Results 1 - 10
of
32
Recognizing named entities in tweets
- In Proc. of ACL
, 2011
"... All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately. ..."
Abstract
-
Cited by 73 (1 self)
- Add to MetaCart
(Show Context)
All in-text references underlined in blue are linked to publications on ResearchGate, letting you access and read them immediately.
Domain Adaptation of Rule-based Annotators for Named-Entity Recognition Tasks
- In EMNLP (To appear
, 2010
"... Named-entity recognition (NER) is an important task required in a wide variety of applications. While rule-based systems are appealing due to their well-known “explainability,” most, if not all, state-of-the-art results for NER tasks are based on machine learning techniques. Motivated by these resul ..."
Abstract
-
Cited by 19 (7 self)
- Add to MetaCart
(Show Context)
Named-entity recognition (NER) is an important task required in a wide variety of applications. While rule-based systems are appealing due to their well-known “explainability,” most, if not all, state-of-the-art results for NER tasks are based on machine learning techniques. Motivated by these results, we explore the following natural question in this paper: Are rule-based systems still a viable approach to named-entity recognition? Specifically, we have designed and implemented a high-level language NERL on top of SystemT, a general-purpose algebraic information extraction system. NERL is tuned to the needs of NER tasks and simplifies the process of building, understanding, and customizing complex rule-based named-entity annotators. We show that these customized annotators match or outperform the best published results achieved with machine learning techniques. These results confirm that we can reap the benefits of rule-based extractors ’ explainability without sacrificing accuracy. We conclude by discussing lessons learned while building and customizing complex rule-based annotators and outlining several research directions towards facilitating rule development. 1
Joint inference of named entity recognition and normalization for tweets
- In Proceedings of the Association for Computational Linguistics
, 2012
"... Tweets represent a critical source of fresh information, in which named entities occur frequently with rich variations. We study the problem of named entity normalization (NEN) for tweets. Two main challenges are the errors propagated from named entity recognition (NER) and the dearth of information ..."
Abstract
-
Cited by 15 (0 self)
- Add to MetaCart
(Show Context)
Tweets represent a critical source of fresh information, in which named entities occur frequently with rich variations. We study the problem of named entity normalization (NEN) for tweets. Two main challenges are the errors propagated from named entity recognition (NER) and the dearth of information in a single tweet. We propose a novel graphical model to simultaneously conduct NER and NEN on multiple tweets to address these challenges. Particularly, our model introduces a binary random variable for each pair of words with the same lemma across similar tweets, whose value indicates whether the two related words are mentions of the same entity. We evaluate our method on a manually annotated data set, and show that our method outperforms the baseline that handles these two tasks separately, boosting the F1 from 80.2 % to 83.6 % for NER, and the Accuracy from 79.4% to 82.6 % for NEN, respectively. 1
Conceptual Modeling Foundations for a Web of Knowledge
"... The semantic web purports to be a web of knowledge that can answer our questions, help us reason about everyday problems as well as scientific endeavors, and service many of our wants and needs. Researchers and others expound various views about exactly what this means. Here we propose an answer w ..."
Abstract
-
Cited by 11 (9 self)
- Add to MetaCart
The semantic web purports to be a web of knowledge that can answer our questions, help us reason about everyday problems as well as scientific endeavors, and service many of our wants and needs. Researchers and others expound various views about exactly what this means. Here we propose an answer with conceptual modeling as its foundation. We define a web of knowledge as a collection of interconnected knowledge bundles superimposed over a web of documents. Knowledge bundles are conceptual model instances augmented with facilities that provide for both extensional and intensional facts, for linking between knowledge bundles yielding a web of data, and for linking to an underlying document collection providing a means of authentication. We formally define both the component parts of these augmented conceptual models and their synergistic interconnections. As for practicalities, we discuss problems regarding the potentially high cost of constructing a web of knowledge and explain how they may be mitigated. We also discuss usage issues and show how untrained users can interact with and gain benefit from
Hierarchical Joint Learning: Improving Joint Parsing and Named Entity Recognition with Non-Jointly Labeled Data
"... One of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms single-task models learned from the same data, but still underperforms compared to single-task models learned on the more a ..."
