CMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing

Mills, Chad; Levow, Gina‐Anne

doi:10.18653/v1/s15-2075

Cited by 4 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CPA parsing aims at identifying the arguments of the target and tagging predefined semantic meaning on them; CPA clustering clusters the instances to obtain CPA frames based on the result of CPA parsing. However, the first step results seem unpromising (Feng et al, 2015;Mills and Levow, 2015;Elia, 2016) which will influence the process of obtaining CPA frames. Since our model can be applied on sentence-level input without feature extraction we can directly evaluate …”

Section: Cpa Experimentsmentioning

confidence: 99%

Semantic Frame Labeling with Target-based Neural Model

Feng

Xu³

et al. 2017

Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)

View full text Add to dashboard Cite

This paper explores the automatic learning of distributed representations of the target's context for semantic frame labeling with target-based neural model. We constrain the whole sentence as the model's input without feature extraction from the sentence. This is different from many previous works in which local feature extraction of the targets is widely used. This constraint makes the task harder, especially with long sentences, but also makes our model easily applicable to a range of resources and other similar tasks. We evaluate our model on several resources and get the state-of-the-art result on subtask 2 of SemEval 2015 task 15. Finally, we extend the task to word-sense disambiguation task and we also achieve a strong result in comparison to state-of-the-art work.

show abstract

Section: Cpa Experimentsmentioning

confidence: 99%

Semantic Frame Labeling with Target-based Neural Model

Feng

Xu³

et al. 2017

Proceedings of the 6th Joint Conference on Lexical and Computational Semantics (*SEM 2017)

View full text Add to dashboard Cite

show abstract

“…The most important part in solving this task is undoubtedly identifying which tokens in the sentence are actual arguments for the verb, because mistakes at this stage will reflect on all the following steps and will negatively impact the performance of the system. For this reason, similarly to the approach used in [1], I divided the CPA parsing task into three smaller subtasks: argument identification, syntactic classification and semantic classification. Although a single classifier could be used to jointly identify and syntactically classify each token (i.e., by directly assigning a label of "subj", "obj", etc... when a token is an argument and assigning a label of "none" when the token is not) this division allows to separately study which features work best for argument identification and thus improve it without having to worry about the syntactic classification yet.…”

Section: Cpa Parsingmentioning

confidence: 99%

Syntactic and semantic classification of verb arguments using dependency-based and rich semantic features

Elia¹

2016

Preprint

View full text Add to dashboard Cite

Corpus Pattern Analysis (CPA) has been the topic of Semeval 2015 Task 15, aimed at producing a system that can aid lexicographers in their efforts to build a dictionary of meanings for English verbs using the CPA annotation process. CPA parsing is one of the subtasks which this annotation process is made of and it is the focus of this report. A supervised machinelearning approach has been implemented, in which syntactic features derived from parse trees and semantic features derived from WordNet and word embeddings are used. It is shown that this approach performs well, even with the data sparsity issues that characterize the dataset, and can obtain better results than other system by a margin of about 4% f-score.

show abstract

“…CMILLS (Mills and Levow, 2015) used three models to solve the task: one for argument detection, and the other two for each layer. Argument detection and syntactic tagging were performed using a MaxEnt supervised classifier, while the last was based on heuristics.…”

Section: Subtaskmentioning

confidence: 99%

SemEval-2015 Task 15: A CPA dictionary-entry-building task

Baisa

Bradbury

Cinková

et al. 2015

Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

View full text Add to dashboard Cite

This paper describes the first SemEval task to explore the use of Natural Language Processing systems for building dictionary entries, in the framework of Corpus Pattern Analysis. CPA is a corpus-driven technique which provides tools and resources to identify and represent unambiguously the main semantic patterns in which words are used. Task 15 draws on the Pattern Dictionary of English Verbs (www.pdev.org.uk), for the targeted lexical entries, and on the British National Corpus for the input text.Dictionary entry building is split into three subtasks which all start from the same concordance sample: 1) CPA parsing, where arguments and their syntactic and semantic categories have to be identified, 2) CPA clustering, in which sentences with similar patterns have to be clustered and 3) CPA automatic lexicography where the structure of patterns have to be constructed automatically. Subtask 1 attracted 3 teams, though none could beat the baseline (rule-based system). Subtask 2 attracted 2 teams, one of which beat the baseline (majority-class classifier). Subtask 3 did not attract any participant.The task has produced a major semantic multidataset resource which includes data for 121 verbs and about 17,000 annotated sentences, and which is freely accessible.

show abstract

CMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing

Cited by 4 publications

References 8 publications

Semantic Frame Labeling with Target-based Neural Model

Semantic Frame Labeling with Target-based Neural Model

Syntactic and semantic classification of verb arguments using dependency-based and rich semantic features

SemEval-2015 Task 15: A CPA dictionary-entry-building task

Contact Info

Product

Resources

About