A consequence of this research was the creation of It-Bank, a collection of thousands of labelled examples of the pronoun it, which will benefit other coreference resolution researchers.

Another avenue of study will look at the interaction between coreference resolution and machine translation.

In general, jointly optimizing translation and coreference is an exciting and largely unexplored research area, now partly enabled by our portable non-referential detection methodology.

Standard coreference resolution data sets annotate all noun phrases that have an antecedent noun phrase in the text.

The goal of coreference resolution is to determine which noun phrases in a document refer to the same real-world entity.

As part of this task, coreference resolution systems must decide which pronouns refer to preceding noun phrases (called antecedents) and which do not.

In sentence (1), it is an anaphoric pronoun referring to some previous noun phrase, like “the sauce” or “an appointment.” In sentence (2), it is part of the idiomatic expression “make it” meaning “succeed.” A coreference resolution system should find an antecedent for the first it but not the second.

Although coreference evaluations, such as the MUC (1997) tasks, also make this distinction, it is not necessarily used by all researchers.

First of all, research in coreference resolution has shown the benefits of modules for general noun anaphoricity determination (Ng and Cardie, 2002; Denis and Baldridge, 2007).

Bergsma and Lin (2006) determine the likelihood of coreference along the syntactic path connecting a pronoun to a possible antecedent, by looking at the distribution of the path in text.

Notably, the first noun-phrase before the context is the word “software.” There is strong compatibility between the pronoun-parent “install” and the candidate antecedent “software.” In a full coreference resolution system, when the anaphora resolution module has a strong preference to link it to an antecedent (which it should when the pronoun is indeed referential), we can override a weak non-referential probability.

We present an unsupervised model for coreference resolution that casts the problem as a clustering task in a directed labeled weighted multigraph.

Coreference resolution is the task of determining which mentions in a text refer to the same entity.

Quite recently, however, rule-based approaches regained popularity due to Stanford’s multi-pass sieve approach which exhibits state-of-the-art performance on many standard coreference data sets (Raghunathan et al., 2010) and also won the CoNLL-2011 shared task on coreference resolution (Lee et al., 2011; Pradhan et al., 2011).

In this paper we present a graph-based approach for coreference resolution that models a document to be processed as a graph.

Graph-based coreference resolution.

Nicolae and Nicolae (2006) phrase coreference resolution as a graph clustering problem: they first perform pairwise classification and then construct a graph using the derived confidence values as edge weights.

(2010) and Cai and Strube (2010) perform coreference resolution in one step using graph partitioning approaches.

To resolve such problem, this paper proposes a novel global argument inference model to explore specific relationships, such as Coreference , Sequence and Parallel, among relevant event mentions to recover those inter-sentence arguments in the sentence, discourse and document layers which represent the cohesion of an event or a topic.

In this paper, we divide the relations among relevant event mentions into three categories: Coreference , Sequence and Parallel.

An event may have more than one mention in a document and coreference event mentions refer to the same event, as same as the definition in the ACE evaluations.

Those coreference event mentions always have the same arguments and roles.

extractor, it is really challenging to recognize these entities as the arguments of its corefered mention E3 since to reduce redundancy in a Chinese discourse, the later Chinese sentences omit many of these entities already mentioned in previous sentences.

This paper proposes a new method for significantly improving the performance of pairwise coreference models.

In effect, our approach finds an optimal feature space (derived from a base feature set and indicator set) for discriminating coreferential mention pairs.

Coreference resolution is the problem of partitioning a sequence of noun phrases (or mentions), as they occur in a natural language text, into a set of referential entities.

A common approach to this problem is to separate it into two modules: on the one hand, one defines a model for evaluating coreference links, in general a discriminative classifier that detects coreferential mention pairs.

In this kind of architecture, the performance of the entire coreference system strongly depends on the quality of the local pairwise classifier.1 Consequently, a lot of research effort on coreference resolution has focused on trying to boost the performance of the pairwise classifier.

Pairwise models basically employ one local classifier to decide whether two mentions are coreferential or not.

