Abstract | We present an incremental joint framework to simultaneously extract entity mentions and relations using structured perceptron with efficient beam-search. |
Abstract | In addition, by virtue of the inexact search, we developed a number of new and effective global features as soft constraints to capture the interdependency among entity mentions and relations. |
Introduction | The goal of end-to-end entity mention and relation extraction is to discover relational structures of entity mentions from unstructured texts. |
Introduction | This problem has been artificially broken down into several components such as entity mention boundary identification, entity type classification and relation extraction. |
Introduction | For example, in Figure 1, the output structure of each sentence can be interpreted as a graph in which entity mentions are nodes and relations are directed arcs with relation types. |
Feature Construction | An entity mention is a reference to an entity. |
Feature Construction | The entity mention is annotated with its full extent and its head, referred to as the extend mention and the head mention respectively. |
Feature Construction | Head Noun: The head noun (or head mention) of entity mention is manually annotated. |
Experimental Setup | The data was first tagged with the Stanford NER system (Finkel et al., 2005) and then entity mentions were found by collecting each continuous phrase where words were tagged identically (i.e., as a person, location, or organization). |
Experimental Setup | These include indicators for various lexical, part of speech, named entity, and dependency tree path properties of entity mentions in specific sentences, as computed with the Malt dependency parser (Nivre and Nilsson, 2004) and OpenNLP POS taggerl. |
Learning | As input we have (1) E, a set of sentences, (2) E, a set of entities mentioned in the sentences, (3) R, a set of relation names, and (4) A, a database of atomic facts of the form 7“(€1, 62) for 7“ E R and 6,- E E. Since we are using weak learning, the Y7" variables in Y are not directly observed, but can be approximated from the database A. |
Modeling Overlapping Relations | (2) E, a set of entities mentioned in the sentences, (3) R, a set of relation names, and |
Weak Supervision from a Database | An entity mention is a contiguous sequence of textual tokens denoting an entity. |
Weak Supervision from a Database | In this paper we assume that there is an oracle which can identify all entity mentions in a corpus, but the oracle doesn’t normalize or disambiguate these mentions. |
Weak Supervision from a Database | A relation mention is a sequence of text (including one or more entity mentions ) which states that some ground fact r(e) is true. |
Corporate Acquisitions | Table 5 further shows results on NER, the task of recovering the sets of named entity mentions pertaining to each target field. |
Problem Setting | Generally, parent-free relations in the hierarchy correspond to generic entities, realized as entity mentions in the text. |
Problem Setting | Figure 3 demonstrates the correct mapping of named entity mentions to tuples, as well as tuple unification, for the example shown in Figure 1. |
Related Work | In their model, slot-filling entities are first generated, and entity mentions are then realized in text. |
Related Work | In addition to proper nouns (named entity mentions ) that are considered in this work, they also account for nominal and pronominal noun mentions. |
Related Work | Compared with the extraction of tuples of entity mention pairs, template filling is associated with a more complex target relational schema. |
Seminar Extraction Task | Another feature encodes the size of the most semantically detailed named entity that maps to a field; for example, the most detailed entity mention of type stime in Figure l is “3:30”, comprising of two attribute values, namely hour and minutes. |
Seminar Extraction Task | We have experimented with features that encode the shortest distance between named entity mentions mapping to different fields (measured in terms of separating lines or sentences), based on the hypothesis that field values typically co-appear in the same segments of the document. |
Cross-event Approach | For argument tagging, we only consider the entity mentions in the same sentence as the trigger word, because by the ACE event guidelines, the arguments of an event should appear within the same sentence as the trigger. |
Cross-event Approach | For a given event, we re-tag the entity mentions that have not already been assigned as arguments of that event by the confident-event or conflict table. |
Task Description | (coreferential) entity mentions . |
Task Description | Entity mention : a reference to an entity (typically, a noun phrase) |
Task Description | Event mention arguments (roles)2: the entity mentions that are involved in an event mention, and their relation to the event. |
Abstract | (2005): a) Lexical features of entities and their contexts WMl: bag-of-words in the 1st entity mention HMl: headword of M1 WM2: bag-of-words in the 2nd entity mention HM2: headword of M2 HM12: combination of HMl and HMZ WBNULL: when no word in between WBFL: the only one word in between WBF: the first word in between when at least two words in between |
Abstract | c) Mention level ML12: combination of entity mention levels MT12: combination of LDC mention types |
Abstract | Put in another way, entity alignment automatically marks the entity mentions in the translated instance, thereby the feature vector corresponding to the translated instance can be constructed. |
Abstract | We present a statistical model for canonicalizing named entity mentions into a table whose rows represent entities and whose columns are attributes (or parts of attributes). |
