Show the predictive score before the sigmoid
max(a) is sigmoid(z), and sigmoid is monotone, so it ranks the collocates
the way the raw score z does - but only in principle. It is read out of
expTable, whose index is (z + MAX_EXP) * (EXP_TABLE_SIZE / MAX_EXP / 2),
integer arithmetic that comes to 83: z is bucketed at 1/83 and everything
from MAX_EXP up lands in one value, 0.99741. Of the 1000 rows for
"König - Mann + Frau" only 264 have a distinct max(a), up to fifteen share
one, and Gemahlin, römisch-deutsche, ungekrönte and Co-Fürsten sit
together on the cap.
z was computed for every candidate at every window position and dropped at
that lookup, which is what the unused max_f and maxmax_f in
getCollocators once tracked. It is carried through now, per position in
collocator.raw and as the maximum over positions in collocator.max_raw,
and shown next to max(a) as max(z).
Nothing else changes: the threshold, the ordering inside a position's list
and the auto focus all still work on the activation. The column renders
three decimals but sorts on the unrounded value.
The info page entry says that the arithmetic covers the paradigmatic and
the predictive syntagmatic analysis, and about the latter that it used to
consider only the first word form and has gained the max(z) column. The
saturation change needs no notice of its own: of ten frequent single words
the highest max(z) is 5.981, so none reaches the cap of 6 and only
expressions get past it.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Change-Id: If26bd78b36e247a4250b63059114470c473fb6c5
diff --git a/Changelog.md b/Changelog.md
index 6f18c1e..6b1471d 100644
--- a/Changelog.md
+++ b/Changelog.md
@@ -22,6 +22,14 @@
- the tails of that score saturate rather than being dropped. Activations
outside ±MAX_EXP used to skip the collocate entirely, which lost exactly the
strongest ones and left them out of the position and target sums as well
+- the predictive collocator table has a max(z) column, the score before the
+ sigmoid, i.e. the dot product of the query vector with the output weights of
+ the collocate. max(a) is its image under expTable, which buckets it at 1/83
+ and caps it at MAX_EXP, so it cannot separate the strongest collocates from
+ each other: of 1000 rows for "König - Mann + Frau" only 264 have a distinct
+ max(a), and four sit on the cap. The dot product was computed for every
+ candidate and thrown away at that lookup; it is kept now, and sorting the
+ column uses the unrounded value
- the count based collocators stay restricted to a single word form, since they
are looked up per node in the co-occurrence database. For a query of several
operands the interface says so in place of that table, rather than showing
diff --git a/lib/IDS/DeReKoVecs/derekovecs-server.c b/lib/IDS/DeReKoVecs/derekovecs-server.c
index 5a08486..e72cf4c 100644
--- a/lib/IDS/DeReKoVecs/derekovecs-server.c
+++ b/lib/IDS/DeReKoVecs/derekovecs-server.c
@@ -53,6 +53,12 @@
float probability;
float activation_sum;
float max_activation;
+ /* The score before the sigmoid, q . syn1neg[collocate, position]. activation
+ is expTable[z], quantized in steps of 1/83 and capped at MAX_EXP; z is
+ not. raw is the value at one position, max_raw the maximum over
+ positions. */
+ float raw;
+ float max_raw;
float heat[16];
} collocator;
@@ -410,21 +416,16 @@
free(nbs);
}
-/* Predicts the collocates of a query. The score of a collocate is
- sigmoid(q . syn1neg[target, position]), which is linear in q before the
- sigmoid, so the query does not have to be a single word: q can be the same
- signed combination of input vectors that the paradigmatic side searches
- around, and "König - Mann + Frau" asks for the contexts that König and Frau
- predict but Mann does not.
+/* Predicts the collocates of a query. The score is
+ sigmoid(q . syn1neg[target, position]), linear in q before the sigmoid, so q
+ may be the signed combination of input vectors that the paradigmatic side
+ searches around rather than the vector of a single word.
- The combination is the mean over the positive terms rather than their sum,
- because the sigmoid is only informative over a narrow range of q . syn1neg
- and the strongest collocates of a single word already sit at the top of it.
