Shallow Parsing System

A Shallow Parsing System is a Text Segmentation System that can solve a Shallow Parsing Task by implementing a Shallow Parsing Algorithm.

• AKA: Light Parsing System.
• Context:
  • It can range from being a Shallow Syntactic Parsing System to being a Shallow Semantic Parsing System.
  • It can use Shallow Neural Network to train the system to a learn a shallow parsing task.
• Example(s):
  • a Memory-Based Shallow Parsing System (Sang, 2002),
  • a Shallow Parsing System with Conditional Random Fields (e.g. Sha & Pereira, 2003).
  • …
• Counter-Example(s):
  • Deep Parsing System.
• See: Chunking System, Phrase Chunking System, Semantic Role Labeler, Syntactic Chunking System, Semantic Role Labeling, Parsing, Sentence (Linguistics), Noun, Noun Phrase, Regular Expression, Machine Learning, Natural Language Processing, Lexical Analysis.

---

---

References

2019

• (Wikipedia, 2019) ⇒ https://en.wikipedia.org/wiki/Shallow_parsing Retrieved:2019-11-22.
  • Shallow parsing (also chunking, "light parsing") is an analysis of a sentence which first identifies constituent parts of sentences (nouns, verbs, adjectives, etc.) and then links them to higher order units that have discrete grammatical meanings (noun groups or phrases, verb groups, etc.). While the most elementary chunking algorithms simply link constituent parts on the basis of elementary search patterns (e.g. as specified by Regular Expressions), approaches that use machine learning techniques (classifiers, topic modeling, etc.) can take contextual information into account and thus compose chunks in such a way that they better reflect the semantic relations between the basic constituents. That is, these more advanced methods get around the problem that combinations of elementary constituents can have different higher level meanings depending on the context of the sentence. It is a technique widely used in natural language processing. It is similar to the concept of lexical analysis for computer languages. Under the name of the Shallow Structure Hypothesis, it is also used as an explanation for why second language learners often fail to parse complex sentences correctly.

2006

• (Garat, 2006) ⇒ Diego Garat (2006) "Shallow Parsing Based on Comma Values". In: Sichman J.S., Coelho H., Rezende S.O. (eds) Advances in Artificial Intelligence - IBERAMIA-SBIA 2006. IBERAMIA 2006, SBIA 2006. Lecture Notes in Computer Science, vol 4140. DOI:10.1007/11874850_53

2003

• (Sha & Pereira, 2003) ⇒ Fei Sha, and Fernando Pereira (2003). "Shallow Parsing with Conditional Random Fields". Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2003).
  • QUOTE: Sequence analysis tasks in language and biology are often described as mappings from input sequences to sequences of labels encoding the analysis. In language processing, examples of such tasks include part-of-speech tagging, named-entity recognition, and the task we shall focus on here, shallow parsing. Shallow parsing identifies the non-recursive cores of various phrase types in text, possibly as a precursor to full parsing or information extraction (Abney, 1991). The paradigmatic shallow parsing problem is NP chunking, which finds the nonrecursive cores of noun phrases called base NPs. The pioneering work of Ramshaw and Marcus (1995) introduced NP chunking as a machine-learning problem, with standard datasets and evaluation metrics (...)

     Conditional random fields (CRFs) bring together the best of generative and classification models. Like classification models, they can accommodate many statistically correlated features of the inputs, and they are trained discriminatively. But like generative models, they can trade off decisions at different sequence positions to obtain a globally optimal labeling. Lafferty et al. (2001) showed that CRFs beat related classification models as well as HMMs on synthetic data and on a part-of-speech tagging task.

    In the present work, we show that CRFs beat all reported single-model NP chunking results on the standard evaluation dataset, and are statistically indistinguishable from the previous best performer, a voting arrangement of 24 forward - and backward-looking support-vector classifiers (Kudo and Matsumoto, 2001). To obtain these results, we had to abandon the original iterative scaling CRF training algorithm for convex optimization algorithms with better convergence properties. We provide detailed comparisons between training methods.

    The generalized perceptron proposed by Collins (2002) is closely related to CRFs, but the best CRF training methods seem to have a slight edge over the generalized perceptron.

2002a

• (Collins, 2002) ⇒ Michael Collins (2002). "Discriminative Training Methods for Hidden Markov Models: Theory and Experiments with Perceptron Algorithms". In: Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing (EMNLP 2002), Volume 10. DOI:10.3115/1118693.1118694

2002b

• (Sang, 2002) ⇒ Erik F. Tjong Kim Sang (2002). "Memory-Based Shallow Parsing". In: Journal of Machine Learning Research 2 (2002) 559-594.

2002c

• (Molina & Pla, 2002) ⇒ Antonio Molina, Ferran Pla (2002). "Shallow Parsing using Specialized HMMs". In: Journal of Machine Learning Research 2 (2002) 595-613.

2001a

• (Lafferty et al., 2001) ⇒ John D. Lafferty, Andrew McCallum, and Fernando Pereira (2001). "Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data".

2001b

• (Kudo & Matsumoto, 2001) ⇒ Taku Kudo, and Yuji Matsumoto (2001). "Chunking with Support Vector Machines". DOI:10.3115/1073336.1073361.

2000

• (Munoz et al., 2000) ⇒ Marcia Munoz, Vasin Punyakanok, Dan Roth, and Dav Zimak (2002). "A Learning Approach to Shallow Parsing". In: EMNLP 1999, arxiv: 0008022.

1995

• (Ramshaw & Marcus, 1995) ⇒ Lance A. Ramshaw, and Mitchell P. Marcus (1995). "Text Chunking Using Transformation-Based Learning". In: Armstrong S., Church K., Isabelle P., Manzi S., Tzoukermann E., Yarowsky D. (eds) Natural Language Processing Using Very Large Corpora. Text, Speech and Language Technology, vol 11. DOI:10.1007/978-94-017-2390-9_10.

1991

• (Abney, 1991) ⇒ Steven P. Abney (1991). "Parsing By Chunks". In Principle-based parsing (pp. 257-278). Springer, Dordrecht. DOI:10.1007/978-94-011-3474-3_10.

---