Chinese named entity recognition using lexicalized hmms
This presentation is the property of its rightful owner.
Sponsored Links
1 / 22

Chinese Named Entity Recognition using Lexicalized HMMs PowerPoint PPT Presentation


  • 88 Views
  • Uploaded on
  • Presentation posted in: General

Chinese Named Entity Recognition using Lexicalized HMMs. Advisor : Dr. Hsu Presenter : Zih-Hui Lin Author :Guohong Fu, Kang-Kwong Luke. Outline. Motivation Objective Introduction NER as Known Word Tagging Known Word Segmentation Lexicalized HMM Tager Conclusions

Download Presentation

Chinese Named Entity Recognition using Lexicalized HMMs

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Chinese named entity recognition using lexicalized hmms

Chinese Named Entity Recognition using Lexicalized HMMs

Advisor : Dr. Hsu

Presenter : Zih-Hui Lin

Author :Guohong Fu, Kang-Kwong Luke


Chinese named entity recognition using lexicalized hmms

Outline

  • Motivation

  • Objective

  • Introduction

  • NER as Known Word Tagging

  • Known Word Segmentation

  • Lexicalized HMM Tager

  • Conclusions

  • Future Research


Chinese named entity recognition using lexicalized hmms

Motivation

  • A HMM-based tagger don’t provide contextual word information, which sometimes gives strong evidence for NER.

  • Some learning methods such as ME and SVMs usually need much more time in training and tagging.


Chinese named entity recognition using lexicalized hmms

Objective

  • Our system is able to integrate both the internal formation patterns and the surrounding contextual clues for NER under the framework of HMMs

  • As a result, the performance of the system can be improved without losing its efficiency in training and tagging.


Introduction

Introduction

  • We develop a two-stage NERsystem for Chinese.

    • Given a sentence, a known word bigram model is first applied to segment it into a meaningful sequence of known words.

    • Then, a lexicalized HMM tagger is used to assign each known word a proper hybrid tag that indicates its pattern in forming an entity and the category of the formed entity.


Introduction cont

Introduction(cont.)

  • Our system is able to explore three types of features

    • entity-internal formation patterns

    • contextual word evidence

    • contextual category information

  • As a consequence, the system’s performance can be improved without losing its efficiency in training and processing.


Ner as known word tagging categorization of entities

NER as Known Word Tagging- Categorization of Entities

  • We use the same named entity tag set as defined in the IEER-99 Mandarin named entity task, these entity categories are further encoded using twelve different abbreviated SGML tags.

  • Our system will also assign each common word in the input sentence a proper POS tag. (Peking University POS tag-set)


Ner as known word tagging patterns of known words in ner

NER as Known Word Tagging- Patterns of known words in NER

  • A known word w may take one of the following four patterns to present itself during NER:

    • w is an independent named entity ISE

    • w is the beginning component of a named entity  BOE

    • w is at the middle of a named entity MOE

    • w is at the end of a named entity ISE

      • Example:

        • “温家宝/总理/”

          “<BOE>温</BOE><MOE>家</MOE><EOE>宝</EOE><ISE>总理</ISE>”.


Ner as known word tagging ner as known word tagging

NER as Known Word Tagging- NER as known word tagging

  • We define a hybrid tag set by merging the category tags and the pattern tags.


Known word segmentation

Known Word Segmentation

  • To find the most appropriate segmentation that

    maximizes the conditional probability P(W | C) , i.e.

    • P (w | wt-1) denotes the known word bigram probability, which can be estimated from a segmented corpus using maximum likelihood estimation (MLE).


Lexicalized hmm tager lexicalized hmms

Lexicalized HMM Tager- Lexicalized HMMs

  • We employ the uniformly lexicalized models to perform the tagging of known words for Chinese NER.

  • To find an appropriate sequence of hybrid tags

    that maximizes the conditional probability P(T |W) , namely


Lexicalized hmm tager lexicalized hmms cont

Lexicalized HMM Tager- Lexicalized HMMs (cont.)

  • Two types of approximations are employed to simplify the general model.

    • The firs approximation is based on the independent hypothesis used in standard HMMs:

    • The second pproximation follows the notion of the lexicalization technique,


Lexicalized hmm tager lexicalized hmms cont1

Lexicalized HMM Tager- Lexicalized HMMs (cont.)

  • Because MLE will yield zero will yield zero probabilities for any cases that are not observed in the training data. To solve this problem, we employ the linear interpolation smoothing technique .


Lexicalized hmm tager lattice based tagging

Lexicalized HMM Tager- Lattice-Based Tagging

  • In our implementation, we employ the classical Viterbi algorithm to find the most probable sequence of hybrid tags for a given sequence of known words, which works in three major steps as follows:

    • The generation of candidate tags

    • The decoding of the best tag sequence

    • The conversion of the results


Lexicalized hmm tager inconsistent tagging

Lexicalized HMM Tager- Inconsistent Tagging

  • Our system may yield two types of inconsistent tagging :

    • pattern inconsistency

      • when two adjacent known words are assigned inconsistent pattern tags such as “ISE:MOE” or “ISE:EOE”.

    • class inconsistency

      • two adjacent known words are labeled with different category-tags while at the same time

        • <CPN-BOE>张</CPN-BOE><Vg-MOW>晓</Vg-MOW><CPN-EOE>华</CPN-EOE>


Experiments experimental measures

Experiments - Experimental Measures

  • F-measure is a weighted harmonic mean of precision and recall.

    • R=

    • P=

    • β is the weighing coefficient

correctly recognized NEs

manually annotated corpus

correctly recognized NEs

recognized by the system


Experiments data

Experiments Data


Experiments experimental results

Experiments - Experimental Results

  • Consequently, our first aim is to examine how the use of thelexicalization technique affects the performance of our system.


Experiments experimental results cont

Experiments - Experimental Results(cont.)

  • To investigate whether the word-level mode or the character-level model is more effective for Chinese NER.


Experiments experimental results cont1

Experiments - Experimental Results(cont.)

  • to compare our system with other public systems for Chinese NER.


Conclusions

Conclusions

  • The experimental results indicate

    • on different public corpora show that the NER performance can be significantly enhanced using lexicalization techniques.

    • character-level tagging are comparable to and may even outperform known-word based tagging when a lexicalized method is applied.


Future directions

Future Directions

  • Our current tagger is a purely statistical system; it will inevitably suffer from the problem of data sparseness, particularly in open-domain applications.

  • Our system usually fails to yield correct results for some complicated NEs such as nested organization names.


  • Login