For instance, some coreference resolution systems process different kinds of anaphors separately, which suggests for example that pairs containing an anaphoric pronoun behave differently from pairs with non-

where Q classically represents randomness, X is the space of objects (“mention pairs”) that is not directly observable and yij(w) E 3/ = {+1, —1} are the labels indicating whether mi and 7m are coreferential or not.

We tested 3 classical greedy link selection strategies that form clusters from the classifier decision: Closest-First (merge mentions with their closest coreferent mention on the left) (Soon et al., 2001),

We also propose to use a coreference resolution system and consider coreferent entities to be the same discourse entity.

As the coreference resolution system is trained on well-formed textual documents and expects a correct sentence ordering, we use in all our experiments only features that do not rely on sentence order (e.g.

Second, we want to evaluate the influence of automatically performed coreference resolution in a controlled fashion.

Finally, they include a heuristic coreference resolution component by linking mentions which share a

Efficiently incorporating entity-level information is a challenge for coreference resolution systems due to the difficulty of exact inference over partitions.

We describe an end-to-end discriminative probabilistic model for coreference that, along with standard pairwise features, enforces structural agreement constraints between specified properties of coreferent mentions.

One way is to exploit the correct coreference decision we have already made, they A referring to people, since people are not as likely to have a price as art items are.

Because even these six mentions have hundreds of potential partitions into coreference chains, we cannot search over partitions exhaustively, and therefore we must design our model to be able to use this information while still admitting an efficient inference scheme.

The inclusion of entity-level features has been a driving force behind the development of many coreference resolution systems (Luo et al., 2004; Rahman and Ng, 2009; Haghighi and Klein, 2010; Lee et al., 2011).

However, such systems may be locked into bad coreference decisions and are difficult to directly optimize for standard evaluation metrics.

structural agreement factors softly drive properties of coreferent mentions to agree with one another.

,i—1,<neW>}; this variable specifies mention i’s selected antecedent or indicates that it begins a new coreference chain.

Note that a set of coreference chains 0 (the final desired output) can be uniquely determined from a, but a is not uniquely determined by C.

Figure 1: Our BASIC coreference model.

In this paper, we propose a model for cross-document coreference resolution that achieves robustness by learning similarity from unlabeled data.

even identical—do not necessarily corefer .

In this paper, we propose a method for jointly (1) learning similarity between names and (2) clustering name mentions into entities, the two major components of cross-document coreference resolution systems (Baron and Freedman, 2008; Finin et al., 2009; Rao et al., 2010; Singh et al., 2011; Lee et al., 2012; Green et al., 2012).

Such creative spellings are especially common on Twitter and other social media; we give more examples of coreferents learned by our model in Section 8.4.

Cross-document coreference resolution (CDCR) was first introduced by Bagga and Baldwin (1998b).

Most approaches since then are based on the intuitions that coreferent names tend to have “similar” spellings and tend to appear in “similar” contexts.

We adopt a “phylogenetic” generative model of coreference .

Methods that measure compatibility between mention pairs are currently the dominant approach to coreference .

These trees succinctly summarize the mentions providing a highly compact, information-rich structure for reasoning about entities and coreference uncertainty at massive scales.

We demonstrate that the hierarchical model is several orders of magnitude faster than pairwise, allowing us to perform coreference on six million author mentions in under four hours on a single CPU.

Coreference resolution, the task of clustering mentions into partitions representing their underlying real-world entities, is fundamental for high-level information extraction and data integration, including semantic search, question answering, and knowledge base construction.

For example, coreference is Vital for determining author publication lists in bibliographic knowledge bases such as CiteSeer and Google Scholar, where the repository must know if the “R.

31 for Fast Coreference at Large Scale

We investigate different ways of learning structured perceptron models for coreference resolution when using nonlocal features and beam search.

Coreference resolution is the task of grouping referring expressions (or mentions) in a text into disjoint clusters such that all mentions in a cluster refer to the same entity.

In recent years much work on coreference resolution has been devoted to increasing the ex-pressivity of the classical mention-pair model, in which each coreference classification decision is limited to information about two mentions that make up a pair.

