From 45d6b4d78865113886fe4f75f65f9fb052f406f5 Mon Sep 17 00:00:00 2001 From: Natalia Isupova <32172496+NatalieIsupova@users.noreply.github.com> Date: Wed, 31 Oct 2018 13:59:51 +0300 Subject: [PATCH 01/27] Quiz 1 completed --- .../quizzes/Quiz 1 Natalia Isupova.md | 33 +++++++++++++ .../quizzes/Quiz 1 Natalia Isupova.md.html | 47 +++++++++++++++++++ 2 files changed, 80 insertions(+) create mode 100644 2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md create mode 100644 2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html diff --git a/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md b/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md new file mode 100644 index 00000000..351aae53 --- /dev/null +++ b/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md @@ -0,0 +1,33 @@ +# 1. Which problems does maxmatch suffer from? (Choose all that apply.) +- a) requires comprehensive dictionary +- d) constructs non-grammatical sentences + +# 2. Write a perl/sed substitution with regular expressions that adds whitespace for segmentation around "/" in "either/or" expressions but not around fractions "1/2". +```sh +sed 's/\([a-zA-Z]\+\)\/\([a-zA-Z]\+\)/\1 \/ \2/g' +``` + +# 3. The text mentions several times that machine learning techniques produce better segmentation than rule-based systems; what are some downsides of machine learning techniques compared to rule-based? +- the need of huge manually marked corpora for training +- machine learning techniques take more time to create/choose and adjust the algorithm +- machine learning techniques can sometimes have unexpected results + +# 4. Write a sentence (in English or in Russian) which maxmatch segments incorrectly. +thetabledownthere -> theta bled own there + +# 5. What are problems for sentence segmentation? Provide one example in English or Russian for each that applies. + +- a) ambiguous abbrevations with punctuation: +> Более 2 тыс. бутылок воды было роздано пассажирам столичной подземки и МЦК за выходные из-за жары. + +(The full stop after abbreviation "тыс." can be considered as the end of the sentence.) +- b) sentences containing symbols '!' and '?' +> "Что? Где? Когда?" — популярная телевизионная интеллектуальная игра, в которой команда знатоков в течение минуты ищет ответы на вопросы телезрителей. + +(The question marks in the title can be considered as the end of the sentence.) +- c) sentences lacking separating punctuation +> завидую крутым девочкам в тви у которых не только своя компания но и большая аудитория которая сразу пишет комменты вам через 0.5 секунд когда вы пишете твит, я чувствую себя тем самым одиноким чуваком в школьной столовке который всегда ест один + +(Many examples from social media, e.g. Twitter or VK) +- d) sentences not separated by whitespace: +> This is a test.This is a test. diff --git a/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html b/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html new file mode 100644 index 00000000..8879bb97 --- /dev/null +++ b/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html @@ -0,0 +1,47 @@ +
sed 's/\([a-zA-Z]\+\)\/\([a-zA-Z]\+\)/\1 \/ \2/g'
+
+thetabledownthere -> theta bled own there
+++Более 2 тыс. бутылок воды было роздано пассажирам столичной подземки и МЦК за выходные из-за жары.
+
(The full stop after abbreviation “тыс.” can be considered as the end of the sentence.)
+++“Что? Где? Когда?” — популярная телевизионная интеллектуальная игра, в которой команда знатоков в течение минуты ищет ответы на вопросы телезрителей.
+
(The question marks in the title can be considered as the end of the sentence.)
