Integer linear programming inference for conditional random fields

By Dan Roth, Wen-tau Yih. 2005

215 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

Citations in the corpus

Solving General Arithmetic Word Problems (2016, methodology): “This has been successfully used to incorporate world knowledge at inference time, as well as getting around the need for large amounts of jointly annotated data for structured prediction (Roth and Yih, 2005; Punyakanok et al., 2005; Punyakanok et al., 2008; Clarke and Lapata, 2006; Barzilay and Lapa”
Learning to Branch in Mixed Integer Programming (2016, methodology): “Recently, discrete optimization has been successfully lever-aged to improve machine learning (ML) methodology (Roth and Yih 2005; Bertsimas, King, and Mazumder 2015).”
Towards Open Intent Discovery for Conversational Text (2019, methodology): “In the second approach, we adopt the idea of reducing the Viterbi decoding algorithm to a graph shortest path problem, solvable by Integer Linear Programming [41].”
An Introduction to Conditional Random Fields for Relational Learning (2007, background): “, 2004], finding semantic roles in text [Roth and Yih, 2005], identifying the sources of opinions [Choi et al.”
Global inference for sentence compression : an integer linear programming approach (2008, methodology): “Contrary to most other NLP work using ILP (a notable exception is Roth & Yih, 2005 ), we do not view compression generation as a two stage process where learning and inference are carried out sequentially (i.e., first a local classifier hypothesizes a list of possible answers and then the best answ”
Efficient Inference in Large Conditional Random Fields (2006, methodology): “These results can be roughly compared to [14], who applied (constrained) CRFs to the SRL argument labelling task.”
An Introduction to Conditional Random Fields (2010, background): “Since then, linear-chain CRFs have been applied to many problems in natural language processing, including named-entity recognition [72], feature induction for NER [71], shallow parsing [108, 120], identifying protein names in biology abstracts [107], segmenting addresses in Web pages [26], informat”
Training structural SVMs when exact inference is intractable (2008, methodology): “Therefore, the partition function is approximated (Culotta et al., 2007; He et al., 2004; Kumar & Hebert, 2003; Vishwanathan et al., 2006), or the model is simpli.ed to make the partition function tractable (Sutton & McCallum, 2005), or CRF max-likelihood training is replaced with Perce”
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling (2017, background): “, 2005) as well as declarative constraints (Punyakanok et al., 2008; Roth and Yih, 2005).”
A Tutorial on Dual Decomposition and Lagrangian Relaxation for Inference in Natural Language Processing (2012, unknown): “1 Combined Constituency and Dependency Parsing Rush et al. (2010) describe an algorithm for finding the highest scoring lexicalized context-free parse tree for an input sentence, under a combination of two models: a lexicalized probabilistic context-free grammar, and a discriminative dependency pars”
A Primal Dual Formulation For Deep Learning With Constraints (2019, methodology): “These include the work by Xu et al. [2018], Mehta et al.”
The Importance of Syntactic Parsing and Inference in Semantic Role Labeling (2008, background): “Some work on combining statistical and declarative constrains has already started and is reported in (Roth and Yih, 2005).”
Structured learning with constrained conditional models (2012, methodology): “Comparing these models is outside the scope of this paper; the interested reader is referred to Sarawagi and Cohen (2004) and Roth and Yih (2005).”
Guiding Semi-Supervision with Constraint-Driven Learning (2007, methodology): “(Punyakanok et al., 2005; Toutanova et al., 2005; Roth and Yih, 2005).”
An Approximate, Efficient LP Solver for LP Rounding (2013, methodology): “Graphical Models Heuristic Semantic role labeling [18], Clustering [21].”
Named Entity Recognition in the Medical Domain with Constrained CRF Models (2017, background): “The work most related to our approach for applying constraints with CRF decoding is (Culotta and McCallum, 2004; Roth and Yih, 2005; Kristjansson et al., 2004).”
A Joint Model for Extended Semantic Role Labeling (2011, methodology): “Integer linear programs were used by Roth and Yih (2005) to add general constraints for inference with conditional random ﬁelds.”
Identifying Relations for Open Information Extraction (2011, unknown): “have shown how to incorporate constraints into CRF learners (Roth and Yih, 2005).”