A Linear Programming Formulation for Global Inference in Natural Language Tasks

By Dan Roth, Wen-tau Yih. 2004

579 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Solving General Arithmetic Word Problems (2016, methodology): “We deﬁne Score( E ) of an expression E in terms of the above scoring functions and a scaling parameter w I RR as follows: P AIR ( q i , q j , LCA ( q i , q j , T )) Our ﬁnal expression tree is an outcome of a constrained optimization process, following (Roth and Yih, 2004; Chang et al., 2012).”
Parsing Algebraic Word Problems into Equations (2015, methodology): “Our work is also related to research in using ILP to enforce global constraints in NLP appli- cations (Roth and Yih, 2004).”
GLM-130B: An Open Bilingual Pre-trained Model (2022, methodology): “For example, CoNLL04 only contains five different relations; the most diverse NYT dataset contains 24 Freebase predicates.”
Mitigating Gender Bias in Natural Language Processing: Literature Review (2019, background): “tional model (Roth and Yih, 2004), which takes an existing model’s optimization function and constrains that function to ensure its predictions fit defined conditions.”
Modeling Biological Processes for Reading Comprehension (2014, methodology): “Table 2 states the constraints we include, which are expressed as linear inequalities over output variables using standard techniques (e.g., (Roth and Yih, 2004)).”
Question Answering via Integer Programming over Semi-Structured Knowledge (2016, methodology): “ILP based discrete optimization has been successful in several NLP tasks [ Roth and Yih, 2004; Chang et al. , 2010; Berant et al. , 2010; Srikumar and Roth, 2011; Goldwasser and Roth, 2011 ] .”
Solving Hard Coreference Problems (2019, methodology): “straints, and make use of an ILP driven framework (Roth and Yih, 2004) to make decisions.”
Question Answering as Global Reasoning Over Semantic Abstractions (2018, background): “Search-based reasoning systems have been successful in several NLP areas (Roth and Yih 2004; Chang et al. 2010; Berant, Dagan, and Goldberger 2010; Srikumar and Roth 2011; Goldwasser and Roth 2011; Schüller 2014; Fei et al. 2015).”
Mapping to Declarative Knowledge for Word Problem Solving (2017, methodology): “More recent approaches tried to incorporate knowledge in the form of constraints or expectations from the output (Roth and tau Yih, 2004; wei Chang et al., 2007; Chang et al., 2012; Ganchev et al., 2010; Smith and Eisner, 2006; Naseem et al., 2010; Bisk and Hockenmaier, 2012; Gimpel and Bansal,…”
Span-based Joint Entity and Relation Extraction with Transformer Pre-training (2019, background): “• CoNLL04: The CoNLL04 dataset [27] contains sentences with annotated named entities and relations extracted from news articles.”
Structured Learning with Approximate Inference (2007, background): “Second, approximations can respond to parameter changes in such a way that standard learning algorithms are misled.”
Unified Structure Generation for Universal Information Extraction (2022, unknown): “, 2006); CoNLL03 (Tjong Kim Sang and De Meulder, 2003), CoNLL04 (Roth and Yih, 2004), SciERC (Luan et al.”
A Study of Global Inference Algorithms in Multi-document Summarization (2007, methodology): “This includes applications to relation and entity classiﬁcation [19], sentence compression [3], temporal link analysis [2], as well as syntactic and semantic parsing [17, 18].”
Joint Constrained Learning for Event-Event Relation Extraction (2020, methodology): “Though previous efforts have been devoted to preserving logical consistency through inference or structured learning (Roth and Yih, 2004; Roth and tau Yih, 2007; Chang et al., 2008), this is difﬁcult to do in the context of neural networks.”
Structured Models for Fine-to-Coarse Sentiment Analysis (2007, background): “, 2000), entity labeling and relation extraction (Roth and Yih, 2004), and part-of-speech tagging and chunking (Sutton et al.”
Structured Prediction as Translation between Augmented Natural Languages (2021, methodology): “CoNLL04 Boston University’s Michael D. Papagiannis said he believes the crater was created 100 million years ago when a 50-mile-wide meteorite slammed into the Earth.”
Context-Aware Representations for Knowledge Base Relation Extraction (2017, background): “Roth and Yih (2004) have combined named entity recognition and relation extraction in a structured prediction approach to improve both tasks.”