Abstract
-
Cited by 11 (0 self)
- Add to MetaCart
One of the main obstacles to producing high quality joint models is the lack of jointly annotated data. Joint modeling of multiple natural language processing tasks outperforms single-task models learned from the same data, but still underperforms compared to single-task models learned on the more abundant quantities of available single-task annotated data. In this paper we present a novel model which makes use of additional single-task annotated data to improve the performance of a joint model. Our model utilizes a hierarchical prior to link the feature weights for shared features in several single-task models and the joint model. Experiments on joint parsing and named entity recognition, using the OntoNotes corpus, show that our hierarchical joint model can produce substantial gains over a joint model trained on only the jointly annotated data. 1
An Information Theoretic Approach to Bilingual Word Clustering
"... We present an information theoretic objective for bilingual word clustering that incorporates both monolingual distributional evidence as well as cross-lingual evidence from parallel corpora to learn high quality word clusters jointly in any number of languages. The monolingual component of our obje ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
We present an information theoretic objective for bilingual word clustering that incorporates both monolingual distributional evidence as well as cross-lingual evidence from parallel corpora to learn high quality word clusters jointly in any number of languages. The monolingual component of our objective is the average mutual information of clusters of adjacent words in each language, while the bilingual component is the average mutual information of the aligned clusters. To evaluate our method, we use the word clusters in an NER system and demonstrate a statistically significant improvement in F1 score when using bilingual word clusters instead of monolingual clusters. 1
E-Dictionaries and Finite-State Automata for the Recognition of Named Entities
"... In this paper we present a system for named entity recognition and tagging in Serbian that relies on large-scale lexical resources and finite-state transducers. Our system recognizes several types of name, temporal and numerical expressions. Finite-state automata are used to describe the context of ..."
Abstract
-
Cited by 3 (0 self)
- Add to MetaCart
(Show Context)
In this paper we present a system for named entity recognition and tagging in Serbian that relies on large-scale lexical resources and finite-state transducers. Our system recognizes several types of name, temporal and numerical expressions. Finite-state automata are used to describe the context of named entities, thus improving the precision of recognition. The widest context was used for personal names and it included the recognition of nominal phrases describing a person’s position. For the evaluation of the named entity recognition system we used a corpus of 2,300 short agency news. Through manual evaluation we precisely identified all omissions and incorrect recognitions which enabled the computation of recall and precision. The overall recall R = 0.84 for types and R = 0.93 for tokens, and overall precision P = 0.95 for types and P = 0.98 for tokens show that our system gives priority to precision. 1
An Experiment in Integrating Sentiment Features for Tech Stock Prediction in Twitter
"... Economic analysis indicates a relationship between consumer sentiment and stock price movements. In this study we harness features from Twitter messages to capture public mood related to four Tech companies for predicting the daily up and down price movements of these companies’ NASDAQ stocks. We pr ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Economic analysis indicates a relationship between consumer sentiment and stock price movements. In this study we harness features from Twitter messages to capture public mood related to four Tech companies for predicting the daily up and down price movements of these companies’ NASDAQ stocks. We propose a novel model combining features namely positive and negative sentiment, consumer confidence in the product with respect to ‘bullish ’ or ‘bearish’ lexicon and three previous stock market movement days. The features are employed in a Decision Tree classifier using cross-fold validation to yield accuracies of 82.93%,80.49%, 75.61% and 75.00 % in predicting the daily up and down changes of Apple (AAPL), Google (GOOG), Microsoft (MSFT) and Amazon (AMZN) stocks respectively in a 41 market day sample.
Tools and Methodologies for Annotating Syntax and Named Entities in the National Corpus of Polish
"... Abstract—The on-going project aiming at the creation of the National Corpus of Polish assumes several levels of linguistic annotation. We present the technical environment and methodological background developed for the three upper annotation levels: the level of syntactic words and groups, and the ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
Abstract—The on-going project aiming at the creation of the National Corpus of Polish assumes several levels of linguistic annotation. We present the technical environment and methodological background developed for the three upper annotation levels: the level of syntactic words and groups, and the level of named entities. We show how knowledge-based platforms Spejd and Sprout are used for the automatic pre-annotation of the corpus, and we discuss some particular problems faced during theelaborationofthesyntacticgrammar, whichcontainsover 800 rules and is one of the largest chunking grammars for Polish. We also show how the tree editor TrEd has been customized for manual post-editing of annotations, and for further revision of discrepancies. Our XML format converters and customized archiving repository ensure the automatic data flow and efficient corpus file management. We believe that this environment or substantial parts of it can be reused in or adapted for other corpus annotation tasks.
Towards a model of formal and informal address in English
"... Informal and formal (“T/V”) address in dialogue is not distinguished overtly in modern English, e.g. by pronoun choice like in many other languages such as French (“tu”/“vous”). Our study investigates the status of the T/V distinction in English literary texts. Our main findings are: (a) human rater ..."
Abstract
-
Cited by 2 (0 self)
- Add to MetaCart
(Show Context)
Informal and formal (“T/V”) address in dialogue is not distinguished overtly in modern English, e.g. by pronoun choice like in many other languages such as French (“tu”/“vous”). Our study investigates the status of the T/V distinction in English literary texts. Our main findings are: (a) human raters can label monolingual English utterances as T or V fairly well, given sufficient context; (b), a bilingual corpus can be exploited to induce a supervised classifier for T/V without human annotation. It assigns T/V at sentence level with up to 68 % accuracy, relying mainly on lexical features; (c), there is a marked asymmetry between lexical features for formal speech (which are conventionalized and therefore general) and informal speech (which are text-specific). 1