This shortcoming has been addressed by entity-mention models, which relate a candidate mention to the full cluster of mentions predicted to be coreferent so far (for more discussion on the model types, see, e.g., (Ng, 2010)).

We show that for the task of coreference resolution the straightforward combination of beam search and early update (Collins and Roark, 2004) falls short of more limited feature sets that allow for exact search.

Coreferent mentions in a document are usually annotated as sets of mentions, where all mentions in a set are coreferent .

This approach provides a powerful boost to the performance of coreference resolvers, but we find that it does not combine well with the LaSO learning strategy.

To address semantic ambiguities in coreference resolution, we use Web n-gram features that capture a range of world knowledge in a diffuse but robust way.

When added to a state-of-the-art coreference baseline, our Web features give significant gains on multiple datasets (ACE 2004 and ACE 2005) and metrics (MUC and B3), resulting in the best results reported to date for the end-to-end task of coreference resolution.

Reconcile is one of the best implementations of the mention-pair model (Soon et al., 2001) of coreference resolution.

The mention-pair model relies on a pairwise function to determine whether or not two mentions are coreferent .

Pairwise predictions are then consolidated by transitive closure (or some other clustering method) to form the final set of coreference clusters (chains).

Many of the most difficult ambiguities in coreference resolution are semantic in nature.

For resolving coreference in this example, a system would benefit from the world knowledge that Obama is the president.

There have been multiple previous systems that incorporate some form of world knowledge in coreference resolution tasks.

Cross-document coreference , the task of grouping all the mentions of each entity in a document collection, arises in information extraction and automated knowledge base construction.

To solve the problem we propose two ideas: (a) a distributed inference technique that uses parallelism to enable large scale processing, and (b) a hierarchical model of coreference that represents uncertainty over multiple granular—ities of entities to facilitate more effective approximate inference.

Given a collection of mentions of entities extracted from a body of text, coreference or entity resolution consists of clustering the mentions such that two mentions belong to the same cluster if and only if they refer to the same entity.

While significant progress has been made in within-document coreference (Ng, 2005; Culotta et al., 2007; Haghighi and Klein, 2007; Bengston and Roth, 2008; Haghighi and Klein,

2009; Haghighi and Klein, 2010), the larger problem of cross-document coreference has not received as much attention.

From a system-to-system perspective, wikification has demonstrated its usefulness in a variety of applications, including coreference resolution (Ratinov and Roth, 2012) and classification (Vitale et al., 2012).

_ _. Coreference . '

Principle 2 (Coreference): Two coreferential mentions should be linked to the same concept.

For example, if we know “nc” and “North Carolina” are coreferential , then they should both be linked to North Carolina.

In this subsection, we introduce the concept meta path which will be used to detect coreference (section 4.3) and semantic relatedness relations (section 4.4).

4.3 Coreference

A coreference relation (Principle 2) usually occurs across multiple tweets due to the highly redundant information in Twitter.

In this paper, we present an unsupervised framework that bootstraps a complete coreference resolution (CoRe) system from word associations mined from a large unlabeled corpus.

We show that word associations are useful for CoRe — e. g., the strong association between Obama and President is an indicator of likely coreference .

Coreference resolution (CoRe) is the process of finding markables (noun phrases) referring to the same real world entity or concept.

Until recently, most approaches tried to solve the problem by binary classification, where the probability of a pair of markables being coreferent is estimated from labeled data.

Alternatively, a model that determines whether a markable is coreferent with a preceding cluster can be used.

We use the term semi-supervised for approaches that use some amount of human-labeled coreference pairs.

(2002) used co-training for coreference resolution, a semi-supervised method.

We present an ILP-based model of zero anaphora detection and resolution that builds on the joint determination of anaphoricity and coreference model proposed by Denis and Baldridge (2007), but revises it and extends it into a three-way ILP problem also incorporating subject detection.

The felicitousness of zero anaphoric reference depends on the referred entity being sufficiently salient, hence this type of data—particularly in Japanese and Italian—played a key role in early work in coreference resolution, e.g., in the development of Centering (Kameyama, 1985; Walker et a1., 1994; Di Eugenio, 1998).

