added features.tsv
Change-Id: Ie3631a7022c7d6e2bdc53ec954ad7baa07a7cb2a
diff --git a/data/features.tsv b/data/features.tsv
new file mode 100644
index 0000000..94877c7
--- /dev/null
+++ b/data/features.tsv
@@ -0,0 +1,39 @@
+innames oldnames newnames explanation getrid
+rankDiff SY_RD SY_R_D rank difference: SY_W_R1-SY_C1_R 0
+af SY_C_LDAF SY_C1_LDAF logdice with autofocus 0
+dice SY_C_DICE SY_C1_DICE dice 1
+ld SY_C_LD SY_C1_LD logdice 0
+lfmd SY_C_MI3 SY_C1_MI3 MI^3 0
+llfmd SY_C_LEFTN_MI SY_C1_MI_L MI with left neighbour 1
+llr SY_C_LL SY_C1_LL loglikelihood 0
+lnpmi SY_C_LEFTN_COUNT SY_C1_C_L raw count of left neighbour 1
+md SY_C_MI2 SY_C1_MI2 MI^2 0
+npmi SY_C_NPMI SY_C1_NMI normalized MI 1
+pmi SY_C_MI SY_C1_MI (pointwise) mutual information, MI 0
+rlfmd SY_C_RIGHTN_MI SY_C1_MI_R MI with right neighbour 1
+rnpmi SY_C_RIGHTN_COUNT SY_C1_C_R raw count of right neighbour 1
+average SY_W_AVG SY_W_AVG average of output activations with autofocus 0
+cprob SY_W_CON SY_W_CON conorm of column normalized output activations with autofocus 0
+max SY_W_MAX SY_W_MAX max of output activations 0
+overall SY_W_NSUM1 SY_W_NSUM_AF sum of output activations normalized by total sum over all selected columns with autofocus 0
+prob SY_W_NSUM2 SY_W_NSUM sum of output activations normalized by total sum over all columns 0
+w2v.rank SY_W_RK1 SY_W_R1 rank by SY_W_CON 0
+w2v.rank1 SY_W_RK2 SY_W_R2 rank by SY_W_NSUM2 0
+classic.rank SY_C_RK SY_C1_R rank by SY_C_LD 0
+NSTOPW NSTOPW O_NSTOPW number of non stop words in idiom candidate 0
+CO_NUMBER CO_NUMBER O_C2_N number of occurrences in pop lyrics 1
+CO_SGT CO_SGT O_C2_SGT Simple Good-Turing estimate of probability in pop lyrics 0
+CO_EXPECTED CO_EXPECTED SY_C2_EXP expected number of occurrences 1
+CO_PMI CO_PMI SY_C2_MI (pointwise) mutual information, MI 0
+CO_MI3 CO_MI3 SY_C2_MI3 MI^3 0
+CO_LOCALMI CO_LOCALMI SY_C2_LMI local mutual information 0
+CO_Z CO_Z SY_C2_Z zscore 0
+CO_T CO_T SY_C2_T p-value of ttest 1
+CO_LL CO_LL SY_C2_LL loglikelihood 0
+CO_LOGDICE CO_LOGDICE SY_C2_LD logdice 0
+CO_K CO_K SY_C2_K k-value (Kita et al.1994) 1
+CO_G CO_G SY_C2_G lexical gravity (Gries/Mukherjee 2010) 1
+CO_WIN5_VEC CO_WIN5_VEC CO_VEC avg. cosine similarity between words in candidate and words in +/-5 context 0
+CO_WIN5_VEC_AUTOSEM CO_WIN5_VEC_AUTOSEM CO_VEC_LEX like CO_WIN5_VEC but only on lexical words 0
+CO_DEREKO CO_DEREKO O_DEREKO number of words available in DeReKo 0
+CO_GRAM CO_GRAM O_GRAM number of words in idiom candidate 0
\ No newline at end of file