+++завидую крутым девочкам в тви у которых не только своя компания но и большая аудитория которая сразу пишет комменты вам через 0.5 секунд когда вы пишете твит, я чувствую себя тем самым одиноким чуваком в школьной столовке который всегда ест один
+
(Many examples from social media, e.g. Twitter or VK)
+++ + \ No newline at end of file From 52ba188c1747bdb6e62806ebd58c84520b72bebc Mon Sep 17 00:00:00 2001 From: Natalia Isupova <32172496+NatalieIsupova@users.noreply.github.com> Date: Wed, 31 Oct 2018 14:05:32 +0300 Subject: [PATCH 02/27] Quiz 1 completed, fixed the title --- .../quizzes/{Quiz 1 Natalia Isupova.md => Quiz 1 - Response.md} | 0 1 file changed, 0 insertions(+), 0 deletions(-) rename 2018-komp-ling/quizzes/{Quiz 1 Natalia Isupova.md => Quiz 1 - Response.md} (100%) diff --git a/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md b/2018-komp-ling/quizzes/Quiz 1 - Response.md similarity index 100% rename from 2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md rename to 2018-komp-ling/quizzes/Quiz 1 - Response.md From 2aa52d6987f0f6eb86b336297004b0990de203aa Mon Sep 17 00:00:00 2001 From: Natalia Isupova <32172496+NatalieIsupova@users.noreply.github.com> Date: Wed, 31 Oct 2018 14:06:09 +0300 Subject: [PATCH 03/27] Quiz 1 completed, fixed the title --- .../{Quiz 1 Natalia Isupova.md.html => Quiz 1 - Response.html} | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) rename 2018-komp-ling/quizzes/{Quiz 1 Natalia Isupova.md.html => Quiz 1 - Response.html} (99%) diff --git a/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html b/2018-komp-ling/quizzes/Quiz 1 - Response.html similarity index 99% rename from 2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html rename to 2018-komp-ling/quizzes/Quiz 1 - Response.html index 8879bb97..3434ba62 100644 --- a/2018-komp-ling/quizzes/Quiz 1 Natalia Isupova.md.html +++ b/2018-komp-ling/quizzes/Quiz 1 - Response.html @@ -44,4 +44,4 @@This is a test.This is a test.
+
L=kUF!k@vFw
zH)n?9D?=ZDAfVoGrjU4-WVGeX __whJTSnQ=1(Gb)4__#03;Zq`F0?H~0YhfRlWUQaKt nBgaJ0uM`URK1MB8I=LjqG3TosoptL+
z658Do>BY^H?~4)4W$9Os>Uap#x6slknh$Zy2O&8Sia&k?@0_8z5iM}ETPU9Wbrotn
zH0ru0ZOMJGYVEZ}HOU+?_?tt1nUBJdxfMAAIZt*uA$}%TVQaku?XFPdBqgHoJ6OMY
zJoPjU4!;bIol>@>DN!Gd=2q ^UnuLtHet=(5N=*
zO^Lbv%Tpo1UFFN-_YT?8nbk<j*uc
zGkYJ|y>f-?w&n9^Kyc~-_eb>6-ZiVVxW)SfJsa7rUJZYL&gF$FJ$;;?f9%kuEAEMi
zbLA2)x+<>=W1G6q-8}>`HezY{YZCTTJUc=@SL2f
k}cPuF)3_sa?i(1`E?cU1+0&k-|sB#t~OIDTvObvpS>B*r8K}~#$~wq
z>7{Tgpd`b4L<6Cxpea*L3U+6qiQ`;xCEls$vb|9#3eRv%y#JTv)xs7F9fxJ_pvDQ$
zesP#K*)v}|sj>I^fN=(srYWaK69;{3O3@ctqzJdka4O#bWduf5E=6vzlAv8X^Sfpp
z@b|qlTPAfCu4cB#OW(W8y<{0vCmJ927*|aC7_MyJwnb(=$cXMz0VY+gjmA>E1Fe;N
zReCT&xlCQ@c!1|?INt+@+}(JTsjUny44aA=#ictcNMEVty^t?@x8j)($`0-#&!VS?
zB}Lx97Nl_hHQ43Kh`;OQ-|4RTc&Z@FBE)tL9!3e`f+Em~e0;!#Z4-94&D3rZ8FRz^w
zk1_GU01q5#%j;%r&&$ul#|ufq-0Y3v)(8}<2?E%2r4CM(U=Ffcno1qi5?10