(2010)), and their use in competitions such as SEMEVAL 2010 Task 1 on Multilingual Coreference (Recasens et a1., 2010), is leading to a renewed interest in zero anaphora resolution, particularly at the light of the mediocre results obtained on zero anaphors by most systems participating in SEMEVAL.

We integrate the zero anaphora resolver with a coreference resolver and demonstrate that the approach leads to improved results for both Italian and Japanese.

We first applied the semantic parser and coreference classifier as described in Section 4.1 to process each dialogue, and then built a graph representation based on the automatic processing results at the end of the dialogue.

Our system first processes the data using automatic semantic parsing and coreference resolution.

We then perform pairwise coreference resolution on the discourse entities to find out the discourse relations between entities from different utterances.

Based on the semantic parsing and pairwise coreference resolution results, our system further builds a graph representation to capture the collaborative discourse and formulate referential grounding as a probabilistic labeling problem, as described next.

BLANC is a link-based coreference evaluation metric for measuring the quality of coreference systems on gold mentions.

Coreference resolution aims at identifying natural language expressions (or mentions) that refer to the same entity.

A critically important problem is how to measure the quality of a coreference resolution system.

In particular, MUC measures the degree of agreement between key coreference links (i.e., links among mentions within entities) and response coreference links, while non-coreference links (i.e., links formed by mentions from different entities) are not explicitly taken into account.

Let and Or be the set of coreference links formed by mentions in 19, and 73-:

Note that when an entity consists of a single mention, its coreference link set is empty.

When Tk, = Tr, Rand Index can be applied directly since coreference resolution reduces to a clustering problem where mentions are partitioned into clusters (entities):

Focus, coherence and referential clarity are best evaluated by a class of features measuring local coherence on the basis of cosine similarity between sentences, coreference information, and summarization specific features.

This class of linguistic quality indicators is a combination of factors related to coreference , adjacent sentence similarity, and summary-specific context of surface cohesive devices.

Coreference Steinberger et al.

(2007) compare the coreference chains in input documents and in summaries in order to locate potential problems.

For all four other questions, the best feature set is Continuity, which is a combination of summarization specific features, coreference features and cosine similarity of adjacent sentences.

We now investigate to what extent each of its components—summary-specific features, coreference , and cosine similarity between adjacent sentences—contribute to performance.

However, the coreference features do not seem to contribute much towards predicting summary linguistic quality.

Discourse references, notably coreference and bridging, play an important role in many text understanding applications, but their impact on textual entailment is yet to be systematically understood.

The simplest form of information that discourse provides is coreference , i.e., information that two linguistic expressions refer to the same entity or event.

Coreference is particularly important for processing pronouns and other anaphoric expressions, such as he in Example 1.

While coreference indicates equivalence, bridging points to the existence of a salient semantic relation between two distinct entities or events.

The detection and resolution of discourse references such as coreference and bridging anaphora play an important role in text understanding applications, like question answering and information extraction.

The understanding that the second sentence of the text entails the hypothesis draws on two coreference relationships, namely that he is Oswald, and

However, the utilization of discourse information for such inferences has been so far limited mainly to the substitution of nominal coreferents , while many aspects of the interface between discourse and semantic inference needs remain unexplored.

The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing.

To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level.

The solution can explicitly express relations between an entity and the contained mentions, and automatically learn first-order rules important for coreference decision.

Coreference resolution is the process of linking multiple mentions that refer to the same entity.

Most of previous work adopts the mention-pair model, which recasts coreference resolution to a binary classification problem of determining whether or not two mentions in a document are co-referring (e.g.

An alternative learning model that can overcome this problem performs coreference resolution based on entity-mention pairs (Luo et al., 2004; Yang et al., 2004b).

The cross-narrative coreference and temporal relation weights used in both these approaches are learned from a corpus of clinical narratives.

These cross-narrative coreferences act as important anchors for reasoning with information across narratives.

