NAACL Debrief

Annotation

• Dirk Hovy, Taylor Berg-Kirkpatrick, Ashish Vaswani, Eduard Hovy. Learning Whom to Trust with MACE. NAACL 2013.

Word vector representations

• Richard Socher, John Bauer, Christopher D. Manning and Andrew Y. Ng. Parsing with Compositional Vector Grammars. ACL 2013. Paper where constituents are also assigned vectors
• Shay B. Cohen, Karl Stratos, Michael Collins, Dean P. Foster, and Lyle Ungar. Experiments with Spectral Learning of Latent-Variable PCFGs. NAACL 2013. Paper where they use absolute value to fix spectral learning.
• Tomas Mikolov, Wen-tau Yih, Geoffrey Zweig. Linguistic Regularities in Continuous Space Word Representations. NAACL 2013. Testing on analogy questions
• William Blacoe, Elham Kashefi, Mirella Lapata. A Quantum-Theoretic Approach to Distributional Semantics. NAACL 2013.
• SENNA word embeddings

Word senses

• Jey Han Lau, Paul Cook and Timothy Baldwin. unimelb: Topic Modelling-based Word Sense Induction for Web Snippet Clustering. SemEval 2013. An hierarchical Dirichlet processing model trained for a different task wins

Relation extraction

• Sebastian Riedel, Limin Yao, Andrew McCallum, Benjamin M. Marlin. Relation Extraction with Matrix Factorization and Universal Schemas. NAACL 2013. Somewhere between Open Information Extraction and supervised relation extraction

Machine translation

• Yarin Gal, Phil Blunsom. A Systematic Bayesian Treatment of the IBM Alignment Models. NAACL 2013.

Semantic Roles

• Jiří Materna Parameter Estimation for LDA-Frames
• Jackie Chi Kit Cheung; Hoifung Poon; Lucy Vanderwende Probabilistic Frame Induction

Interesting Ideas/Applications

• Marta Recasens; Marie-Catherine de Marneffe; Christopher Potts The Life and Death of Discourse Entities: Identifying Singleton Mentions best short paper
• Amnon Lotan; Asher Stern; Ido Dagan TruthTeller: Annotating Predicate Truth