Science topic
Word Sense Disambiguation - Science topic
Explore the latest questions and answers in Word Sense Disambiguation, and find Word Sense Disambiguation experts.
Questions related to Word Sense Disambiguation
May I know, What are different algorithms/techniques for word sense disambiguation using knowledge based approach?
Also any resources where I can find the papers or data for my research?
Kindly help
Hi ,
This is related to my final year project for bachelors degree.
I was wondering if Reinforcement learning models can be applied to Word sense Disambiguation and that if it will give a better performance than existing methods?
Thank you
I did a word sense disambiguation project and now I need to calculate f-measure. So I have to calculate tp, tn, fp and fn. I calculated them but the problem is the fp in the first class equals to the fn in the other class and so when calculating micro average precision and recall, they have exactly same result and this is wrong. Because they should be different. How should I change the piece of code below to calculate fp and fn correctly. (this code is for a two sense wsd. t[1] is the tag (sense) of the sentence, argmax is the tag that the code has identified for the sentence).
the piece of code to calculte tp, tn, fp and fn:
if t[1] == clas1 and argmax == clas1:
tp1 += 1
elif t[1] == clas1 and argmax != clas1:
fn1 += 1
elif t[1] != clas1 and argmax == clas1:
fp1 += 1
elif t[1] != clas1 and argmax != clas1:
tn1 += 1
if t[1] == clas2 and argmax == clas2:
tp2 += 1
elif t[1] == clas2 and argmax != clas2:
fn2 += 1
elif t[1] != clas2 and argmax == clas2:
fp2 += 1
elif t[1] != clas2 and argmax != clas2:
tn2 += 1
The result:
tp1 176 tn 112 fp 49 fn 24
tp2 112 tn 176 fp 24 fn 49
MacroAvrgPrecision: 0.802875816993464
MacroAvrgRecall: 0.7878260869565217
MacroF-measure: 0.7952797587571994
true: 288 false: 73
accuracy: 79.77839335180056
weightedAvrPrecision: 0.7977839335180056
weightedAvrRecall: 0.7977839335180056
weightedF-measure: 0.7977839335180056
microAvrPrecision: 0.7977839335180056
microAvrRecall: 0.7977839335180056
microF_measure: 0.7977839335180056
For word sense disambiguation, there are supervised and unsupervised methods. The supervised method contains, statistical method, exemplar based methods and rule based methods. I know support vector machine is a supervised method, but which class of that? Is it statistical? (The answer should have a reference). Thanks.
I want to do WSD as part of my research. My dataset is not larg so I prefer to use a good tool instead of implementing a WSD algorithm.
speech perception tests such as Word and Non-word repetition tasks
I would like to identify certain processes in my study and what leads up to each one. I would like to extract this information from email messages. In order to automate the process, I am using regular expression matching but would like to explore a more robust approach .
I think identifying sample sentences and trying to match its semantics with sentences in email messages would be a good start.
I have been through and ran sample java code for stemming, pos, lemmatizing and similarity. However I am now looking for some basic code which integrates all this
approaches in one program/project. I am hoping it also includes tokenisation and word sense disambiguation as well. Importantly it should have an approach of calculating sentence similarity as well. I am sure some one has done this.
I am particularly looking for java, standford core nlp and wordnet approach which integrates tokenising, stemming, pos, lemmatizing, word sense disambiguation and an approach of calculating sentence similarity as well
I'm looking for interesting/original applications of CRFs in NLP/text-mining that would not be PoS Tagging or Named Entity Recognition. Things like reconstruction the structure of a document, word sense disambiguation or pattern recognition for instance, but that can be something else.
Do you know of some?
My motivation is to somehow (blindly) learn (negative) patterns with plain text corpora.
For a bag of words {this, is, a, book}, once a corpus tells us there is no usage of "book is this a" for sure, and so on so forth, then hopefully by negation one may find some hidden rules to promote the bag-of-words model to something similar to LDA.
I am familiar with TLG and the Perseus Digital Project. I want to do corpus linguistics on Hellenistic Greek. Some of the things I need to do is search by POS, search by Lemma, search by morphological element (reduplication, particular morpheme, stem formation, etc.) and search for collocates.
I am not sure either of the above will do all of that. I am considering developing my own corpora and using a tagger that does all of this to the corpora, as well as a search engine that will recognize what I tagged.
Do I need to do this, or is there already a selection of tools that will get the job done?
I'm working on a case in which I need a WSD algorithm to disambiguate all the words of a sentence for a step.
I want to know if there is any tool which can help to make it's implementation faster.
Of course if it'll be in Java it would be much more better.
Pagerank works on a graph which only has direct edges between vertices and there is no weight on edges of the graph but random walk's graph edges are not directed and they have weight. Then, how we should change pagerank which could be applied to these kinds of graphs.
