Browse SoTA > Natural Language Processing > Word Sense Disambiguation

Word Sense Disambiguation

41 papers with code · Natural Language Processing

The task of Word Sense Disambiguation (WSD) consists of associating words in context with their most suitable entry in a pre-defined sense inventory. The de-facto sense inventory for English in WSD is WordNet. For example, given the word “mouse” and the following sentence:

“A mouse consists of an object held in one's hand, with one or more buttons.”

we would assign “mouse” with its electronic device sense (the 4th sense in the WordNet sense inventory).

Benchmarks

TREND DATASET BEST METHOD PAPER TITLE PAPER CODE COMPARE

Latest papers without code

Multimodal Word Sense Disambiguation in Creative Practice

15 Jul 2020

We present a dataset, Ambiguous Descriptions of Art Images (ADARI), of contemporary workpieces, which aims to provide a foundational resource for subjective image description and multimodal word disambiguation in the context of creative practice.

MULTI-LABEL CLASSIFICATION SENTENCE CLASSIFICATION WORD SENSE DISAMBIGUATION

Moving Down the Long Tail of Word Sense Disambiguation with Gloss Informed Bi-encoders

ACL 2020

A major obstacle in Word Sense Disambiguation (WSD) is that word senses are not uniformly distributed, causing existing models to generally perform poorly on senses that are either rare or unseen during training.

WORD SENSE DISAMBIGUATION

CluBERT: A Cluster-Based Approach for Learning Sense Distributions in Multiple Languages

ACL 2020

Knowing the Most Frequent Sense (MFS) of a word has been proved to help Word Sense Disambiguation (WSD) models significantly.

WORD SENSE DISAMBIGUATION

SenseBERT: Driving Some Sense into BERT

ACL 2020

The ability to learn from large unlabeled corpora has allowed neural language models to advance the frontier in natural language understanding.

LANGUAGE MODELLING NATURAL LANGUAGE UNDERSTANDING WORD SENSE DISAMBIGUATION

Personalized PageRank with Syntagmatic Information for Multilingual Word Sense Disambiguation

ACL 2020

Exploiting syntagmatic information is an encouraging research focus to be pursued in an effort to close the gap between knowledge-based and supervised Word Sense Disambiguation (WSD) performance.

WORD SENSE DISAMBIGUATION

Hinting Semantic Parsing with Statistical Word Sense Disambiguation

29 Jun 2020

The task of Semantic Parsing can be approximated as a transformation of an utterance into a logical form graph where edges represent semantic roles and nodes represent word senses.

SEMANTIC PARSING WORD SENSE DISAMBIGUATION

Exploiting Non-Taxonomic Relations for Measuring Semantic Similarity and Relatedness in WordNet

22 Jun 2020

Various applications in the areas of computational linguistics and artificial intelligence employ semantic similarity to solve challenging tasks, such as word sense disambiguation, text classification, information retrieval, machine translation, and document clustering.

INFORMATION RETRIEVAL MACHINE TRANSLATION SEMANTIC SIMILARITY SEMANTIC TEXTUAL SIMILARITY TEXT CLASSIFICATION WORD SENSE DISAMBIGUATION

Explainable and Discourse Topic-aware Neural Language Understanding

18 Jun 2020

Marrying topic models and language models exposes language understanding to a broader source of document-level context beyond sentences via topics.

DOCUMENT CLASSIFICATION LANGUAGE MODELLING TEXT GENERATION TOPIC MODELS WORD SENSE DISAMBIGUATION

An Algorithm for Fuzzification of WordNets, Supported by a Mathematical Proof

7 Jun 2020

Although the standard WLDs are being used in many successful Text-Mining applications, they have the limitation that word-senses are considered to represent the meaning associated to their corresponding synsets, to the same degree, which is not generally true.

WORD SENSE DISAMBIGUATION