2018-08-15 22:37:23 +00:00
|
|
|
|
using System;
|
|
|
|
|
|
using System.Collections.Generic;
|
|
|
|
|
|
using System.Text;
|
|
|
|
|
|
|
|
|
|
|
|
namespace BotSharp.NLP.Tokenize
|
|
|
|
|
|
{
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
|
/// A tokenizer is a component used for dividing text intotokens.
|
|
|
|
|
|
/// A tokenizer is language specific and takes into account the peculiarities of the language, e.g. don’t in English is tokenized as two tokens.
|
|
|
|
|
|
/// </summary>
|
|
|
|
|
|
public interface ITokenizer
|
|
|
|
|
|
{
|
|
|
|
|
|
/// <summary>
|
|
|
|
|
|
/// Tokenize
|
|
|
|
|
|
/// </summary>
|
2018-08-16 22:27:50 +00:00
|
|
|
|
/// <param name="sentence">input sentence</param>
|
2018-08-15 22:37:23 +00:00
|
|
|
|
/// <param name="options">Options such as: regex expression</param>
|
|
|
|
|
|
/// <returns></returns>
|
2018-08-17 20:49:29 +00:00
|
|
|
|
List<Token> Tokenize(string sentence, TokenizationOptions options);
|
2018-08-15 22:37:23 +00:00
|
|
|
|
}
|
|
|
|
|
|
}
|