An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
Article Structure
Abstract
The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing.
Introduction
Coreference resolution is the process of linking multiple mentions that refer to the same entity.
Related Work
There are plenty of learning-based coreference resolution systems that employ the mention-pair model.
Modelling Coreference Resolution
Suppose we have a document containing n mentions {mj : l < j < n}, in which mj is the jth mention occurring in the document.
Entity-mention Model with ILP
4.1 Motivation
Experiments and Results
5.1 Experimental Setup
Conclusions
This paper presented an expressive entity-mention model for coreference resolution by using Inductive Logic Programming.
Topics
coreference
Appears in 37 sentences as: Coreference (1) coreference (33) coreferential (3)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing.Page 1, “Abstract”
- To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level.Page 1, “Abstract”
- The solution can explicitly express relations between an entity and the contained mentions, and automatically learn first-order rules important for coreference decision.Page 1, “Abstract”
- The evaluation on the ACE data set shows that the ILP based entity-mention model is effective for the coreference resolution task.Page 1, “Abstract”
- Coreference resolution is the process of linking multiple mentions that refer to the same entity.Page 1, “Introduction”
- 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.Page 1, “Introduction”
- 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).Page 1, “Introduction”
- Compared with the traditional mention-pair counterpart, the entity-mention model aims to make coreference decision at an entity level.Page 1, “Introduction”
- mention model for coreference resolution.Page 2, “Introduction”
- On top of this, a set of first-order rules is automatically learned, which can capture the information of each individual mention in an entity, as well as the global information of the entity, to make coreference decision.Page 2, “Introduction”
- And our experimental results on the ACE data set shows the model is effective for coreference resolution.Page 2, “Introduction”
See all papers in Proc. ACL 2008 that mention coreference.
See all papers in Proc. ACL that mention coreference.
Back to top.
ILP
Appears in 24 sentences as: ILP (24)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- The model adopts the Inductive Logic Programming ( ILP ) algorithm, which provides a relational way to organize different knowledge of entities and mentions.Page 1, “Abstract”
- The evaluation on the ACE data set shows that the ILP based entity-mention model is effective for the coreference resolution task.Page 1, “Abstract”
- The model employs Inductive Logic Programming ( ILP ) to represent the relational knowledge of an active mention, an entity, and the mentions in the entity.Page 2, “Introduction”
- Inductive Logic Programming ( ILP ) has been applied to some natural language processing tasks, including parsing (Mooney, 1997), POS disambiguation (Cussens, 1996), lexicon construction (Claveau et al., 2003), WSD (Specia et al., 2007), and so on.Page 2, “Related Work”
- In the next section, we will present a more expressive entity-mention model by using ILP .Page 4, “Modelling Coreference Resolution”
- This requirement motivates our use of Inductive Logic Programming ( ILP ), a learning algorithm capable of inferring logic programs.Page 4, “Entity-mention Model with ILP”
- The relational nature of ILP makes it possible to explicitly represent relations between an entity and its mentions, and thus provides a powerful expressiveness for the coreference resolution task.Page 4, “Entity-mention Model with ILP”
- ILP uses logic programming as a uniform representation for examples, background knowledge and hypotheses.Page 5, “Entity-mention Model with ILP”
- Given a set of positive and negative example E : E4r U E‘, and a set of background knowledge K of the domain, ILP tries to induce a set of hypotheses h that covers most of E+ with no E_,i.e.,K/\h )=E+ andK/\h %E‘.Page 5, “Entity-mention Model with ILP”
- In our study, we choose ALEPHZ, an ILP implementation by Srinivasan (2000) that has been proven well suited to deal with a large amount of data in multiple domains.Page 5, “Entity-mention Model with ILP”
- 4.2 Apply ILP to coreference resolutionPage 5, “Entity-mention Model with ILP”
See all papers in Proc. ACL 2008 that mention ILP.
See all papers in Proc. ACL that mention ILP.
Back to top.
coreference resolution
Appears in 22 sentences as: Coreference resolution (1) coreference resolution (21)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- The traditional mention-pair model for coreference resolution cannot capture information beyond mention pairs for both learning and testing.Page 1, “Abstract”
- To deal with this problem, we present an expressive entity-mention model that performs coreference resolution at an entity level.Page 1, “Abstract”
- The evaluation on the ACE data set shows that the ILP based entity-mention model is effective for the coreference resolution task.Page 1, “Abstract”
- Coreference resolution is the process of linking multiple mentions that refer to the same entity.Page 1, “Introduction”
- 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.Page 1, “Introduction”
- 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).Page 1, “Introduction”
- mention model for coreference resolution .Page 2, “Introduction”
- And our experimental results on the ACE data set shows the model is effective for coreference resolution .Page 2, “Introduction”
- There are plenty of learning-based coreference resolution systems that employ the mention-pair model.Page 2, “Related Work”
- (2004) propose a system that performs coreference resolution by doing search in a large space of entities.Page 2, “Related Work”
- (2004b) suggest an entity-based coreference resolution system.Page 2, “Related Work”
See all papers in Proc. ACL 2008 that mention coreference resolution.
