Automatic disambiguation of English puns

@inproceedings{Miller2015AutomaticDO,
  title={Automatic disambiguation of English puns},
  author={Tristan Miller and Iryna Gurevych},
  booktitle={Annual Meeting of the Association for Computational Linguistics},
  year={2015}
}
Traditional approaches to word sense disambiguation (WSD) rest on the assumption that there exists a single, unambiguous communicative intention underlying every word in a document. However, writers sometimes intend for a word to be interpreted as simultaneously carrying multiple distinct meanings. This deliberate use of lexical ambiguity---i.e., punning---is a particularly common source of humour. In this paper we describe how traditional, language-agnostic WSD approaches can be adapted to… 

Tables from this paper

Towards the automatic detection and identification of English puns

A case for research into computational methods for the detection of puns in running text and for the isolation of the intended meanings is made and plans for evaluating WSD-inspired systems in a dedicated pun identification task are outlined.

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

The first competitive evaluation for the automatic detection, location, and interpretation of puns is described, which describes the motivation for these tasks, the evaluation methods, and the manually annotated data set.

A Synset Relation-enhanced Framework with a Try-again Mechanism for Word Sense Disambiguation

A Synset Relation-Enhanced Framework that leverages sense relations for both sense embedding enhancement and a try-again mechanism that implements WSD again, after obtaining basic sense embeddings from augmented WordNet glosses is proposed.

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

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.

A Dual-Attention Neural Network for Pun Location and Using Pun-Gloss Pairs for Interpretation

A model called DANN (Dual-Attentive Neural Network) is proposed for pun location, effectively integrates word senses and pronunciation with context information to address two kinds of pun at the same time.

Humour Agent Detection in Puns

  • MonikaSonakshi Vij
  • Computer Science
    2019 4th International Conference on Internet of Things: Smart Innovation and Usages (IoT-SIU)
  • 2019
This paper aims to propose a method to identify the humour agent in pun-based sentences that utilizes the structural information of the sentence and then uses a semantic similarity measure to find a relationship between the words.

Punny Captions: Witty Wordplay in Image Descriptions

In a Turing test style evaluation, people find the image descriptions generated by the model to be slightly wittier than human-written witty descriptions when the human is subject to similar constraints as the model regarding word usage and style.

A MBI P UN : Generating Puns with Ambiguous Context

A simple yet effective way to generate pun sentences that does not require any training on existing puns by outperforming well crafted baselines and the state-of-the-art models by a large margin.

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.
...

References

SHOWING 1-10 OF 56 REFERENCES

Towards the automatic detection and identification of English puns

A case for research into computational methods for the detection of puns in running text and for the isolation of the intended meanings is made and plans for evaluating WSD-inspired systems in a dedicated pun identification task are outlined.

DKPro WSD: A Generalized UIMA-based Framework for Word Sense Disambiguation

Implementations of word sense disambiguation (WSD) algorithms tend to be tied to a particular test corpus format and sense inventory. This makes it difficult to test their performance on new data

Using Distributional Similarity for Lexical Expansion in Knowledge-based Word Sense Disambiguation

A distributional thesaurus is used, computed from a large parsed corpus, for lexical expansion of context and sense information and it is shown that distributional information significantly improves disambiguation results across several data sets.

A Language-independent Sense Clustering Approach for Enhanced WSD

A method for clustering word senses of a lexical-semantic resource by mapping them to those of another sense inventory by using Dijkstra-WSA, a parameterizable alignment algorithm which is largely resource- and language-agnostic.

Knowledge-Rich Word Sense Disambiguation Rivaling Supervised Systems

It is shown that, when provided with a vast amount of high-quality semantic relations, simple knowledge-lean disambiguation algorithms compete with state-of-the-art supervised WSD systems in a coarse-grained all-words setting and outperform them on gold-standard domain-specific datasets.

An Enhanced Lesk Word Sense Disambiguation Algorithm through a Distributional Semantic Model

A new Word Sense Disambiguation (WSD) algorithm which extends two well-known variations of the Lesk WSD method which relies on the use of a word similarity function defined on a distributional semantic space to compute the gloss-context overlap.

SemEval-2013 Task 13: Word Sense Induction for Graded and Non-Graded Senses

A new SemEval task for evaluating Word Sense Induction and Disambiguation systems in a setting where instances may be labeled with multiple senses, weighted by their applicability.

An analysis of ambiguity in word sense annotations

It is shown that contextual underspecification is the primary cause of multiple interpretations but that syllepsis still accounts for more than a third of the cases and that sense coarsening can only partially remove the need for labeling instances with multiple senses.

Reducing Lexical Semantic Complexity with Systematic Polysemous Classes and Underspecification

This paper presents an algorithm for finding systematic polysemous classes in WordNet and similar semantic databases, based on a definition in (Apresjan 1973), while addressing some previous shortcomings.

Automatically Extracting Word Relationships as Templates for Pun Generation

T-PEG, a system that utilizes phonetic and semantic linguistic resources to automatically extract word relationships in puns and store the knowledge in template form, resulting in computer-generated puns that received an average score of 2.13 as compared to 2.70 for human- generated puns from user feedback.
...