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
Book ChapterDOI
Voting between multiple data representations for text chunking
Hong Shen,Anoop Sarkar +1 more
TL;DR: This paper focuses on choosing specific data representations combined with simple majority voting and achieves high scores for arbitrary phrase identification and Base NP identification on the community standard CoNLL-2000 data set.
Proceedings ArticleDOI
Mention Detection Crossing the Language Barrier
Imed Zitouni,Radu Florian +1 more
TL;DR: Results show that propagated features from English help improve the source-language system performance even when used in conjunction with all feature types built from the source language.
Proceedings Article
Word-based and Character-based Word Segmentation Models: Comparison and Combination
TL;DR: A theoretical and empirical comparative analysis of the two dominant categories of approaches in Chinese word segmentation shows that, in spite of similar performance overall, the two models produce different distribution of segmentation errors, in a way that can be explained by theoretical properties of theTwo models.
Proceedings Article
The Hungarian Gigaword Corpus
TL;DR: The paper reports on the development of the Hungarian Gigaword Corpus, an extended new edition of the Hungary National Corpus, with upgraded and redesigned linguistic annotation and an increased size of 1.5 billion tokens.
Proceedings ArticleDOI
BioMegatron: Larger Biomedical Domain Language Model
Hoo-Chang Shin,Yang Zhang,Evelina Bakhturina,Raul Puri,Mostofa Patwary,Mohammad Shoeybi,Raghav Mani +6 more
TL;DR: This work empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer.
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.