In linguistics, a word sense is one of the meanings of a word. For example, a dictionary may have over 50 different senses of the word play, each of these having a different meaning based on the context of the word's usage in a sentence, as follows:
In each sentence we associate a different meaning of the word "play" based on hints the rest of the sentence gives us.
People and computers, as they read words, must use a process called word-sense disambiguation to find the correct meaning of a word. This process uses context to narrow the possible senses down to the probable ones. The context includes such things as the ideas conveyed by adjacent words and nearby phrases, the known or probable purpose and register of the conversation or document, and the orientation (time and place) implied or expressed. The disambiguation is thus context-sensitive.
A word sense may correspond to either a seme (the smallest unit of meaning) or a sememe (the next larger unit of meaning), and polysemy is the property of having multiple semes or sememes and thus multiple senses.
The human brain is quite proficient at word-sense disambiguation. The fact that natural language is formed in a way that requires so much of it is a reflection of that neurologic reality. In other words, human language developed in a way that reflects (and also has helped to shape) the innate ability provided by the brain's neural networks. In computer science and the information technology that it enables, it has been a long-term challenge to develop the ability in computers to do natural language processing and machine learning.
To date, a rich variety of techniques have been researched, from dictionary-based methods that use the knowledge encoded in lexical resources, to supervised machine learning methods in which a classifier is trained for each distinct word on a corpus of manually sense-annotated examples, to completely unsupervised methods that cluster occurrences of words, thereby inducing word senses. Among these, supervised learning approaches have been the most successful algorithms to date.
Microsoft Office 2008 for Mac is a version of the Microsoft Officeproductivity suite for Mac OS X. It supersedes Office 2004 for Mac (which did not have Intel native code) and is the Mac OS X equivalent of Office 2007. Office 2008 was developed by Microsoft's Macintosh Business Unit and released on January 15, 2008. Office 2008 was the last version of Office for Mac to support Mac OS X Tiger (10.4.9 or higher) and Macs with a PowerPC processor (G4 or higher) as well as newer Macs with Intel processors. Office 2008 was followed by Microsoft Office for Mac 2011 released on October 26, 2010, requiring a Mac with an Intel processor and Mac OS version 10.5 or later. Office 2008 is also the last version to feature Entourage, which was replaced by Outlook in Office 2011.
Release
Office 2008 was originally slated for release in the second half of 2007; however, it was delayed until January 2008, purportedly to allow time to fix lingering bugs. Office 2008 is the first version of Office for Mac supplied as a Universal Binary.
Mod-01 Lec-35 Word Sense Disambiguation: Semi - Supervised and Unsupervised method
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
published: 03 Jul 2012
Mod-01 Lec-34 Word Sense Disambiguation: Supervised and Unsupervised methods
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
published: 03 Jul 2012
Semi Supervised Preposition-Sense Disambiguation using Multilingual Data - Hila Gonen
published: 04 Jul 2017
Mod-01 Lec-31 Wordnet; Metonymy and Word Sense Disambiguation
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
published: 03 Jul 2012
Unsupervised Word Sense Disambiguation with Images and Videos, Seyed Kamyar Seyed Ghasemipour
DCS Undergraduate Research Video competition 2014.
First place winner: Seyed Kamyar Seyed Ghasemipour
published: 05 Nov 2014
Mod-01 Lec-33 Word Sense Disambiguation; Overlap Based Method; Supervised Method
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
published: 03 Jul 2012
Supervised Word Sense Disambiguation
published: 14 Jun 2021
Rapid Construction of Supervised Word Sense Disambiguation System for Lesser-resourced Languages
We introduce a method to quickly build a Word Sense Disambiguation (WSD) system for a lesser-resourced language L, under the condition that a Statistical Machine Transation system (SMT) is available from a well resourced language where semantically annotated corpora are available (here, English) towards L. We argue that it is less difficult to obtain the resources mandatory for the development of an SMT system (parallel-corpora) than it is to create the resources necessary for a WSD system (semantically annotated corpora, lexical resources). In the present work, we propose to translate a semantically annotated corpus from English to L and then to create a WSD system for L following the classical supervised WSD paradigm. We demonstrate the feasibility and genericity of our proposed method b...
