Some languages lack large knowledge bases and good discriminative features for Name Entity Recognition ( NER ) that can generalize to previously unseen named entities.

Named Entity Recognition ( NER ) is essential for a variety of Natural Language Processing (NLP) applications such as information extraction.

There has been a fair amount of work on NER for a variety of languages including Arabic.

To train an NER system, some of the following feature types are typically used (Benajiba and Rosso, 2008; Nadeau and Sekine, 2009):

Translated bi-texts contain complementary language cues, and previous work on Named Entity Recognition ( NER ) has demonstrated improvements in performance over monolingual taggers by promoting agreement of tagging decisions between the two languages.

We observe that NER label information can be used to correct alignment mistakes, and present a graphical model that performs bilingual NER tagging jointly with word alignment, by combining two monolingual tagging models with two unidirectional alignment models.

We design a dual decomposition inference algorithm to perform joint decoding over the combined alignment and NER output space.

We assume access to two monolingual linear-chain CRF-based NER models that are already trained.

We study the problem of Named Entity Recognition ( NER ) in a bilingual context, where the goal is to annotate parallel bi-texts with named entity tags.

(2012) have also demonstrated that bi-texts annotated with NER tags can provide useful additional training sources for improving the performance of standalone monolingual taggers.

In this work, we first develop a bilingual NER model (denoted as BI-NER) by embedding two monolingual CRF-based NER models into a larger undirected graphical model, and introduce additional edge factors based on word alignment (WA).

Compared to shallow (POS, NER ) structured retrieval, deep structures need more processing power and smoothing, but might also be more precise.

This will be our off-the-shelf QA system, which recognizes the association between question type and expected answer types through various features based on e.g., part-of-speech tagging (POS) and named entity recognition ( NER ).

For instance, line 2 in Table 1 says that if there is a when question, and the current token’s NER label is DATE, then it is likely that this token is tagged as ANS.

IR can easily make use of this knowledge: for a when question, IR retrieves sentences with tokens labeled as DATE by NER , or POS tagged as CD.

We let the trained QA system guide the query formulation when performing coupled retrieval with Indri (Strohman et al., 2005), given a corpus already annotated with POS tags and NER labels.

For instance, the NER tagger we used divides location into two categories: GPE (geo locations) and LOC

Take the previous where question, besides NER[O]=GPE and NER[O]=LOC, we also found oddly N ER[O]=PERSON an important feature, due to that the NER tool sometimes mistakes PERSON for LOC.

Table 1 gives statistics for both corpora, including the number and ambiguity of gold standard toponyms for both as well as NER identified to-

ponyms for TR-CONLL.4 We use the pre-trained English NER from the OpenNLP project.5

False positives occur when the NER incorrectly predicts a toponym, and false negatives occur when it fails to predict a toponym identified by the annotator.

In this case, the ORACLE results are less than 100% due to the limitations of the NER, and represent the best possible results given the NER we used.

Results on TR-CONLL indicate much higher performance than the resolvers presented by Leidner (2008), whose F-scores do not exceed 36.5% with either gold or NER toponyms.7 TRC-TEST is a subset of the documents Leidner uses (he did not split development and test data), but the results still come from overlapping data.

However, our evaluation is more penalized since SPIDER loses precision for NER’s false positives (Jack London as a location) while Leidner only evaluated on actual locations.

Given a set of toponyms provided via annotations or identified using NER , a resolver must select a candidate location for each toponym (or, in some cases, a resolver may abstain).

4States and countries are not annotated in CWAR, so we do not evaluate end-to-end using NER plus toponym resolution for it as there are many (falsely) false positives.

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.

We have shown that improvement in clustering can be obtained across a range of language pairs, evaluated in terms of their value as features in an extrinsic NER task.

Our evaluation task is the German corpus with NER annotation that was created for the shared task at CoNLL-2003 3.

Table 1 shows the performance of NER when the word clusters are obtained using only the bilingual information for different language pairs.

We varied the weight of the bilingual objective (/3) from 0.05 to 0.9 and observed the effect in NER performance on English-German language pair.

Random confounder (RND) most closes to the realistic case; While nearest confounder ( NER ) is reproducible and it avoids frequency bias (Chambers and Jurafsky, 2010).

In this work, we employ both RND and NER confounders: 1) for RND, we randomly select

2) for NER , firstly we sort the arguments by their frequency.

We use the standard automatic parses and NER tags for each document.

We evaluate our system on the dataset from the CoNLL 2011 shared task using three different types of properties: synthetic oracle properties, entity phi features (number, gender, animacy, and NER type), and properties derived from unsupervised clusters targeting semantic type information.

Agreement features: Gender, number, animacy, and NER type of the current mention and the antecedent (separately and conjoined).

Each mention 2' has been augmented with a single property node pi E {1, ..., The unary B factors encode prior knowledge about the setting of each pi; these factors may be hard (I will not refer to a plural entity), soft (such as a distribution over named entity types output by an NER tagger), or practically uniform (e. g. the last name Smith does not specify a particular gender).

Directly applying Named Entity Recognition ( NER ) tools on news titles or

Accordingly, we first apply the NER tool on news summaries, then label named entities in the tweets in the same way as labeling the hashtags: if there is a string in the tweet that matches a named entity from the summaries, then it is labeled as a named entity in the tweet.

The noise introduced during automatic NER accumulates much faster given the large number of named entities in news data.

Named entities acquired from a news document, typically with high accuracy using Named Entity Recognition [ NER ] tools, may be particularly informative.

Generally, the quality of NER is crucial in this task.

As standard named entity recognition ( NER ) systems do not capture categories that are relevant to the movie domain, we opt for a lexicon-based approach similar to (Zhuang et al., 2006).

Many entries are unsuitable for NER , e.g., dog is frequently listed as a character.

This rule has precedence over NER, so if a name matches a labeled entity, we do not attempt to label it through NER .