We leverage cross-narrative coreference information along with confident cross-narrative temporal relation predictions and learn to align and temporally order medical event sequences across longitudinal clinical narratives.

The cross-narrative coreference and temporal relation scores used in both these approaches are learned from a corpus of patient narratives from The Ohio State University Wexner Medical Center.

elstart 2 628mm; and elstop = 6287501,, when 61 and 62 corefer .

Thus, in order to align event sequences, we need to compute scores corresponding to cross-narrative medical event coreference resolution and cross-narrative temporal relations.

4 Cross-Narrative Coreference Resolution and Temporal Relation Learning

We use dynamic programming to compute the best alignment, given the temporal and coreference information between medical events across these sequences.

Although we consistently observed development gains from using automatic coreference resolution, this process creates errors that need to be studied more closely.

First, the system identified coreferent mentions of Olivetti that participated in exporting and supplying events (not shown).

A candidate constituent c will often form a coreference chain with other constituents in the discourse.

When determining whether 0 is the iargg of investment, one can draw evidence from other mentions in 0’s coreference chain.

Thus, the unit of classification for a candidate constituent c is the three-tuple (p, iargn, c’), where c’ is a coreference chain comprising 0 and its coreferent constituents.3 We defined a binary classification function Pr(+| (p,iargn,c’ that predicts the probability that the entity referred to by c fills the missing argument position iargn of predicate instance p. In the remainder of this paper, we will refer to c as the primary filler, differentiating it from other mentions in the coreference chain c’ .

(2005) suggested approaches to implicit argument identification based on observed coreference patterns; however, the authors did not implement and evaluate such methods.

analysis of naturally occurring coreference patterns to aid implicit argument identification.

Opinion Coreference Sentences in a discourse can be linked by many types of coherence relations (Jurafsky et al., 2000).

Coreference is one of the commonly used relations in written text.

In this work, we explore coreference in the context of sentence-level sentiment analysis.

(2008) defines coreference relations on opinion targets and applies them to constrain the polarity of sentences.

This paper introduces a novel sentence processing model that consists of a parser augmented with a probabilistic logic-based model of coreference resolution, which allows us to simulate how context interacts with syntax in a reading task.

This is the first model we know of which introduces a broad-coverage sentence processing model which takes the effect of coreference and discourse into account.

There are three main parts of the model: a syntactic processor, a coreference resolution system, and a simple pragmatics processor which computes certain limited forms of discourse coherence.

The coreference resolution system is implemented

The model comprises three parts: a parser, a coreference resolution system, and a pragmatics subsystem.

However, as the coreference processor takes trees as input, we must therefore unpack parses before resolving referential ambiguity.

the agent), get the -LGS label; (iv) non-recursive NPs are renamed NPbase (the coreference system treats each NPbase as a markable).

The authors remark that extracted sentences with VFs that are referentially related to previous context (e. g., they contain a coreferential noun phrase or a discourse relation like “therefore”) are reinserted at higher accuracies.

The main focus of that work, however, was to adapt the model for use in a low-resource situation when perfect coreference information is not available.

Table 3: Accuracy of automatic annotations of noun phrases with coreferents .

Coreferencing entities across documents in a large corpus enables advanced document understanding tasks such as question answering.

This paper presents a novel cross document coreference approach that leverages the profiles of entities which are constructed by using information extraction tools and reconciled by using a within-document coreference module.

We compare the kernelized clustering method with a popular fuzzy relation clustering algorithm (FRC) and show 5% improvement in coreference performance.

Cross document coreference (CDC) is the task of consolidating named entities that appear in multiple documents according to their real referents.

document coreference (WDC), which limits the scope of disambiguation to within the boundary of a document.

Cross document coreference , on the other hand, is a more challenging task because these linguistics cues and sentence structures no longer apply, given the wide variety of context and styles in different documents.

We make distinctions between document level and profile based cross document coreference .

persons in this work), a within-document coreference (WDC) module then links the entities deemed as referring to the same underlying identity into a WDC chain.

Therefore, the chained entities placed in a name cluster are deemed as coreferent .

