Article Structure
Abstract
Temporal resolution systems are traditionally tuned to a particular language, requiring significant human effort to translate them to new languages.
Introduction
Temporal resolution is the task of mapping from a textual phrase describing a potentially complex time, date, or duration to a normalized (grounded) temporal representation.
Related Work
Our approach follows the work of Angeli et al.
Temporal Representation
We define a compositional representation of time, similar to Angeli et a1.
Learning
The system is trained using a discriminative k:-best parser, which is able to incorporate arbitrary features over partial derivations.
Evaluation
We evaluate our model on all six languages in the TempEval-2 Task A dataset (Verhagen et al.,
Conclusion
We have presented a discriminative, multilingual approach to resolving temporal expressions, using a language-flexible latent parse and rich features on both the types and values of partial derivations in the parse.
Topics
rule-based
Appears in 6 sentences as: rule-based (6)
In Language-Independent Discriminative Parsing of Temporal Expressions
- Many approaches to this problem make use of rule-based methods, combining regular-expression matching and handwritten interpretation functions.
Page 1, “Introduction”
- dynamically back off to a rule-based system in the case of low confidence parses.
Page 1, “Introduction”
- A rule-based number recognizer was used for each language to recognize and ground numeric expressions, including information on whether the number was an ordinal (e.g., two versus second).
Page 5, “Learning”
- 0 GUTime (Mani and Wilson, 2000), a widely used, older rule-based system.
Page 8, “Evaluation”
- o SUTime (Chang and Manning, 2012), a more recent rule-based system for English.
Page 8, “Evaluation”
- o UC3M (Vicente-Diez et al., 2010), a rule-based system for Spanish.
Page 8, “Evaluation”
See all papers in Proc. ACL 2013 that mention rule-based.
See all papers in Proc. ACL that mention rule-based.
Back to top.
logical form
Appears in 4 sentences as: logical form (2) logical forms (2)
In Language-Independent Discriminative Parsing of Temporal Expressions
- For example, Zettlemoyer and Collins (2007) learn a mapping from textual queries to a logical form .
Page 2, “Related Work”
- Importantly, the logical form of these parses contain all of the predicates and entities used in the parse — unlike the label provided in our case, where a grounded time can correspond to any of a number of latent parses.
Page 2, “Related Work”
- (2011) relax supervision to require only annotated answers rather than full logical forms .
Page 2, “Related Work”
- Recent probabilistic approaches to temporal resolution include UzZaman and Allen (2010), who employ a parser to produce deep logical forms , in conjunction with a CRF classifier.
Page 2, “Related Work”
See all papers in Proc. ACL 2013 that mention logical form.
See all papers in Proc. ACL that mention logical form.
Back to top.
parse tree
Appears in 4 sentences as: parse tree (4)
In Language-Independent Discriminative Parsing of Temporal Expressions
- The root of a parse tree should be one of these types.
Page 2, “Temporal Representation”
- At the root of a parse tree , we recursively apply
Page 3, “Temporal Representation”
- Inference A discriminative k-best parser was used to allow for arbitrary features in the parse tree .
Page 5, “Learning”
- Unlike syntactic parsing, child types of a parse tree uniquely define the parent type of the rule; this is a direct consequence of our combination rules being functions with domains defined in terms of the temporal types, and therefore necessarily projecting their inputs into a single output type.
Page 5, “Learning”
See all papers in Proc. ACL 2013 that mention parse tree.
See all papers in Proc. ACL that mention parse tree.
Back to top.
semantic parser
Appears in 4 sentences as: semantic parser (2) semantic parsing (2)
In Language-Independent Discriminative Parsing of Temporal Expressions
- We present a language independent semantic parser for learning the interpretation of temporal phrases given only a corpus of utterances and the times they reference.
Page 1, “Abstract”
- As in this previous work, our approach draws inspiration from work on semantic parsing .
Page 2, “Related Work”
- Supervised approaches to semantic parsing prominently include Zelle and Mooney (1996), Zettlemoyer and Collins (2005), Kate et al.
Page 2, “Related Work”
- 0 ParsingTime (Angeli et al., 2012), a semantic parser for temporal expressions, similar to this system (see Section 2).
Page 8, “Evaluation”
See all papers in Proc. ACL 2013 that mention semantic parser.
See all papers in Proc. ACL that mention semantic parser.
Back to top.