160 likes | 344 Views
Automatic classification for implicit discourse relations. Lin Ziheng. PDTB and discourse relations. Explicit relations Arg1: The bill intends to restrict the RTC to Treasury borrowings only,
E N D
Automatic classification for implicit discourse relations Lin Ziheng
PDTB and discourse relations • Explicit relations • Arg1: The bill intends to restrict the RTC to Treasury borrowings only, Arg2:unless the agency receives specific congressional authorization. (Alternative) (wsj_2200) • Implicit relations • Arg1: The loss of more customers is the latest in a string of problems. • Arg2:[for instance] Church's Fried Chicken Inc. and Popeye's Famous Fried Chicken Inc., which have merged, are still troubled by overlapping restaurant locations. (Instantiation) (wsj_2225)
PDTB and discourse relations (2) • PDTB hierarchy of relation classes, types and subtypes
PDTB and discourse relations (3) • Level-2 relation types, on implicit dataset from the training sections (sec. 2 - 21) • Remove Condition, Pragmatic Condition, Pragmatic Contrast, Pragmatic Concession and Exception • 11 relation types remained • Dominating types: • Cause • Conjunction • Restatement
Contextual features r1 r2 • Arg1:Tokyu Department Store advanced 260 to 2410. Arg2:[and]Tokyu Corp. was up 150 at 2890. (List) (wsj_0374) • Arg1:Tokyu Department Store advanced 260 to 2410. Tokyu Corp. was up 150 at 2890. Arg2:[and]Tokyu Construction gained 170 to 1610. (List) (wsj_0374) Shared argument r1.Arg1 r1.Arg2 r2.Arg1 r2.Arg2 r2 Fully embedded argument r1 r1.Arg1 r1.Arg2 r2.Arg2 r2.Arg1
Contextual features (2) • For each relation curr, look at the surrounding two relations prev and next, giving to a total of six features First figure in previous slide where curr = r2 Second figure in previous slide where curr = r2
Syntactic Features • Arg1: "The HUD budget has dropped by more than 70% since 1980," argues Mr. Colton. Arg2:[so] "We've taken more than our fair share. (Cause) (wsj_2227)
Syntactic Features (2) • Collect all production rules: • Ignore function tags, such as -TPC, -SBJ, -EXT • From Arg1: S NP VP, NP DT NNP NN, VP VBZ VP, VP VBN PP PP, PP IN NP, NP QP NN, QP JJ IN CD, NP CD, DT The, NNP HUD, NN budget, VBZ has, VBN dropped, IN by, JJ more, IN than, CD 70, NN %, IN since, CD 1980 • From Arg2: S `` NP VP ., NP PRP, VP VBP VP, VP VBN NP, NP NP PP, NP JJR, PP IN NP, NP PRP$ JJ NN, `` ``, PRP We, VBP ‘ve, VBN taken, JJR more, IN than, PRP$ our, JJ fair, NN share, . .
Dependency features (2) • Collect all words with dependency types from their dependents • From Arg1: budget detnn, dropped nsubj aux prep prep, by pobj, than advmod, 70 quantmod, % num, since pobj, argues ccompnsubj, Colton nn • From Arg2: taken nsubj aux dobj, more prep, than pobj, share possamod
Lexical features • Collect all word pairs from Arg1 and Arg2, i.e., all (wi, wj) where wi is a word from Arg1 and wj is a word from Arg2
Experiments • Classifier: OpenNLPMaxEnt • Training data: sections 2 – 21 • Test data: section 23 • Use Mutual Information(MI) to rank features for production rules, dependency rules and word pairs separately • Majority baseline: 26.1%, where all instances are classified into Cause
Experiments (2) • Use contextual features and one other feature class • context + production rules • context + dependency rules • context + word pairs
Experiments (3) • With large numbers of features • context + all production rules: 36.68% • context + all dependency rules: 27.94% • context + 10,000 word pairs: 35.25%
Experiments (4) • Combine all feature classes, got an accuracy of 40.21%. • The following shows that all feature classes contribute to the performance