5. 英語学習者支援のための共通タスク
(小町, 2013)
• Helping Our Own (HOO) 2011
European Workshop on Natural Language Generation
論文の文法的誤り訂正
ACL Anthology Reference Corpus
• Helping Our Own (HOO) 2012
Building Educational Applications Workshop
前置詞と限定詞の文法的誤り訂正
Cambridge Learner Corpus
5
6. 英語学習者支援のための共通タスク
(小町, 2013)
• Native Language Identification Shared Task
Building Educational Applications Workshop
英作文から英語学習者の母語推定
TOEFL11 データセット
• Grammatical Error Correction
CoNLL 2013
限定詞、前置詞、数、動詞の形、一致、スペル、句読点
の文法的誤り訂正
NUS Corpus of Learner English
6
15. 研究の動機
• 大規模なコーパスや統計手法の出現によって、
統語解析や意味解析の問題がなおざりにされて
きた。 (池原, 2001)
• Chapelle and Chung (2010) stated that “[t]he
ideal hybrid may be one in which sentence-level
feedback is provided by an automated
mechanism, leaving the teacher free to comment.
Nevertheless, research in natural language
processing is focusing on these higher-order
concerns” (p. 41).
15
21. 応用例
• Powerset (→Bing)
• 機械翻訳 (Owczarzak et al., 2007)
• コンピュータ支援語学学習 (Butt & King, 2007)
• 質問応答システム (Judge et al., 2006)
• 日本語LFG (Masuichi et al., 2006)
21
22. XLEの問題点
• “The development of large coverage, rich
unification- (constraint-) based grammar
resources is very time consuming” (Cahill et
al., 2002).
• 語順、左方転移構文などの例文において容
認性に問題がみられることがある。
→改善手法はいくつか提示されている (Kuhn,
Rohrer & Zarries, 2010)。
22
24. 今回対象とした誤り
• 三人称単数形のsの脱落
*he kick it.
• 日本語の影響から生じる誤り
*today is tired. (→I am tired today.)
• 時制のミスマッチ
*we kick it yesterday.
• 冠詞の誤り
*girl is tired.
*a boys are tired.
24
25. 三人称単数形の-sの脱落 (1/2)
• 日本人英語学習者が最も誤りを犯すのが動
詞に関係する誤りである (Abe, 2003; Izumi et
al., 2003)。
• Quirk et al. (1985) stated that “[t]he most
important type of concord in English is
concord of third person number between
subject and verb”.
25
30. 結論
• 形態素レベルの文法的誤りはルールベースで検出出来る。
• 冠詞などは確率的モデルで検討した方が精度が高い。
• 最適性理論 (OT)などを援用し、error gravityの順位付け。
• [A]utomated feedback would be more appropriate for
students at lower levels of language proficiency who were
still learning basic writing skills (Chen and Cheng, 2008)
30
38. Kitamura (2011)
• エラータイプが3種類しか扱われていない(いわ
ゆるProblem-oriented tagging)。
• subject-verb agreement
→ He have been living there since June.
• verb form
→I can’t skiing well, but…
• sentence fragment
→Because people’s interesting thing is not the
same.
38
44. エッセイの例 (University life)
My university life is very interesting. Because I <v_lxc crr="do">act</v_lxc> many things <prp
crr="">since</prp> now. First I <uk crr="am a member of">join</uk> <at crr="a"></at> cercle. I
feel <ord crr="very good about this"><prp crr="about"></prp> this very good</ord>. <uk crr="I
kill time by">My killing time is</uk> writing <n_num crr="novels">novel</n_num> or drawing
<n_num crr="pictures">picture</n_num>. <uk>This has many people like me</uk>.So I
concentrate <prp crr="on"></prp> this. Second is summer vacation. I <v_tns crr="did"><v_lxc
crr="do">act</v_lxc></v_tns> many <n_num crr="things">thing</n_num> in <pn
crr="my"></pn> summer vacation. My best memory is <at crr="the"></at> seminar on the sea. I
went to Ho-chi-min and Singapore. I got many friends <prp crr="from">around</prp> Hyogo
university. And I <av crr="sometimes">sometime</av> meet <pn crr="them">friends</pn>. Last I
have many friends <prp crr="from">in</prp> high school, junior high school and <aj
crr="other">etc</aj> <n_num crr="groups">group</n_num>. We always talk about each <n_o
crr="other's">other</n_o> <n_num crr="lives">life</n_num> <prp crr="by">in</prp> e-mail or
internet. And We play <prp crr="">in</prp> inside or outside home.
We play funny <n_num crr="games">game</n_num>. For example, <n_lxc crr="one of us">a
friend</n_lxc> <v_agr crr="calls">call</v_agr> <prp crr="">in</prp> Macdonald <con
crr="and"></con> <v_lxc crr="says"></v_lxc> "Please give me <at crr="a"></at> hundred <n_num
crr="hamburgers">hunbergar</n_num>.“ And others look <prp crr="at"></prp> him and laugh. I
have many friends, so my university life is very interesting.
44