Table 7 Special characters included in our tokenizer.
From: A CRF-based system for recognizing chemical entity mentions (CEMs) in biomedical literature
( ) [ ] { } > < ≥ ≤ , . / \ ' ™ @ · ©® " : = ≠ ≡ ≈ + - ? _ | ↑ ↓ ← → ↗ ↘ ↙ ↖ ↔ ⇌ ± ~ ∗ % ‰ ∘ # & ; ! £ € ¥ $ × ÷ ‡ † ⋯ ∞ ∨ ∧ √ ⊥ ⊤ ∈ ∃ ⊂ ⊃ ∇ ■ ∂ ∫ |