As is common for many natural language processing problems, the state-of-the-art in noun phrase (NP) coreference resolution is typically quantified based on system performance on manually annotated text corpora.

MUC-6 (1995), ACE NIST (2004)) and their use in many formal evaluations, as a field we can make surprisingly few conclusive statements about the state-of-the-art in NP coreference resolution.

In particular, it remains difi‘icult to assess the effectiveness of diflerent coreference resolution approaches, even in relative terms.

For richer annotations that include lemmatiza-tions, part of speech, NER, and in-doc coreference , we preprocessed each of the datasets using tools7 similar to those used to create the Annotated Gigaword corpus (Napoles et al., 2012).

Extended Event Coreference Bank Based on the dataset of Bejan and Harabagiu (2010), Lee et al.

(2012) introduced the Extended Event Coreference Bank (EECB) to evaluate cross-document event coreference .

Similar to entity coreference resolution, almost all of this work assumes unanchored mentions: predicate argument tuples are grouped together based on coreferent events.

The first work on event coreference dates back to Bagga and Baldwin (1999).

Predicates are represented as mention spans and arguments are represented as coreference chains (sets of mention spans) provided by in-document coreference resolution systems such as included in the Stanford NLP toolkit.

For argument coref chains we heuristically choose a canonical mention to represent each chain, and some features only look at this canonical mention.

The canonical mention is chosen based on length,4 information about the head word,5 and position in the document.6 In most cases, coref chains that are longer than one are proper nouns and the canonical mention is the first and longest mention (outranking pronominal references and other name shortenings).

For instance, our system can also profit from additional annotations like coreference , that has proved its utility in previous works.

For each missing argument, the gold-standard includes the whole coreference chain of the filler.

Therefore, the scorer selects from all coreferent mentions the highest Dice value.

Filling the implicit arguments of a predicate has been identified as a particular case of coreference , very close to pronoun resolution (Silberer and Frank, 2012).

This work applied selectional restrictions together with coreference chains, in a very specific domain.

These early works agree that the problem is, in fact, a special case of anaphora or coreference resolution.

Silberer and Frank (2012) adapted an entity-based coreference resolution model to extend automatically the training corpus.

The Chambers and Jurafsky (2008) model learns chains completely unsupervised, (albeit after parsing and resolving coreference in the text) by counting pairs of verbs that share corefer-ring arguments within documents and computing the pointwise mutual information (PMI) between these verb-argument pairs.

Even more telling is that these arguments are jointly shared (the same or coreferent ) across all three events.

We use the OpenNLP1 coreference engine to resolve entity mentions.

As mentioned above, narrative chains are learned by parsing the text, resolving coreference , and extracting chains of events that share participants.

In our new model, argument types are learned simultaneously with narrative chains by finding salient words that represent coreferential arguments.

We record counts of arguments that are observed with each pair of event slots, build the referential set for each word from its coreference chain, and then represent each observed argument by the most frequent head word in its referential set (ignoring pronouns and mapping entity mentions with person pronouns to a constant PERSON identifier).

We parse the text into dependency graphs and resolve coreferences .

Coreference relations between nodes of certain category types are captured.

Attributes coref_text.rf and coref_gram.rf contain ids of coreferential nodes of the respective types.

2.1.7 Coreferences

Two types of coreferences are annotated on the tectogrammatical layer:

0 grammatical coreference

0 secondary edges, secondary dependencies, coreferences , long-range relations

From the tables it is apparent that good performance on a range of phenomena in our inference model are likely to have a significant effect on RTE results, with coreference being deemed essential to the inference process for 35% of examples, and a number of other phenomena are sufficiently well represented to merit near-future attention (assuming that RTE systems do not already handle these phenomena, a question we address in section 4).

