Text Chunking Using Transformation-Based Learning
Lance Ramshaw,Mitchell Marcus +1 more
- pp 157-176
Reads0
Chats0
TLDR
This work has shown that the transformation-based learning approach can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive “baseNP” chunks.Abstract:
Transformation-based learning, a technique introduced by Eric Brill (1993b), has been shown to do part-of-speech tagging with fairly high accuracy. This same method can be applied at a higher level of textual interpretation for locating chunks in the tagged text, including non-recursive “baseNP” chunks. For this purpose, it is convenient to view chunking as a tagging problem by encoding the chunk structure in new tags attached to each word. In automatic tests using Treebank-derived data, this technique achieved recall and precision rates of roughly 93% for baseNP chunks (trained on 950K words) and 88% for somewhat more complex chunks that partition the sentence (trained on 200K words). Working in this new application and with larger template and training sets has also required some interesting adaptations to the transformation-based learning approach.read more
Citations
More filters
Web Entity Detection for Semi-structured Text Data Records with Unlabeled Data
TL;DR: A framework for named entity detection from Web content associated with semi-structured text data records is proposed, by exploiting the inherent structure via a transformation process facilitating collective detection.
Journal ArticleDOI
A top-down information theoretic word clustering algorithm for phrase recognition
TL;DR: This paper designs a top-down divisive clustering algorithm that ensures maximal information gain in the use of unlabeled data via clustering similar words, and implements it with state-of-the-art performance on the shallow parsing and base-chunking benchmarks.
Proceedings ArticleDOI
Integrating Genetic Algorithms with Conditional Random Fields to Enhance Question Informer Prediction
TL;DR: A hybrid approach that integrates genetic algorithms (GAs) with CRF to optimize feature subset selection in CRF-based question informer prediction models and shows that the proposed hybrid GA-CRF model improves the accuracy of question informers prediction of traditional CRF models.
Proceedings ArticleDOI
Impact of Tokenization on Language Models: An Analysis for Turkish
TL;DR: Morphological and word-level tokenizers outperform de-facto tok- 017 enizers in particular cases and mini models can be competitive to larger state-of-the-art models, such that a 14-times smaller model can recover 94% of the performance of a larger model.
Proceedings ArticleDOI
Neural Particle Smoothing for Sampling from Conditional Sequence Models
Chu-Cheng Lin,Jason Eisner +1 more
TL;DR: This work introduces neural particle smoothing, a sequential Monte Carlo method for sampling annotations of an input string from a given probability model that looks ahead to the end of the input string by means of a right-to-left LSTM.
References
More filters
Book ChapterDOI
Parsing By Chunks
TL;DR: The typical chunk consists of a single content word surrounded by a constellation of function words, matching a fixed template, and the relationships between chunks are mediated more by lexical selection than by rigid templates.
Proceedings ArticleDOI
A Stochastic Parts Program and Noun Phrase Parser for Unrestricted Text
TL;DR: The authors used a linear-time dynamic programming algorithm to find an assignment of parts of speech to words that optimizes the product of (a) lexical probabilities (probability of observing part of speech i given word i) and (b) contextual probabilities (pb probability of observing n following partsof speech).
Proceedings Article
Some advances in transformation-based part of speech tagging
TL;DR: In this article, a rule-based approach to tagging unknown words is described, where the tagger-can be extended into a k-best tagger, where multiple tags can be assigned to words in some cases of uncertainty.
Journal ArticleDOI
Performance structures: A psycholinguistic and linguistic appraisal☆
James Paul Gee,François Grosjean +1 more
TL;DR: In this paper, two lines of research are combined to deal with a long-standing problem in both fields: why the performance structures of sentences (structures based on experimental data, such as pausing and parsing values) are not fully accountable for by linguistic theories of phrase structure.
Book
A corpus-based approach to language learning
TL;DR: A learning algorithm is described that takes a small structurally annotated corpus of text and a larger unannotated corpus as input, and automatically learns how to assign accurate structural descriptions to sentences not in the training corpus.