SemEval-2017 Task 7: Detection and Interpretation of English Puns

@inproceedings{Miller2017SemEval2017T7,
  title={SemEval-2017 Task 7: Detection and Interpretation of English Puns},
  author={Tristan Miller and Christian F. Hempelmann and Iryna Gurevych},
  booktitle={SemEval@ACL},
  year={2017}
}
A pun is a form of wordplay in which a word suggests two or more meanings by exploiting polysemy, homonymy, or phonological similarity to another word, for an intended humorous or rhetorical effect.  Though a recurrent and expected feature in many discourse types, puns stymie traditional approaches to computational lexical semantics because they violate their one-sense-per-context assumption.  This paper describes the first competitive evaluation for the automatic detection, location, and… 

Tables from this paper

Joint Detection and Location of English Puns

An approach that addresses pun detection and pun location jointly from a sequence labeling perspective is presented, employing a new tagging scheme such that the model is capable of performing such a joint task, where useful structural information can be properly captured.

Detecting Intentional Lexical Ambiguity in English Puns

A model of automatic analysis of puns, where a word is intentionally used in two meanings at the same time (the target word) and several rule-based methods are applied to locate intentionally ambiguous words, based on structural and semantic criteria.

Sense-Aware Neural Models for Pun Location in Texts

This paper proposes a sense-aware neural model that leverages a bidirectional LSTM network to model each sequence of word senses in the task of pun location, which aims to identify the pun word in a given short text.

N-Hance at SemEval-2017 Task 7: A Computational Approach using Word Association for Puns

A system developed for SemEval-2017 Task 7, Detection and Interpretation of English Puns consisting of three subtasks; pun detection, pun location, and pun interpretation, respectively, confirms the potential of this approach.

Idiom Savant at Semeval-2017 Task 7: Detection and Interpretation of English Puns

This paper describes our system, entitled Idiom Savant, for the 7th Task of the Semeval 2017 workshop, “Detection and interpretation of English Puns”. Our system consists of two probabilistic models

AmbiPun: Generating Humorous Puns with Ambiguous Context

In this paper, we propose a simple yet effective way to generate pun sentences that does not require any training on existing puns. Our approach is inspired by humor theories that ambiguity comes

BuzzSaw at SemEval-2017 Task 7: Global vs. Local Context for Interpreting and Locating Homographic English Puns with Sense Embeddings

A knowledge-based Word Sense Disambiguation (WSD) method based on sense embeddings is used for pun interpretation, which splits the context that is input to the WSD system into two local contexts and finds the best sense for each of them.

Homophonic Pun Generation with Lexically Constrained Rewriting

This paper first finds the constraint words supporting the semantic incongruity for a sentence, then rewrite the sentence with explicit positive and negative constraints, and achieves the state-of-the-art results in both automatic and human evaluations.

PunFields at SemEval-2018 Task 3: Detecting Irony by Tools of Humor Analysis

PunFields, the system of automatic analysis of English puns that was introduced at SemEval-2017, is used to detect irony in tweets, and preliminary tests showed that it can reach the score of F1=0.596.

WECA: A WordNet-Encoded Collocation-Attention Network for Homographic Pun Recognition

This work uses WordNet to understand and expand word embedding for settling the polysemy of homographic puns, and proposes a WordNet-Encoded Collocation-Attention network model (WECA) which combined with the context weights for recognizing the puns.
...

References

SHOWING 1-10 OF 56 REFERENCES

N-Hance at SemEval-2017 Task 7: A Computational Approach using Word Association for Puns

A system developed for SemEval-2017 Task 7, Detection and Interpretation of English Puns consisting of three subtasks; pun detection, pun location, and pun interpretation, respectively, confirms the potential of this approach.

Idiom Savant at Semeval-2017 Task 7: Detection and Interpretation of English Puns

This paper describes our system, entitled Idiom Savant, for the 7th Task of the Semeval 2017 workshop, “Detection and interpretation of English Puns”. Our system consists of two probabilistic models

BuzzSaw at SemEval-2017 Task 7: Global vs. Local Context for Interpreting and Locating Homographic English Puns with Sense Embeddings

A knowledge-based Word Sense Disambiguation (WSD) method based on sense embeddings is used for pun interpretation, which splits the context that is input to the WSD system into two local contexts and finds the best sense for each of them.

Fermi at SemEval-2017 Task 7: Detection and Interpretation of Homographic puns in English Language

This paper describes the system for detection and interpretation of English puns and provides detailed description of the approach, as well as the results obtained in the task.

UWaterloo at SemEval-2017 Task 7: Locating the Pun Using Syntactic Characteristics and Corpus-based Metrics

Analysis of the developed method for locating a pun word showed that IDF is the most useful characteristic, whereas the count of words with which the given word has high NPMI has a negative effect on performance.

Automatic disambiguation of English puns

This paper describes how traditional, language-agnostic WSD approaches can be adapted to "disambiguate" puns, or rather to identify their double meanings and evaluates several such approaches on a manually sense-annotated corpus of English puns.

ECNU at SemEval-2017 Task 7: Using Supervised and Unsupervised Methods to Detect and Locate English Puns

This paper describes the submissions to task 7 in SemEval 2017, i.e., Detection and Interpretation of English Puns, and the first two subtasks, which are to detect and locate English puns respectively.

ELiRF-UPV at SemEval-2017 Task 7: Pun Detection and Interpretation

The ELiRF-UPV team's approach is based on the use of word embeddings to find related words in a sentence and a version of the Lesk algorithm to establish relationships between synsets.

UWAV at SemEval-2017 Task 7: Automated feature-based system for locating puns

This system is created for SemEval-2017 Task 7: Detection and Interpretation of English Puns by leveraging features selected from sentences to design a classifier that can disambiguate between the presence or absence of a pun.

PunFields at SemEval-2017 Task 7: Employing Roget’s Thesaurus in Automatic Pun Recognition and Interpretation

A model of automatic interpretation of English puns, based on Roget’s Thesaurus, and its implementation, PunFields, which shows a considerably good result in pun classification, but requires improvement in searching for the target word and its definition.
...