- A plain sum would push them past MAX_EXP, where they all saturate to the
- same value. Dividing by the number of terms keeps every query in the range
- the threshold and the auto focus below are calibrated for, and leaves the
- single word case exactly as it was: one term, divisor one. A balanced
- analogy has one term as well, +1 -1 +1, and lands in the same range. */
+ q is the mean over the terms, not their sum: the sigmoid is informative over
+ a narrow range only, and a sum would push the strongest collocates past
+ MAX_EXP into saturation. The mean keeps every query in the range MIN_RESP
+ and the auto focus are calibrated for. One word, and a balanced analogy
+ (+1 -1 +1), are one term and keep the previous scale. */
void *getCollocators(void *args) {
knnpars *pars = args;
int N = pars->N;
@@ -433,7 +434,7 @@
knn *nbs = NULL;
long window_layer_size = size * window * 2;
long a, b, c, d, op, window_offset, target, max_target = 0, maxmax_target;
- float f, max_f, maxmax_f, scale;
+ float f, raw, max_f, maxmax_f, scale;
float qvec[max_size];
int terms = 0;
float *target_sums = NULL, worstbest, wpos_sum;
@@ -466,6 +467,7 @@
best[b].wordi = -1;
best[b].probability = 1;
best[b].activation = worstbest;
+ best[b].raw = 0;
}
d = wl->wordi[0];
@@ -492,9 +494,9 @@
f = 0;
for (c = 0; c < size; c++)
f += qvec[c] * syn1neg_window[target * window_layer_size + window_offset + c];
- /* Saturate rather than drop. Skipping the tails used to lose exactly
- the collocates the sigmoid can no longer tell apart, i.e. the
- strongest ones, and left them out of wpos_sum and target_sums too. */
+ raw = f;
+ /* Saturate rather than drop: skipping the tails removed the strongest
+ collocates from the list and from wpos_sum and target_sums. */
if (f < -MAX_EXP)
f = -MAX_EXP;
else if (f > MAX_EXP)
@@ -508,6 +510,7 @@
if (f > best[b].activation) {
memmove(best + b + 1, best + b, (N - b - 1) * sizeof(collocator));
best[b].activation = f;
+ best[b].raw = raw;
best[b].wordi = target;
best[b].position = window - a;
break;
@@ -682,8 +685,7 @@
free standing sign applies to the word that follows it.
Tokens that are not in the vocabulary are left out of the list and
- collected in wl->oov, so that the caller can report them instead of
- quietly answering a different question. */
+ collected in wl->oov, so that the caller can report them. */
wordlist *getTargetWords(char *st1, int search_backw) {
wordlist *wl = calloc(1, sizeof(wordlist));
char *copy = strdup(st1), *tok, *saveptr = NULL;
@@ -703,8 +705,8 @@
if (*tok == 0) continue; /* " - Mann": the sign belongs to the next token */
}
if (wl->length >= MAX_TARGET_WORDS) break;
- /* Counted before the lookup: what the query is asking for does not change
- because one of its operands happens to be unknown. */
+ /* Counted before the lookup: an unknown operand does not change what was
+ asked for. */
if (sign == '-') wl->subtractions++;
b = lookupWord(tok, search_backw);
if (b < 0) {
@@ -1158,6 +1160,8 @@
for (b = 0; b < MAX_NEIGHBOURS; b++) {
best[b].wordi = -1L;
best[b].activation = 0;
+ best[b].raw = 0;
+ best[b].max_raw = 0;
best[b].probability = 0;
best[b].position = 0;
best[b].activation_sum = 0;
@@ -1183,6 +1187,7 @@
best[b].position = -1; // syn_nbs[0]->pos[b];
best[b].activation_sum = target_sums[syn_nbs[0]->best[b].wordi];
best[b].max_activation = 0.0;
+ best[b].max_raw = 0.0;
best[b].average = 0.0;
best[b].probability = 0.0;
best[b].cprobability = syn_nbs[0]->best[b].cprobability;
@@ -1198,6 +1203,7 @@
break;
if (i >= found_index) {
best[found_index].max_activation = 0.0;
+ best[found_index].max_raw = 0.0;
best[found_index].average = 0.0;
best[found_index].probability = 0.0;
memset(best[found_index].heat, 0, sizeof(float) * 16);
@@ -1244,6 +1250,8 @@
word_activation_sum += syn_nbs[a]->best[b].activation;
if (syn_nbs[a]->best[b].activation > best[i].max_activation)
best[i].max_activation = syn_nbs[a]->best[b].activation;
+ if (syn_nbs[a]->best[b].raw > best[i].max_raw)
+ best[i].max_raw = syn_nbs[a]->best[b].raw;
if (syn_nbs[a]->best[b].activation > best[i].heat[wpos])
best[i].heat[wpos] = syn_nbs[a]->best[b].activation;
}
@@ -1352,6 +1360,7 @@
hv_store(hash, "average", strlen("average"), newSVnv(best[a].average), 0);
hv_store(hash, "prob", strlen("prob"), newSVnv(best[a].probability), 0);
hv_store(hash, "cprob", strlen("cprob"), newSVnv(best[a].cprobability_sum), 0);
+ hv_store(hash, "dot", strlen("dot"), newSVnv(best[a].max_raw), 0);
hv_store(hash, "max", strlen("max"), newSVnv(best[a].max_activation), 0); // newSVnv(target_sums[best[a].wordi]), 0);
hv_store(hash, "overall", strlen("overall"), newSVnv(best[a].activation_sum / total_activation), 0); // newSVnv(target_sums[best[a].wordi]), 0);
hv_store(hash, "pos", strlen("pos"), newSVnv(best[a].position), 0);
diff --git a/templates/de/about.html.ep b/templates/de/about.html.ep
index e58acd2..02de3f6 100644
--- a/templates/de/about.html.ep
+++ b/templates/de/about.html.ep
@@ -72,7 +72,9 @@
<p>
<strong>06.09.2026</strong>
- Das Suchfeld versteht jetzt Vektorarithmetik, siehe <em>Suchanfragen</em> oben.
