The Effect of Excluding Out of Domain Training Data from Supervised Named-Entity Recognition
نویسنده
چکیده
Supervised named-entity recognition (NER) systems perform better on text that is similar to its training data. Despite this, systems are often trained with as much data as possible, ignoring its relevance. This study explores if NER can be improved by excluding out of domain training data. A maximum entropy model is developed and evaluated twice with each domain in Stockholm-Umeå Corpus (SUC), once with all data and once with only in-domain data. For some domains, excluding out of domain training data improves tagging, but over the entire corpus it has a negative effect of less than two percentage points (both for strict and fuzzy matching).
منابع مشابه
Improvement of Chemical Named Entity Recognition through Sentence-based Random Under-sampling and Classifier Combination
Chemical Named Entity Recognition (NER) is the basic step for consequent information extraction tasks such as named entity resolution, drug-drug interaction discovery, extraction of the names of the molecules and their properties. Improvement in the performance of such systems may affects the quality of the subsequent tasks. Chemical text from which data for named entity recognition is extracte...
متن کاملTraining and Evaluating a German Named Entity Recognizer with Semantic Generalization
We present a freely available optimized Named Entity Recognizer (NER) for German. It alleviates the small size of available NER training corpora for German with distributional generalization features trained on large unlabelled corpora. We vary the size and source of the generalization corpus and find improvements of 6% F1 score (in-domain) and 9% (out-of-domain) over simple supervised training.
متن کاملسیستم شناسایی و طبقه‌بندی موجودیت‌های اسمی در متون زبان فارسی بر پایه شبکه عصبی
Named Entity Recognition (NER) is a fundamental task in natural language processing and also known as a subset of information extraction. We seek to locate and classify named entities in text into predefined categories such as the names of persons, organizations, locations, expressions of times, etc. Named Entity Recognition for English texts has been researched widely for the past years, howev...
متن کاملDomain adaptive bootstrapping for named entity recognition
Bootstrapping is the process of improving the performance of a trained classifier by iteratively adding data that is labeled by the classifier itself to the training set, and retraining the classifier. It is often used in situations where labeled training data is scarce but unlabeled data is abundant. In this paper, we consider the problem of domain adaptation: the situation where training data...
متن کاملThe Effect of Answer Patterns for Supervised Named Entity Recognition in Thai
In this paper, we present Thai named entity recognition (NER) systems using supervised Conditional Random Fields (CRFs) with various answer patterns to find out whether different answer patterns would affect the performance of the systems. Every system used the same set of features except the answers in the training corpus. There are 5 patterns of answer used in this study. The results show tha...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017