Experiments | We collected named entity mentions from two corpora: political blogs and sports news. |
Experiments | Due to the large size of the corpora, we uniformly sampled a subset of documents for each corpus and ran the Stanford NER tagger (Finkel et al., 2005), which tagged named entities mentions as person, location, and organization. |
Experiments | Table 2 summarizes statistics for both datasets of named entity mentions . |
Introduction | We seek an algorithm that infers a set of real-world entities from mentions in a text, mapping each entity mention token to an entity, and discovers general categories of words used in names (e.g., titles and last names). |
Introduction | tributes through transductive learning from named entity mentions with a small number of seeds (see |
Introduction | As a result, the model discovers parts of names—(Mrs., Michelle, Obama)—while simultaneously performing coreference resolution for named entity mentions . |
Background | A relation was defined over a pair of entity mentions within a single sentence. |
Background | The heads of the two entity mentions are marked. |
Cluster Feature Selection | As a relation in ACE is usually short, the words of the two entity mentions can provide more critical indications for relation classification than the words from the context. |
Cluster Feature Selection | Within the two entity mentions , the head word of each mention is usually more important than other words of the mention; the conjunction of the two heads can provide an additional clue. |
Cluster Feature Selection | And in general words other than the chunk head in the context do not contribute to establishing a relationship between the two entity mentions . |
Experiments | Following previous work, we did 5-fold cross-validation on the 348 documents with hand-annotated entity mentions . |
Feature Based Relation Extraction | Given a pair of entity mentions < m. , m j > and the sentence containing the pair, a feature based system extracts a feature vector v which contains diverse lexical, syntactic and semantic features. |
Introduction | 3 For simplicity, a cleaned entity dictionary dumped from the entire ICE is used to detect entity mentions in Q. |
Introduction | Algorithm 2: Q’P-based Question Translation T = (Z); foreach entity mention eg 6 Q do Qpattem = replace eg in Q with [Slot]; foreach question pattern Q73 do if Qpattern == Qppattern then 5 = Disambiguate(eg, QPpredicate); foreach e E 5 do create a new triple query q; q : {ea Qppredicatea {At} = AnswerRetrieve(q, ICE); foreach A 6 {At} do create a new formal triple t; t = {q-esbj, q-p,«4}; t.score = 1.0; insert t to T; |
Introduction | For each entity mention eg 6 Q, we replace it with [Slot] and obtain a pattern string Qpattem (Line 3). |
Experiments | 3If we take the perfect entity mentions and the associated concepts provided by i2b2 (Uzuner et al., 2011) as the input, our system can directly apply to i2b2 relation extraction data. |
Identifying Key Medical Relations | The most well-known tool to detect medical entity mentions is MetaMap (Aronson, 2001), which considers all terms as entities and automatically associates each term with a number of concepts from UMLS CUI dictionary (Lindberg et al., 1993) with 2.7 million distinct concepts. |
Introduction | In i2b2 relation extraction task, entity mentions are manually labeled, and each mention has 1 of 3 concepts: ‘treatment’, ‘problem’, and ‘test’. |
Introduction | To resemble real-world medical relation extraction challenges where perfect entity mentions do not exist, our new setup requires the entity mentions to be automatically detected. |
Introduction | The most well-known tool to detect medical entity mentions is MetaMap (Aronson, 2001), which considers all terms as entities and automatically associates each term with a number of concepts from UMLS CUI dictionary (Lindberg et al., 1993) with more than 2.7 million distinct concepts (compared to 3 in i2b2). |
Abstract | Two main challenges of this task are the dearth of information in a single tweet and the rich entity mention variations. |
Conclusions and Future work | Second, we want to integrate the entity mention normalization techniques as introduced by Liu et al. |
Introduction | In this work, we study the entity linking task for tweets, which maps each entity mention in a tweet to a unique entity, i.e., an entry ID of a knowledge base like Wikipedia. |
Introduction | That means, an entity mention often occurs in many tweets, which allows us to aggregate all related tweets to compute mention-mention similarity and mention-entity similarity. |
Related Work | (2012) propose LIEGE, a framework to link the entities in web lists with the knowledge base, with the assumption that entities mentioned in a Web list tend to be a collection of entities of the same conceptual type. |
Related Work | They propose a machine learning based approach using n-gram features, concept features, and tweet features, to identify concepts semantically related to a tweet, and for every entity mention to generate links to its corresponding Wikipedia article. |
Approach | A target could be another discussant or an entity mentioned in the discussion. |
Approach | The target of opinion can also be an entity mentioned in the discussion. |
Approach | As stated above, a target could be another discussant or an entity mentioned in the discussion. |
Introduction | The target of attitude could be another discussant or an entity mentioned in the discussion. |
Introduction | tity recognition and noun phrase chunking to identify the entities mentioned in the discussion. |
Introduction | The attitude profile of a discussant contains an entry for every other discussant and an entry for every entity mentioned in the discission. |
Experiments | For any entity mention , two annotators independently annotate its canonical form. |