+ Das Suchfeld versteht jetzt Vektorarithmetik (siehe <em>Suchanfragen</em> oben) für
+ paradigmatische und prädiktiv-syntagmatische Analysen; letztere berücksichtigten
+ bisher nur die erste Wortform und wurden außerdem um die Spalte max(z) erweitert.
</p>
<p>
<strong>04.09.2026</strong>
diff --git a/templates/en/about.html.ep b/templates/en/about.html.ep
index 039c427..8ebdbdc 100644
--- a/templates/en/about.html.ep
+++ b/templates/en/about.html.ep
@@ -69,7 +69,9 @@
<p>
<strong>2026-09-06</strong>
- The search field understands vector arithmetic, see <em>Queries</em> above.
+ The search field understands vector arithmetic (see <em>Queries</em> above) for
+ paradigmatic and predictive syntagmatic analyses; the latter used to consider only
+ the first word form, and have also gained a max(z) column.
</p>
<p>
<strong>2026-09-04</strong>
diff --git a/templates/index.html.ep b/templates/index.html.ep
index ce38536..ba2dde5 100644
--- a/templates/index.html.ep
+++ b/templates/index.html.ep
@@ -251,6 +251,8 @@
{ "data": "rank", type: "allnumeric" },
{ "data": "pos", width: "7%", sClass: "dt-center mono compact", render: function ( data, type, row ) {return bitvec2window(data, row.heat, row.word) }},
{ "data": "max", render: function ( data, type, row ) {return data.toFixed(3) }},
+ %# Display rounding only; the sort needs the unrounded value.
+ { "data": "dot", render: function ( data, type, row ) {return type === 'display' ? data.toFixed(3) : data } },
{ "data": "average", render: function ( data, type, row ) {return data.toFixed(3) }},
{ "data": "prob", type: "scientific", render: function ( data, type, row ) {return data.toExponential(3) } },
{ "data": "cprob", type: "scientific", render: function ( data, type, row ) {return data.toExponential(3) } },
@@ -259,21 +261,21 @@
{ "data": "rank", type: "allnumeric" }
],
"columnDefs": [
- { className: "dt-right", "targets": [0,2,3,4,5,6] },
+ { className: "dt-right", "targets": [0,2,3,4,5,6,7] },
{ className: "dt-center", "targets": [ 1] },
{ "searchable": false,
"orderable": false,
- "targets": [0, 8]
+ "targets": [0, 9]
},
{ "type": "scientific", targets: [2,3,4,5,6] },
- { "orderSequence": [ "desc" ], "targets": [ 2, 3, 4, 5, 6 ] },
- { "orderSequence": [ "asc", "desc" ], "targets": [ 1, 7 ] },
- { "targets": [8], "visible": false }
+ { "orderSequence": [ "desc" ], "targets": [ 2, 3, 4, 5, 6, 7 ] },
+ { "orderSequence": [ "asc", "desc" ], "targets": [ 1, 8 ] },
+ { "targets": [9], "visible": false }
],
"oLanguage": {
"sSearch": "Filter: "
},
- "order": [[ 4, 'desc' ]],
+ "order": [[ 5, 'desc' ]],
} );
$.ajaxSetup({
type: 'POST',
@@ -934,6 +936,7 @@
<th>#</th>
<th align="center" title="Activation of the respective collocator in the columns around the target normalized by its maximum (red). Columns selected by the auto-focus funtion (which window of all possible column-combinations maximizes ⊥(a/c)?) are marked with +. Click on the column postions to lauch a KorAP query with target word and collocator in the respective position.">w'</th>
<th align="right" title="Maximum activation of the collocator anywhere in the output layer.">max(a)</th>
+ <th align="right" title="Maximum activation of the collocator before the sigmoid: max(a) = σ(max(z)). Unquantized and uncapped, and therefore able to order collocators of equal max(a).">max(z)</th>
<th title="Average raw activation of the collocator in the columns selected by auto-focus." align="right">⟨a⟩</th>
<th title="Sum of activations over the selected colunns normalized by the total activation sum of the selected columns." align="right">Σa/Σw'</th>
<th title="Co-norm of the column-normalized activations over the colunns selected by the auto-focus." align="right">⊥(a/c)</th>