Skip to main content

Anaphora resolution

"If child doesn't strive on raw milk, boil it." Here the confusion is: 'it' refers to the child or milk, may refer to the 'child' according to machine translation which will reverse the meaning of the sentence.
'it' is an anaphora here.
Another instance:
'Because she was going to the departmental store, Mary was asked to pick up vegetables'.
-when anaphora precedes the antecedent(the entity to which anaphora refers)

 The etymology of anaphora:
ana-back upstream
phora-act of carrying
anaphora-act of carrying back
Anaphora resolution is finding the antecedent of the corresponding referent. Cohesion is the internal continuity or network of points of continuity within a text and anaphora accounts for cohesion in a text. Zero or invisible anaphora is the one that occurs when the anaphoric pronoun is omitted, as an instance-'Ramesh went to the market and (#he missing) bought a camera.'
The factors mainly used for anaphora resolution are preferences (for example- John had a pop tart. Bill had a jelly donut. Mary wanted it.What does it refer to?) and constraints (for example- Jim bought a coffee from the store. He drank it quickly. Again the reference to 'it' to which previous noun?)

 There have been various approaches for anaphora resolution-Rule based, Statistical based and Machine learning based.
Hobb's system, actually Hobb's tree search algorithm finds the most likely referent from the parse trees by searching through them in a specific order. Similarly, Niyu Ge and his team-mates from Brown University proposed an algorithm in which they incorporated multiple anaphora resolutions into a statistical framework and could get an accuracy around 84%. Robert Dale and others proposed a machine learning approach to identification and resolution of one-anaphora. For the resolution of Arabic anaphora, work has been done recently by researchers in Malaysia. An approach using pointer networks has also been used in Korea. Furthermore, a study of anaphora in biomedical scientific literature reveals that resolving anaphora is an important step in the identification of mentions of biomedical entities about which information could be extracted.




An illustration of complexity in the sentences:
"Sophia Loren says she will always be grateful to Bono. The actress revealed that the U2 singer helped her calm down when she became scared by a thunderstorm while travelling by plane"
She-Sophia Loren
The actress-Sophia Loren
The U2 singer-Bono
her-Sophia Loren
She-Sophia Loren

 Tools used for anaphora resolution are- GATE, GUITAR, BART, etc.
Still, there are challenges existing. Majority of anaphora resolution systems do not operate in fully automatic mode. Multilingual anaphora resolution is yet a difficult task.
Problems:
"We gave bananas to the monkeys because they were here". What does 'they' refer to.

References:
rgcl.wlv.ac.uk:8080/papers/cicling.doc
http://www.aclweb.org/anthology/W98-1119


Comments

Post a Comment

Popular posts from this blog

NLP in Video Games

From the last few decades, NLP (Natural Language Processing) has obtained a high level of success in the field  of Computer Science, Artificial Intelligence and Computational Logistics. NLP can also be used in video games, in fact, it is very interesting to use NLP in video games, as we can see games like Serious Games includes Communication aspects. In video games, the communication includes linguistic information that is passed either through spoken content or written content. Now the question is why and where can we use NLP in video games?  There are some games that are related to pedagogy or teaching (Serious Games). So, NLP can be used in these games to achieve these objectives in the real sense. In other games, one can use the speech control using NLP so that the player can play the game by concentrating only on visuals rather on I/O. These things at last increases the realism of the game. Hence, this is the reason for using NLP in games.  We ...
4 comments
Read more

Discourse Analysis

NLP makes machine to understand human language but we are facing issues like word ambiguity, sarcastic sentiments analysis and many more. One of the issue is to predict correctly relation between words like " Patrick went to the club on last Friday. He met Richard ." Here, ' He' refers to 'Patrick'. This kind of issue makes Discourse analysis one of the important applications of Natural Language Processing. What is Discourse Analysis ? The word discourse in linguistic terms means language in use. Discourse analysis may be defined as the process of performing text or language analysis, which involves text interpretation and knowing the social interactions. Discourse analysis may involve dealing with morphemes, n-grams, tenses, verbal aspects, page layouts, and so on. It is often used to refer to the analysis of conversations or verbal discourse. It is useful for performing tasks, like A naphora Resolution (AR) , Named Entity Recognition (NE...
5 comments
Read more

Dbpedia Datasets

WHAT IS Dbpedia? It is a project idea aiming to extract structured content from the information created in the wikipedia project. This structured information is made available on the World Wide Web. DBpedia allows users to semantically query relationships and properties of Wikipedia resources, including links to other related datsets. BUT? But why i am talking about Dbpedia ? How it is related to natural language processing? The DBpedia data set contains 4.58 million entities, out of which 4.22 million are classified in a consistent ontology, including 1,445,000 persons, 735,000 places, 123,000 music albums, 87,000 films, 19,000 video games, 241,000 organizations, 251,000 species and 6,000 diseases. The data set features labels and abstracts for these entities in up to 125 languages; 25.2 million links to images and 29.8 million links to external web pages. In addition, it contains around 50 million links...
4 comments
Read more