Experiments | This explains the cases where our system correctly links multiple entity mentions but fails to generate canonical forms. |
Introduction | However, named entity normalization (NEN) for tweets, which transforms named entities mentioned in tweets to their unambiguous canonical forms, has not been well studied. |
Task Definition | Given a set of tweets, e. g., tweets within some period or related to some query, our task is: 1) To recognize each mention of entities of predefined types for each tweet; and 2) to restore each entity mention into its unambiguous canonical form. |
Task Definition | Given each pair of entity mentions , decide whether they denote the same entity. |
Event Extraction Task | Event argument: an entity mention , temporal expression or value (e.g. |
Joint Framework for Event Extraction | For example, if the nearest entity mention is “Company”, the current token is likely to be Personnel no matter whether it is End-Postion or Start-Position. |
Joint Framework for Event Extraction | In this example, an entity mention is Victim argument to Die event and Target argument to Attack event, and the two event triggers are connected by the typed dependency advcl. |
Joint Framework for Event Extraction | If a partial configuration mistakenly classifies more than one entity mention as Place arguments for the same trigger, then it will be penalized. |
Discussion | Poor entity mention detection is a major source of error in both cases, suggesting that future work should consider integrating entity linking with joint syntactic and semantic parsing. |
Experiments | This performance loss appears to be largely due to poor entity mention detection, as we found that not using entity mention lexicon entries at test time improves ASP’s labeled and unlabeled F-scores by 0.3% on Section 00. |
Experiments | Approximately 50% of errors are caused by marking common nouns as entity mentions (e.g., marking “coin” as a COMPANY). |
Parser Design | Entity mentions appear in logical forms via a special mention predicate, M, instead of as database constants. |
Active Learning for Sequence Labeling | This might, in particular, apply to NER where larger stretches of sentences do not contain any entity mention at all, or merely trivial instances of an entity class easily predictable by the current model. |
Experiments and Results | By the nature of this task, the sequences —in this case, sentences — are only sparsely populated with entity mentions and most of the tokens belong to the OUTSIDE class3 so that SeSAL can be expected to be very beneficial. |
Introduction | In the NER scenario, e.g., large portions of the text do not contain any target entity mention at all. |
Summary and Discussion | In our experiments on the NER scenario, those regions were mentions of entity names or linguistic units which had a surface appearance similar to entity mentions but could not yet be correctly distinguished by the model. |
Baseline | The arguments are the entity mentions involved in an event mention with a specific role, the relation of an argument to an event where it participates. |
Inferring Inter-Sentence Arguments on Relevant Event Mentions | is the kth event mentions in sentence S<U>; A<iyjykyl> is the lth candidate arguments in event mention T<U,k>; Z is used to denote <i,j,k,l>;f[(EZ) is the score of AI identifying entity mention EZ as an argument, where EZ is the lth entity of the kth event mention of the jth sentence of the ith discourse in document D. fD(EZ, Rm) is the score of RD assigning role Rm to argument E Z. |
Inferring Inter-Sentence Arguments on Relevant Event Mentions | same entity mention . |
Headline generation | In the end, for each entity mentioned in the document we have a unique identifier, a list with all its mentions in the document and a list of class labels from Freebase. |
Headline generation | GETRELEVANTENTITIES: For each news collection N we collect the set E of the entities mentioned most often within the collection. |
Headline generation | We invoke again INFERENCE, now using at the same time all the patterns extracted for every subset of E, g E. This computes a probability distribution w over all patterns involving any admissible subset of the entities mentioned in the collection. |
Experiments and results | The corpus is preprocessed by identifying Freebase entity mentions , using an approach similar to (Milne and Witten, 2008), and parsing it with an inductive dependency parser (Nivre, 2006). |
Introduction | A different family of unsupervised methods for relation extraction is unsupervised semantic parsing, which aims at clustering entity mentions and relation surface forms, thus generating a semantic representation of the texts on which inference may be used. |
Introduction | 2009; Hoffmann et al., 2011; Wang et al., 2011), or syntactic restrictions on the sentences and the entity mentions (Wu and Weld, 2010). |
Heuristics-based pattern extraction | (2013), who built well formed relational patterns by extending minimum spanning trees (MST) which connect entity mentions in a dependency parse. |
Introduction | Given input text(s) with resolved and typed entity mentions , event mentions and the most relevant event cluster are detected (first arrow). |
Pattern extraction by sentence compression | entity mentions must be retained, . |
Cognitively Grounded Cost Modeling | These time tags indicate the time it took to annotate the respective phrase for named entity mentions of the types person, location, and organization. |
Experimental Design | An example consists of a text document having one single annotation phrase highlighted which then had to be semantically annotated with respect to named entity mentions . |
Experimental Design | It should be noted that such orthographic signals are by no means a sufficient condition for the presence of a named entity mention within a CNP. |