Dividing device

2:

• The dividing device according to claim 1,
• wherein when the forward division likelihood is greater than a predetermined first threshold value, the detection unit detects, as the division point, a position between the first word and a second word immediately preceding the first word.

3:

• The dividing device according to claim 2,
• wherein when the forward division likelihood is less than the first threshold value and the backward division likelihood is greater than a predetermined second threshold value, the detection unit detects, as the division point, a position between the first word and a third word immediately following the first word.

5:

• The dividing device according to claim 4,
• wherein when the elapsed time is greater than a predetermined third threshold value, the detection unit detects, as the division point, a position corresponding to a largest division likelihood among the forward division likelihood of each word following a previous division point and the backward division likelihood of a last acquired word.

6:

• The dividing device according to claim 1,
• wherein the first calculation unit calculates the forward division likelihood and the backward division likelihood using a long short-term memory (LSTM).

7:

• The dividing device according to claim 2,
• wherein the first calculation unit calculates the forward division likelihood and the backward division likelihood using a long short-term memory (LSTM).

8:

• The dividing device according to claim 3,
• wherein the first calculation unit calculates the forward division likelihood and the backward division likelihood using a long short-term memory (LSTM).

9:

• The dividing device according to claim 4,
• wherein the first calculation unit calculates the forward division likelihood and the backward division likelihood using a long short-term memory (LSTM).

10:

• The dividing device according to claim 5,
• wherein the first calculation unit calculates the forward division likelihood and the backward division likelihood using a long short-term memory (LSTM).