Combining Lexical, Syntactic, and Semantic Features with Maximum Entropy Models for Information Extraction
By N. Kambhatla. 2004
502 citations recorded by the source corpus.
Extracting semantic relationships between entities is challenging because of a paucity of annotated data and the errors induced by entity detection modules. We employ Maximum Entropy models to combine diverse lexical, syntactic and semantic features derived from the text. Our system obtained competitive results in the Automatic Content Extraction (ACE) evaluation. Here we present our general approach and describe our ACE results.
Subfields: Artificial Intelligence, Natural Language Processing, Information Extraction
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
- Zhiyuan Liu
- Maosong Sun
- Mohit Bansal
- Luke S. Zettlemoyer
- Percy Liang
- Christopher D. Manning
- Jianfeng Gao
- Hannaneh Hajishirzi
In Natural Language Processing
- Zhiyuan Liu
- Luke S. Zettlemoyer
- Percy Liang
- Maosong Sun
- Mohit Bansal
- Christopher D. Manning
- Kai-Wei Chang
- Hannaneh Hajishirzi
In Information Extraction
Citations in the corpus
- Modifying Memories in Transformer Models (2020, background): “ter language understanding, Transformers may also replace or assist traditional knowledge bases (KBs) that are either manually curated or require significant amount of supervision (Roth and Yih, 2002; Kambhatla, 2004; Surdeanu and Ji, 2014). Different from conventional KBs that explicitly memorize fa”
- Matching the Blanks: Distributional Similarity for Relation Learning (2019, background): “In a first group, supervised (Kambhatla, 2004; GuoDong et al., 2005; Zeng et al., 2014), or distantly supervised relation extractors (Mintz et al.”
- Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths (2015, methodology): “Traditional relation classification approaches rely largely on feature representation (Kambhatla, 2004), or kernel design (Zelenko et al., 2003; Bunescu and Mooney, 2005).”
- Graph Convolution over Pruned Dependency Trees Improves Relation Extraction (2018, background): “Traditional feature-based models are able to represent dependency information by featurizing dependency trees as overlapping paths along the trees (Kambhatla, 2004).”
- Towards Understanding Gender Bias in Relation Extraction (2019, methodology): “Early on, learning algorithms for relation extraction models were typically categorized as supervised, including feature-based methods (Kambhatla, 2004; Zhou et al., 2005; Zhao and Grishman, 2005) and kernel-based methods (Lodhi et al., 2002; Zelenko et al., 2003), or semi-supervised (Brin, 1998;…”
- A Brief Survey of Text Mining: Classification, Clustering and Extraction Techniques (2017, methodology): “Many studies using the classification approach for relation extraction have been done such as [25, 26, 59, 72, 77].”
- Cross-Sentence N-ary Relation Extraction with Graph LSTMs (2017, methodology): “Binary relation extraction The traditional featurebased methods rely on carefully designed features to learn good models, and often integrate diverse sources of evidence such as word sequences and syntax context (Kambhatla, 2004; GuoDong et al., 2005; Boschee et al., 2005; Suchanek et al., 2006; Cha”
- Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme (2017, methodology): “Existing methods for relation classification can also be divided into handcrafted feature based methods (Rink, 2010; Kambhatla, 2004) and neural network based methods (Xu, 2015a; Zheng et al., 2016; Zeng, 2014; Xu, 2015b; dos Santos, 2015).”
- Relation Classification via Recurrent Neural Network (2015, methodology): “in modeling longdistance patterns. 2 Related Work As mentioned, the conventional approaches to relation classification are based on pattern matching, and can be categorized into feature-based methods (Kambhatla, 2004; Suchanek et al., 2006) and kernel-based methods (Bunescu and Mooney, 2005; Mooney a”
- More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction (2020, methodology): “747 One typical SRE approach is feature-based methods (Kambhatla, 2004; Zhou et al., 2005; Jiang and Zhai, 2007; Nguyen et al., 2007), which design lexical, syntactic and semantic features for entity pairs and their corresponding context, and then input these features into relation classifiers.”
- Relation Classification via Convolutional Deep Neural Network (2014, methodology): “In feature-based methods, a diverse set of strategies have been exploited to convert the classification clues (such as sequences and parse trees) into feature vectors (Kambhatla, 2004; Suchanek et al., 2006).”
- Open Information Extraction from the Web (2007, methodology): “Second, it uses this labeled data to train a Naive Bayes classifier, which is then used by the Extractor module.”
- Semi-supervised Relation Extraction with Large-scale Word Clustering (2011, methodology): “Then the feature based method explicitly extracts a variety of lexical, syntactic and semantic features for statistical learning, either generative or discriminative (Miller et al., 2000; Kambhatla, 2004; Boschee et al., 2005; Grishman et al., 2005; Zhou et al., 2005; Jiang and Zhai, 2007).”