# Keyword Extractor

## Tasks

1. Refactor Bert embedder code from previous tasks so that it can be used in the Keyword Extractor. **POINTS: 5**
2. Research YAKE algorithm, create interface for its usage. If possible and reasonable, experiment with custom implementation of this algorithm. **POINTS: 5**
3. Research RAKE algorithm, create interface for its usage. If possible and reasonable, experiment with custom implementation of this algorithm. **POINTS: 5**
4. Implement keywords candidates generation. **POINTS: 5**
5. Combine the algorithms and implement the final keyword extraction. **POINTS: 5**
6. Research Maximal Marginal Relevance (https://medium.com/tech-that-works/maximal-marginal-relevance-to-rerank-results-in-unsupervised-keyphrase-extraction-22d95015c7c5) and experiment with different values. Find meaningful and interesting examples of how different values influence the outcome. **POINTS: 5**
7. Create an interface. It should take a text as an input, have sliders for the metrics and show not only the final keywords but also the candidates. **POINTS: 10**

## Examples

https://time.com/6255261/us-shoots-down-unidentified-objects/

In the first two weeks of February, the U.S. Air Force has shot down four flying objects that have intruded on the skies over North America. The deployment of force is unprecedented for the U.S. during peacetime—leveraging some of the U.S. military’s most advanced fighter planes, surveillance tools, and expensive air-to-air missiles.

The first object shot down was an alleged Chinese surveillance balloon that the Biden Administration says was part of a years-long scheme to spy on nations across the Earth. But so far, officials have been much less clear about what the other objects are. One shot down over Alaska Feb. 10 was described as a “car-sized object” that did not appear to have a propulsion source. One downed over Canada the next day was described as “cylindrical,” potentially a balloon, but smaller than the Chinese balloon.

https://en.wikipedia.org/wiki/Poland

Poland,[c] officially the Republic of Poland,[d] is a country in Central Europe. It is divided into 16 administrative provinces called voivodeships, covering an area of 312,696 km2 (120,733 sq mi). Poland has a population of 38 million and is the fifth-most populous member state of the European Union. Warsaw is the nation's capital and largest metropolis. Other major cities include Kraków, Wrocław, Łódź, Poznań, Gdańsk, and Szczecin.

Poland has a temperate transitional climate and its territory traverses the Central European Plain, extending from Baltic Sea in the north to Sudeten and Carpathian Mountains in the south. The longest Polish river is the Vistula, and Poland's highest point is Mount Rysy, situated in the Tatra mountain range of the Carpathians. The country is bordered by Lithuania and Russia to the northeast,[e] Belarus and Ukraine to the east, Slovakia and the Czech Republic to the south, and Germany to the west. It also shares maritime boundaries with Denmark and Sweden.

The history of human activity on Polish soil dates to circa 10,000 BC. Culturally diverse throughout late antiquity, the region became inhabited by tribal Polans who gave Poland its name in the early medieval period. The establishment of statehood in 966 coincided with a pagan ruler of the Polans converting to Christianity under the auspices of the Roman Church. The Kingdom of Poland emerged in 1025 and in 1569 cemented its longstanding association with Lithuania, thus forming the Polish–Lithuanian Commonwealth. It was one of the largest great powers of Europe at the time, with a uniquely liberal political system that adopted Europe's first modern constitution in 1791.

With the passing of a prosperous Polish Golden Age, the country was partitioned by neighbouring states at the end of the 18th century and regained its independence in 1918 as the Second Polish Republic. In September 1939, the German-Soviet invasion of Poland marked the beginning of World War II, which resulted in the Holocaust and millions of Polish casualties. As a member of the Communist Bloc in the global Cold War, the Polish People's Republic was a founding signatory of the Warsaw Pact. Through the emergence and contributions of the Solidarity movement, the communist government was dissolved and Poland re-established itself as a democratic state in 1989.

Poland is a parliamentary republic, with its bicameral legislature comprising the Sejm and the Senate. It is a developed market and a high income economy. Considered a middle power, Poland has the sixth largest economy in the European Union by GDP (nominal) and the fifth largest by GDP (PPP). It provides high standards of living, safety and economic freedom, as well as free university education and a universal health care system. The country has 17 UNESCO World Heritage Sites, 15 of which are cultural. Poland is a founding member state of the United Nations, as well as a member of the World Trade Organization, NATO, and the European Union (including the Schengen Area).