14
my
opinion
.
<EOS>
<pad>

<EOS>
<pad>

in

my
opinion
.

,
in

missing
,

we
are

we
are
missing

is
what

this
is
what

this

be
just
-

application
should

its

perfect
,
but

<EOS>
<pad>

<EOS>
<pad>

in
my
opinion
.

my
opinion
.

,
in

missing
,

we
are

we
are
missing

is
what

this

be
just
-

application
should

its

perfect
,
but

be

will
never

The
Law

this
is
what

-

be
just

application
should

its

perfect
,
but

never
be

will

The
Law

Input-Input Layer5

-

be
just

application
should

its

perfect
,
but

be

will
never

will
never
be

The
Law

The
Law

Input-Input Layer5

Figure 4: Two attention heads, also in layer 5 of 6, apparently involved in anaphora resolution. Top:
Full attentions for head 5. Bottom: Isolated attentions from just the word ‘its’ for attention heads 5
and 6. Note that the attentions are very sharp for this word.