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel...
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel...
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel...
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel...
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
We introduce a method to quickly build a Word Sense Disambiguation (WSD) system for a lesser-resourced language L, under the condition that a Statistical Machin...
We introduce a method to quickly build a Word Sense Disambiguation (WSD) system for a lesser-resourced language L, under the condition that a Statistical Machine Transation system (SMT) is available from a well resourced language where semantically annotated corpora are available (here, English) towards L. We argue that it is less difficult to obtain the resources mandatory for the development of an SMT system (parallel-corpora) than it is to create the resources necessary for a WSD system (semantically annotated corpora, lexical resources). In the present work, we propose to translate a semantically annotated corpus from English to L and then to create a WSD system for L following the classical supervised WSD paradigm. We demonstrate the feasibility and genericity of our proposed method by translating SemCor from English to Bangla and from English to French. SemCor is an English corpus annotated with Princeton WordNet sense tags. We show the feasibility of the approach using the Multilingual WSD task from Semeval 2013.
We introduce a method to quickly build a Word Sense Disambiguation (WSD) system for a lesser-resourced language L, under the condition that a Statistical Machine Transation system (SMT) is available from a well resourced language where semantically annotated corpora are available (here, English) towards L. We argue that it is less difficult to obtain the resources mandatory for the development of an SMT system (parallel-corpora) than it is to create the resources necessary for a WSD system (semantically annotated corpora, lexical resources). In the present work, we propose to translate a semantically annotated corpus from English to L and then to create a WSD system for L following the classical supervised WSD paradigm. We demonstrate the feasibility and genericity of our proposed method by translating SemCor from English to Bangla and from English to French. SemCor is an English corpus annotated with Princeton WordNet sense tags. We show the feasibility of the approach using the Multilingual WSD task from Semeval 2013.
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
Natural Language Processing by Prof. Pushpak Bhattacharyya, Department of Computer science & Engineering,IIT Bombay.For more details on NPTEL visit http://nptel.iitm.ac.in
We introduce a method to quickly build a Word Sense Disambiguation (WSD) system for a lesser-resourced language L, under the condition that a Statistical Machine Transation system (SMT) is available from a well resourced language where semantically annotated corpora are available (here, English) towards L. We argue that it is less difficult to obtain the resources mandatory for the development of an SMT system (parallel-corpora) than it is to create the resources necessary for a WSD system (semantically annotated corpora, lexical resources). In the present work, we propose to translate a semantically annotated corpus from English to L and then to create a WSD system for L following the classical supervised WSD paradigm. We demonstrate the feasibility and genericity of our proposed method by translating SemCor from English to Bangla and from English to French. SemCor is an English corpus annotated with Princeton WordNet sense tags. We show the feasibility of the approach using the Multilingual WSD task from Semeval 2013.
In linguistics, a word sense is one of the meanings of a word. For example, a dictionary may have over 50 different senses of the word play, each of these having a different meaning based on the context of the word's usage in a sentence, as follows:
In each sentence we associate a different meaning of the word "play" based on hints the rest of the sentence gives us.
People and computers, as they read words, must use a process called word-sense disambiguation to find the correct meaning of a word. This process uses context to narrow the possible senses down to the probable ones. The context includes such things as the ideas conveyed by adjacent words and nearby phrases, the known or probable purpose and register of the conversation or document, and the orientation (time and place) implied or expressed. The disambiguation is thus context-sensitive.
A word sense may correspond to either a seme (the smallest unit of meaning) or a sememe (the next larger unit of meaning), and polysemy is the property of having multiple semes or sememes and thus multiple senses.