Phenomenon Occurrence Agreement coreference 35.00% 0.698 simple rewrite rule 32.62% 0.580 lexical relation 25.00% 0.738 implicit relation 23.33% 0.633 factoid 15.00% 0.412 parent-sibling 1 1.67% 0.500 genetive relation 9.29% 0.608 nominalization 8.33% 0.514 event chain 6.67% 0.589 coerced relation 6.43% 0.540 passive-active 5.24% 0.583 numeric reasoning 4.05% 0.847 spatial reasoning 3.57% 0.720

The results confirmed our initial intuition about some phenomena: for example, that coreference resolution is central to RTE, and that detecting the connecting structure is crucial in discerning negative from positive examples.

Tasks such as Named Entity and coreference resolution, syntactic and shallow semantic parsing, and information and relation extraction have been identified as worthwhile tasks and pursued by numerous researchers.

relevant NLP tasks such as NER, Coreference , parsing, data acquisition and application, and others.

ported by their designers were the use of structured representations of shallow semantic content (such as augmented dependency parse trees and semantic role labels); the application of NLP resources such as Named Entity recognizers, syntactic and dependency parsers, and coreference resolvers; and the use of special-purpose ad-hoc modules designed to address specific entailment phenomena the researchers had identified, such as the need for numeric reasoning.

As the example in figure 1 illustrates, most RTE examples require a number of phenomena to be correctly resolved in order to reliably determine the correct label (the Interaction problem); a perfect coreference resolver might as a result yield little improvement on the standard RTE evaluation, even though coreference resolution is clearly required by human readers in a significant percentage of RTE examples.

While previous work uses the Stanford CoreNLP toolkit to identify characters and extract typed dependencies for them, we found this approach to be too slow for the scale of our data (a total of 1.8 billion tokens); in particular, syntactic parsing, with cubic complexity in sentence length, and out-of-the-box coreference resolution (with thousands of potential antecedents) prove to be

It includes the following components for clustering character name mentions, resolving pronominal coreference , and reducing vocabulary dimensionality.

3.2 Pronominal Coreference Resolution

(2013) explicitly learn character types (or “personas”) in a dataset of Wikipedia movie plot summaries; and entity-centric models form one dominant approach in coreference resolution (Durrett et al., 2013; Haghighi and Klein, 2010).

Coreference resolution, which could help avoid vague question generation, is discussed in Section 5.

Here we briefly describe three challenges: negation detection, coreference resolution, and verb forms.

5.2 Coreference Resolution

Currently, our system does not use any type of coreference resolution.

The aggregation approach described here can be easily extended to improve relation detection and coreference resolution (two argument mentions referring to the same role of related events are likely to corefer ).

c for each event argument string and the names coreferential with or related to the argument, the frequency of the event type;

c for each event argument string and the names coreferential with or related to the argument, the frequency of the event type and role.

Almost all the current event extraction systems focus on processing single documents and, except for coreference resolution, operate a sentence at a time (Grishman et al., 2005; Ahn, 2006; Hardy et al., 2006).

For each argument we also add other names coreferential with or bearing some ACE relation to the argument.

2 In this paper we don’t consider event mention coreference resolution and so don’t distinguish event mentions and events.

Documents are processed by a full NLP pipeline, including token and sentence segmentation, parsing, semantic role labeling, and an information extraction pipeline consisting of mention detection, NP coreference , cross-document resolution, and relation detection (Florian et al., 2004; Luo et al., 2004; Luo and Zitouni, 2005).

Finally, the postprocessing stage applies coreference resolution and sentence reordering to build the summary.

Then we conduct simple query expansion based on the title of the topic and cross-document coreference resolution.

And for each mention in the query, we add other mentions within the set of documents that corefer with this mention.

We then clustered the noun phrases into coreferents for the same entity (person or organization).

For each named entity, we generate variations on the name that we would expect to see in a coreferent .

For each named entity, we compile a list of other named entities that may be coreferents , either because they are identical or because one is an expected variation on the other.

3Throughout this paper we refer to relation mention as relation since we do not consider relation mention coreference .

Roth (2011), we excluded the D I SC relation type, and removed relations in the system output which are implicitly correct via coreference links for fair comparison.

Coreference consistency Coreferential entity mentions should be assigned the same entity type.

We determine high-recall coreference links between two segments in the same sentence using some simple heuristic rules:

Then we encode a global feature to check whether two coreferential segments share the same entity type.

