• Corpus ID: 18099133

The Theory of Correlation Formulas and Their Application to Discourse Coherence

@inproceedings{Michael2015TheTO,
  title={The Theory of Correlation Formulas and Their Application to Discourse Coherence},
  author={Julian Michael},
  year={2015}
}
The Winograd Schema Challenge (WSC) was proposed as a measure of machine intelligence. It boils down to anaphora resolution, a task familiar from computational linguistics. Research in linguistics and AI has coalesced around discourse coherence as the critical factor in solving this task, and the process of establishing discourse coherence relies fundamentally on world and commonsense knowledge. In this thesis, we build on an approach to establishing coherence on the basis of correlation. The… 
1 Citations

Tables from this paper

Back to Square One: Artifact Detection, Training and Commonsense Disentanglement in the Winograd Schema

TLDR
It is suggested that the apparent progress on WS may not necessarily reflect progress in commonsense reasoning, and the observed progress is mostly due to the use of supervision in training WS models, which is not likely to successfully support all the required Commonsense reasoning skills and knowledge.

References

SHOWING 1-10 OF 33 REFERENCES

The Winograd Schema Challenge and Reasoning about Correlation

TLDR
A framework for reasoning about correlation between sentences is introduced, and it is shown how this framework can be used to justify solutions to some Winograd Schema problems.

An intelligent co-reference resolver for Winograd schema sentences containing resolved semantic entities

TLDR
A pronoun resolver system for the confined domain Winograd sentences and four answering modules which use world knowledge and inferencing mechanisms to try and resolve the pronoun, which gets nearly 4.5 % improvement in the restricted domain.

Solving Winograd Schema Challenge : Using Semantic Parsing, Automatic Knowledge Acquisition and Logical Reasoning

TLDR
A novel technique to solve the Winograd Schema Challenge, a question answering test for predicting the human level intelligence in machines that consists of sentence and question pairs such that the answer to the question depends on the resolution of a definite pronoun or adjective in the sentence.

Coherence and Coreference

TLDR
In this paper, formal definitions are given for several coherence relations, based on the operations of an inference system; that is, the relations between successive portions of a discourse are characterized in terms of the inferences that can be drawn from each.

Ontological Promiscuity

TLDR
This paper proposes a logical notation which is first-order and nonintensional, and for which semantic translation can be naively compositional, and makes a statement about the view of semantics that is presupposed by this approach.

Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge

TLDR
A knowledge-rich approach to the task of resolving complex cases of definite pronouns is employed, which yields a pronoun resolver that outperforms state-of-the-art resolvers by nearly 18 points in accuracy on the authors' dataset.

Coherence and Coreference Revisited

TLDR
The results suggest that pronoun interpretation is incrementally influenced by probabilistic expectations that hearers have regarding what coherence relations are likely to ensue, together with their expectations about what entities will be mentioned next, which, crucially, are conditioned on those coherence Relations.

Coreference Resolution with ILP-based Weighted Abduction

TLDR
This paper presents the first systematic study of the coreference resolution problem in a general inference-based discourse processing framework by employing the mode of inference called weighted abduction and employing a new efficient implementation of weighted abduction based on Integer Linear Programming.

Interpretation as Abduction

TLDR
An approach to abductive inference, called “weighted abduction”, that has resulted in a significant simplification of how the problem of interpreting texts is conceptualized, can be combined with the older view of “parsing as deduction” to produce an elegant and thorough integration of syntax, semantics, and pragmatics.

Weak vs. strong readings of donkey sentences and monotonicity inference in a dynamic setting

In this paper, I show that the availability of what some authors have called the weak reading and the strong reading of donkey sentences with relative clauses is systematically related to