language understanding, and cross domain learning. Lately, I am also interested in neural network based methods for NLP

SELECTED PUBLICATIONS

1. Template Kernels for Dependency Parsing [pdf] NAACL-2015 (Short) Hillel Taub-Tabib, Yoav Goldberg and Amir Globerson  kernels, parsing, dependency, graph-based
2. Neural Word Embedding as Implicit Matrix Factorization [pdf] NIPS-2014 Omer Levy and Yoav Goldberg word representation, matrix factorization, word2vec, negative sampling
3. Linguistic Regularities in Sparse and Explicit Word Representations [pdf] CoNLL-2014 Best Paper Award Omer Levy and Yoav Goldberg word representation, buzz-busting, analogies
4. word2vec explained: deriving Mikolov et al.’s negative-sampling word-embedding method [pdf] Tech-report
Yoav Goldberg and Omer Levy word-embeddings
5. Training Deterministic Parsers with Non-Deterministic Oracles. [pdf] [code] TACL. 1(October):403–414, 2013 Yoav Goldberg and Joakim Nivre Deterministic-decoding, Dynamic-oracles

RESEARCH PROJECTS

• syntactic parsing
• structured-prediction models
• learning for greedy decoding algorithms
• multilingual language understanding, and cross domain learning
• neural network based methods for NLP.