See all papers in Proc. ACL that mention coreference resolution.
Back to top.
F-measure
Appears in 12 sentences as: F-measure (12)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- Trained and tested on Penn WSJ TreeBank, the POS tagger could obtain an accuracy of 97% and the NP chunker could produce an F-measure above 94% (Zhou and Su, 2000).Page 6, “Experiments and Results”
- Evaluated for the MUC-6 and MUC-7 Named-Entity task, the NER module (Zhou and Su, 2002) could provide an F-measure of 96.6% (MUC-6) and 94.1%(MUC-7).Page 6, “Experiments and Results”
- The overall F-measure for NWire, NPaper and BNews is 60.4%, 57.9% and 62.9% respectively.Page 7, “Experiments and Results”
- The results are comparable to those reported in (Ng, 2005) which uses similar features and gets an F-measure ranging in 50-60% for the same data set.Page 7, “Experiments and Results”
- As our system relies only on simple and knowledge-poor features, the achieved F-measure is around 2-4% lower than the state-of-the-art systems do, like (Ng, 2007) and (Yang and Su, 2007) which utilized sophisticated semantic or real-world knowledge.Page 7, “Experiments and Results”
- As a result, we only see i0.4% difference between the F-measure .Page 7, “Experiments and Results”
- In our study, we also tested the “Most-X” strategy for the first-order features as in (Culotta et al., 2007), but got similar results without much difference (i0.5% F-measure ) in perfor-Page 7, “Experiments and Results”
- As shown in the third line of Table 4, such a solution damages the performance; while the recall is at the same level, the precision drops significantly (up to 12%) and as a result, the F-measure is even lower than the original MP model.Page 7, “Experiments and Results”
- Overall, it performs better in F-measure (1.8%) for Npaper, while slightly worse (<l%) for Nwire and BNews.Page 7, “Experiments and Results”
- Although the recall drops slightly (up to 1.8% for BNews), the gain in the precision could compensate it well; it beats the MP model in the overall F-measure for all three domains (2.3% for Nwire, 0.4% for Npaper, 1.4% for BNews).Page 8, “Experiments and Results”
- Compared with the EM model with the manually designed first-order feature (the second line), the ILP-based EM solution also yields better performance in precision (with a slightly lower recall) as well as the overall F-measure (1.0% - 1.8%).Page 8, “Experiments and Results”
See all papers in Proc. ACL 2008 that mention F-measure.
See all papers in Proc. ACL that mention F-measure.
Back to top.
learning algorithms
Appears in 5 sentences as: learning algorithm (2) learning algorithms (3)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- Even worse, the number of mentions in an entity is not fixed, which would result in variant-length feature vectors and make trouble for normal machine learning algorithms .Page 1, “Introduction”
- Based on the training instances, a binary classifier can be generated using any discriminative learning algorithm .Page 3, “Modelling Coreference Resolution”
- However, normal machine learning algorithms work on attribute-value vectors, which only allows the representation of atomic proposition.Page 4, “Entity-mention Model with ILP”
- This requirement motivates our use of Inductive Logic Programming (ILP), a learning algorithm capable of inferring logic programs.Page 4, “Entity-mention Model with ILP”
- Default parameters were applied for all the other settings in ALEPH as well as other learning algorithms used in the experiments.Page 6, “Experiments and Results”
See all papers in Proc. ACL 2008 that mention learning algorithms.
See all papers in Proc. ACL that mention learning algorithms.
Back to top.
feature vector
Appears in 4 sentences as: feature vector (3) feature vectors (1)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- It is impractical to enumerate all the mentions in an entity and record their information in a single feature vector , as it would make the feature space too large.Page 1, “Introduction”
- Even worse, the number of mentions in an entity is not fixed, which would result in variant-length feature vectors and make trouble for normal machine learning algorithms.Page 1, “Introduction”
- In the system, a training or testing instance is formed for two mentions in question, with a feature vector describing their properties and relationships.Page 2, “Related Work”
- As an entity may contain more than one candidate and the number is not fixed, it is impractical to enumerate all the mentions in an entity and put their properties into a single feature vector .Page 4, “Modelling Coreference Resolution”
See all papers in Proc. ACL 2008 that mention feature vector.
See all papers in Proc. ACL that mention feature vector.
Back to top.
machine learning
Appears in 3 sentences as: machine learning (3)
In An Entity-Mention Model for Coreference Resolution with Inductive Logic Programming
- Even worse, the number of mentions in an entity is not fixed, which would result in variant-length feature vectors and make trouble for normal machine learning algorithms.Page 1, “Introduction”
- Both (2) and (1) can be approximated with a machine learning method, leading to the traditional mention-pair model and the entity-mention model for coreference resolution, respectively.Page 3, “Modelling Coreference Resolution”
- However, normal machine learning algorithms work on attribute-value vectors, which only allows the representation of atomic proposition.Page 4, “Entity-mention Model with ILP”
See all papers in Proc. ACL 2008 that mention machine learning.
See all papers in Proc. ACL that mention machine learning.
Back to top.