This paper extends this intuition by introducing a new vector-based approach to coreference similarity.

In the sentence, he ran and then he fell, the subjects of run and fall corefer , and so they likely belong to the same scenario-specific semantic role.

For instance, arguments of the relation go_ofi”:s were seen coreferring with mentions in plant:o, set_ofi”:o and injures We represent go_ofi”:s as a vector of these relation counts, calling this its coref vector representation.

For every event, we collect its trigger and event type; for every argument, we use coreference information and record every entity and its role(s) in events of a certain type.

( coreferential ) entity mentions.

Event extraction depends on previous phases entity mention classification and coreference .

Note that entity mentions that share the same EntityID are coreferential and treated as the same object.

Unlike common practice in grammatical annotation, linkage relations in UCCA can cross sentence boundaries, as can relations represented in other layers (e.g., coreference ).

Another immediate extension to UCCA’s foundational layer can be the annotation of coreference relations.

A coreference layer would annotate a relation between “John” and “his” by introducing a new node whose descendants are these two units.

0 Coreference : indicates that two chunks refer to

The processing includes dependency parsing, named entity recognition and coreference resolution, done with the Stanford CoreNLP software (Klein and Manning, 2003); and events and temporal information extraction, via the TARSQI Toolkit (Verhagen et al., 2005).

Each node of GO clusters together coreferent nodes, representing a discourse referent.

Concept discovery is also related to coreference resolution (Ng, 2008; Poon and Domingos, 2008).

The difference between the two problems is that coreference resolution finds noun phrases that refer to the same concept within a specific document.

We think the concepts produced by a system like ConceptResolver could be used to improve coreference resolution by providing prior knowledge about noun phrases that can refer to the same concept.

The task of identifying reference relations including anaphora and coreferences within texts has received a great deal of attention in natural language processing, from both theoretical and empirical perspectives.

In these data sets, coreference relations are defined as a limited version of a typical coreference; this generally means that only the relations where expressions refer to the same named entities are addressed, because it makes the coreference resolution task more information extraction-oriented.

In other words, the coreference task as defined by MUC and ACE is geared toward only identifying coreference relations anchored to an entity within the text.

These features have been examined by approaches to anaphora or coreference resolution (Soon et al., 2001; Ng and Cardie, 2002, etc.)

For a TH pair, apply dependency parsing and coreference resolution.

Parsing H Abstract I T/H Coreference DCS trees denotations -

DCS trees can be extended to represent linguistic phenomena such as quantification and coreference , with additional markers introducing additional operations on tables.

Coreference We use Stanford CoreNLP to resolve coreferences (Raghunathan et al., 2010), whereas coreference is implemented as a special type of selection.

Therefore, besides canonicalizing named entities, the model also resolves within—document and cross-document coreference , since it assigned a row index for every mention.

As a result, the model discovers parts of names—(Mrs., Michelle, Obama)—while simultaneously performing coreference resolution for named entity mentions.

Our model is focused on the problem of canonicalizing mention strings into their parts, though its 7“ variables (which map mentions to rows) could be interpreted as (within-document and cross-document) coreference resolution, which has been tackled using a range of probabilistic models (Li et al., 2004; Haghighi and Klein, 2007; Poon and Domingos, 2008; Singh et al., 2011).

An edge from sentence 3,- to sj with positive weight indicates that sj may follow 3,- in a coherent summary, e. g. continued mention of an event or entity, or coreference link between 3,- and sj.

A negative edge indicates an unfulfilled discourse cue or coreference mention.

These are coreference mentions 0r discourse cues where none of the sentences read before (either in an ancestor summary or in the current summary) contain an antecedent:

In that work, we also highlight that ACE annotators rarely duplicate a relation link for coreferent mentions.

For instance, assume mentions mi, mj, and mk, are in the same sentence, mentions mi and mj are coreferent , and the annotators tag the mention pair mj, mk, with a particular relation r. The annotators will rarely duplicate the same (implicit)

Of course, using this scoring method requires coreference information, which is available in the ACE data.