Automatically Tagging Constructions of Causation and Their Slot-Fillers
05 Jun 2017-Transactions of the Association for Computational Linguistics (MIT Press One Rogers Street, Cambridge, MA 02142-1209 USA journals-info@mit.edu)-Vol. 5, Iss: 1, pp 117-133
TL;DR: This paper describes two supervised approaches for tagging causal constructions and their arguments that combine automatically induced pattern-matching rules with statistical classifiers that learn the subtler parameters of the constructions.
Abstract: This paper explores extending shallow semantic parsing beyond lexical-unit triggers, using causal relations as a test case. Semantic parsing becomes difficult in the face of the wide variety of linguistic realizations that causation can take on. We therefore base our approach on the concept of constructions from the linguistic paradigm known as construction grammar (CxG). In CxG, a construction is a form/function pairing that can rely on arbitrary linguistic and semantic features. Rather than codifying all aspects of each construction’s form, as some attempts to employ CxG in NLP have done, we propose methods that offload that problem to machine learning. We describe two supervised approaches for tagging causal constructions and their arguments. Both approaches combine automatically induced pattern-matching rules with statistical classifiers that learn the subtler parameters of the constructions. Our results show that these approaches are promising: they significantly outperform naive baselines for both construction recognition and cause and effect head matches.
Citations
More filters
01 Jan 2016
TL;DR: In this article, a construction grammar approach to argument structure is used to deal with argument structure in a good book with a cup of tea in the afternoon, but instead they cope with some harmful virus inside their computer.
Abstract: Thank you for downloading constructions a construction grammar approach to argument structure. As you may know, people have search numerous times for their favorite readings like this constructions a construction grammar approach to argument structure, but end up in harmful downloads. Rather than enjoying a good book with a cup of tea in the afternoon, instead they cope with some harmful virus inside their computer.
979 citations
01 Jul 2018
TL;DR: This paper forms the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality, and shows that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
Abstract: Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must occur earlier than its effect, temporal and causal relations are closely related and one relation often dictates the value of the other. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints that are inherent in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
125 citations
Cites methods from "Automatically Tagging Constructions..."
...Dunietz et al. (2017) used the concept of construction grammar to tag causally related clauses or phrases....
[...]
01 Apr 2017
TL;DR: A new version of the BECauSE corpus is presented with exhaustively annotated expressions of causal language, but also seven semantic relations that are frequently co-present with causation, showing high inter-annotator agreement.
Abstract: Language of cause and effect captures an essential component of the semantics of a text. However, causal language is also intertwined with other semantic relations, such as temporal precedence and correlation. This makes it difficult to determine when causation is the primary intended meaning. This paper presents BECauSE 2.0, a new version of the BECauSE corpus with exhaustively annotated expressions of causal language, but also seven semantic relations that are frequently co-present with causation. The new corpus shows high inter-annotator agreement, and yields insights both about the linguistic expressions of causation and about the process of annotating co-present semantic relations.
72 citations
Posted Content•
TL;DR: The authors formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints inherently in the nature of time and causality, and show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
Abstract: Understanding temporal and causal relations between events is a fundamental natural language understanding task. Because a cause must be before its effect in time, temporal and causal relations are closely related and one relation even dictates the other one in many cases. However, limited attention has been paid to studying these two relations jointly. This paper presents a joint inference framework for them using constrained conditional models (CCMs). Specifically, we formulate the joint problem as an integer linear programming (ILP) problem, enforcing constraints inherently in the nature of time and causality. We show that the joint inference framework results in statistically significant improvement in the extraction of both temporal and causal relations from text.
41 citations
References
More filters
Journal Article•
TL;DR: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems, focusing on bringing machine learning to non-specialists using a general-purpose high-level language.
Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from http://scikit-learn.sourceforge.net.
47,974 citations
"Automatically Tagging Constructions..." refers methods in this paper
...We use the Scikit-learn 0.17.1 (Pedregosa et al., 2011) implementation of logistic regression with L1 regularization and balanced class weights....
[...]
Posted Content•
TL;DR: Scikit-learn as mentioned in this paper is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems.
Abstract: Scikit-learn is a Python module integrating a wide range of state-of-the-art machine learning algorithms for medium-scale supervised and unsupervised problems. This package focuses on bringing machine learning to non-specialists using a general-purpose high-level language. Emphasis is put on ease of use, performance, documentation, and API consistency. It has minimal dependencies and is distributed under the simplified BSD license, encouraging its use in both academic and commercial settings. Source code, binaries, and documentation can be downloaded from this http URL.
28,898 citations
3,698 citations
"Automatically Tagging Constructions..." refers background in this paper
...• the average Jaccard index (Jaccard, 1912) for gold-standard vs....
[...]
...For each, we report: • percent agreement on exact spans • percent agreement on heads • the average Jaccard index (Jaccard, 1912) for gold-standard vs. predicted spans, defined as J(A,B) = |A∩B||A∪B| , where A and B are the sets of tokens in the two spans....
[...]
23 Aug 1992
TL;DR: A set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest are identified.
Abstract: We describe a method for the automatic acquisition of the hyponymy lexical relation from unrestricted text. Two goals motivate the approach: (i) avoidance of the need for pre-encoded knowledge and (ii) applicability across a wide range of text. We identify a set of lexico-syntactic patterns that are easily recognizable, that occur frequently and across text genre boundaries, and that indisputably indicate the lexical relation of interest. We describe a method for discovering these patterns and suggest that other lexical relations will also be acquirable in this way. A subset of the acquisition algorithm is implemented and the results are used to augment and critique the structure of a large hand-built thesaurus. Extensions and applications to areas such as information retrieval are suggested.
3,550 citations
"Automatically Tagging Constructions..." refers background in this paper
...These patterns, similarly represented as fragments of dependency parse trees with slots, have proven useful for hypernym discovery (Hearst, 1992; Snow et al., 2005)....
[...]
Book•
15 Mar 1995
TL;DR: In this paper, the interaction between verbs and constructions is discussed, and relations among constructions are investigated in the context of English Ditransitive construction and English Caused-Motion construction.
Abstract: Acknowledgments 1: Introduction 2: The Interaction between Verbs and Constructions 3: Relations among Constructions 4: On Linking 5: Partial Productivity 6: The English Ditransitive Construction 7: The English Caused-Motion Construction 8: The English Resultative Construction 9: The Way Construction 10: Conclusion Notes Bibliography Index
3,382 citations
Additional excerpts
...A more general approach can be found in the principles of CONSTRUCTION GRAMMAR (CxG; Fillmore et al., 1988; Goldberg, 1995)....
[...]