Comput. Linguistics 2014

16 papers
The 2014 edition of Computational Linguistics featured 18 papers centered on structural inference, semantic modeling, and sentiment analysis. Research themes included the adaptation of sentiment analysis to specialized domains, the detection of coordinated opinion spam, and the disentanglement of multi-target sentiment in complex sentences. Semantic processing was a significant area of inquiry, with studies addressing word sense induction, taxonomic abstraction for robust generalization, and similarity-driven semantic role induction via graph partitioning. Methodological developments emphasized optimization and efficiency, featuring work on Lagrangian dual decomposition for large-scale tasks and feature-frequency-adaptive online training for natural language processing. Structural parsing remained a core topic, with research exploring arc-eager parsing and global structural inference. Prolific authors contributing to this volume included Joakim Nivre, Noah A. Smith, and Ivan Titov. Additionally, the year's publications investigated neuro-symbolic systems through autonomous rule induction and the application of lexicographic semirings to speech and language processing.

Top Research Directions

The 16 research directions with Comput. Linguistics 2014 papers, ranked by paper count, next to 2013. Share is the fraction of the edition’s papers in the direction.

#Direction20142013Share 2014Share 20132013 rank
1Aspect Based Sentiment Analysis for Granular Opinion Mining106.2%0.0%—
2Automating Lexical Semantic Resource Construction106.2%0.0%—
3Detecting Deceptive Opinion Spam106.2%0.0%—
4Dual Decomposition for Structured Inference106.2%0.0%—
5Enforcing Global Structural Constraints on Local Classifiers106.2%0.0%—
6Enforcing Structural Constraints on Language Model Outputs106.2%0.0%—
7Form Meaning Mappings in Computational Linguistics106.2%0.0%—
8Latent Semantic Smoothing for Sparse Lexical Data106.2%0.0%—
9Mapping Syntactic Structures to Semantic Roles106.2%0.0%—
10Mining Specialized Jargon and Terminology from Unstructured Corpora106.2%0.0%—
11Mitigating Lexical Sparsity in Structured Semantic Resources106.2%0.0%—
12Modeling Language through Structured Semantic Frames106.2%0.0%—
13Resolving Domain Specific Sentiment Shift106.2%0.0%—
14Resolving Linguistic Variability in Semantic Mapping106.2%0.0%—
15The Syntactic Dependency Bottleneck in Semantic Parsing106.2%0.0%—
16Unsupervised Induction of Latent Hierarchical Structures106.2%0.0%—

Download all directions as CSV

Institutions

Institutions credited by Comput. Linguistics 2014 papers: a paper credits every institution named in its affiliations, once. 11 institutions share 5 credited papers.

#InstitutionPapersShare20132013 rank
1Google (United States) 240.0%0—
201cc3fy72 120.0%0—
3Bar-Ilan University 120.0%0—
4Carnegie Mellon University 120.0%0—
5Cornell University 120.0%0—
6Massachusetts Institute of Technology 120.0%0—
7Stanford University 120.0%0—
8University of Edinburgh 120.0%15
9University of Illinois Chicago 120.0%0—
10University of the Basque Country 120.0%11
11Uppsala University 120.0%0—

Download all institutions as CSV

About this data

Papers. Comput. Linguistics 2014 lists 16 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers. Comparisons with 2013 use shares, since the edition went from 18 to 16 papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 5 of 16 papers (31.2%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-18 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “Comput. Linguistics 2014”, https://lacuna.tiptreesystems.com/venue/comput-linguistics/2014.

Top Authors

AuthorPapers
Joakim Nivre2
Noah A. Smith2
Adrià de Gispert1
Andre Martins1
Anna Korhonen1
Arun Ahuja1
Bill Byrne1
Brian Roark1
Claire Cardie1
Daniel Fernández-González1
Dan Jurafsky1
Doug Downey1
Eneko Agirre1
Houfeng Wang1
Ivan Titov1
Izhak Shafran1
Kevin Gimpel1
Linlin Li1
Michael Riley1
Mirella Lapata1

Impactful Papers

Papers from Comput. Linguistics 2014 that shaped research clusters.

Influential

Papers

Title
Applications of Lexicographic Semirings to Problems in Speech and Language Processing
Arc-Eager Parsing with the Tree Constraint
Charles J. Fillmore
Constrained Arc-Eager Dependency Parsing
Feature-Frequency-Adaptive On-line Training for Fast and Accurate Natural Language Processing
Frame-Semantic Parsing
Identification of Multiword Expressions by Combining Multiple Linguistic Information Sources
Improved Estimation of Entropy for Evaluation of Word Sense Induction
Learning Representations for Weakly Supervised Natural Language Processing Tasks
Phrase Dependency Machine Translation with Quasi-Synchronous Tree-to-Tree Features
Probabilistic Distributional Semantics with Latent Variable Models
Pushdown Automata in Statistical Machine Translation
Random Walks for Knowledge-Based Word Sense Disambiguation
Sampling Tree Fragments from Forests
Sentiment Analysis and Opinion Mining Bing Liu (University of Illinois at Chicago) Morgan & Claypool (Synthesis Lectures on Human Language Technologies, edited by Graeme Hirst, 5(1)), 2012, 167 pp; pa
Similarity-Driven Semantic Role Induction via Graph Partitioning