update excerpt

diff --git a/excerpt.txt b/excerpt.txt
new file mode 100644 (file)
index 0000000..0a353b4
--- /dev/null
+++ b/excerpt.txt
@@ -0,0 +1,91 @@
+Ch1:  complete
+Overview
+
+Ch2:  complete
+Regex, (non-)deterministic automata
+
+Ch3:  Intro, 3.1, 3.2, 3.8, 3.9, 3.10, 3.11, Summary, Notes
+Morfology, stem, affix, form words from stems, porterstemmer, spelling, minimal
+       edit/levehnstein
+
+Ch4:  Intro, 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7.intro, 4.8, 4.9, 4.10, 4.11, Summary, Notes
+NGrams, smoothing, perplexity, entropy
+
+Ch5:  complete
+POS-tagging, rulebased, hmm, viterbi, table, noisy channel, noisy channel
+       spelling
+
+Ch6:  Intro, 6.1, 6.2, 6.3, 6.4, 6.5,  6.6, 6.7, 6.8, Summary, Notes
+hmm, forward, viterbi, forwardbackward, mem (hypothesis, iterate), 
+
+Ch7:  Intro, 7.1, 7.3, 7.4, Summary
+Phonetics, features, voicing, spectogram, IPA
+
+Ch8:  complete
+Synthesis, (norm-phonetic-prosody-repr-make), diphone, unit selection
+
+Ch9:  complete
+asr, cepstralfeature-model,likelihood-viterbi/codebook(distance), worderrorrate 
+
+Ch12: Intro, 12.1, 12.2, 12.3, 12.4, 12.5, 12.6, 12.7.intro, 12.7.1, 12.8, Summary, Notes
+Grammar, CFG, sample grammars, head(most important), chomsky nf, spoken(disfl)
+
+Ch13: complete
+Syntax parsing, top down(cky), bottomup(early), partial(IOB)
+
+Ch14: Intro, 14.2, 14.3, 14.4, 14.5, 14.6, 14.7, 14.8, 14.9,  14.10, Summary, Notes
+Statistical parsing, PCFG, PCKY, rule calculation, problems, improvements,
+       lexicalized PCFG, collins, evaluation(rec/prec), human parsing(gardenpath)
+
+Ch15: Intro, 15.1, 15.2, 15.3, 15.5.intro, 15.5.1, 15.6.intro, 15.6.1, Summary, Notes
+Features, unification, structures, grammar addition, typing
+
+Ch16: Intro, 16.1, 16.3, Summary
+Complexity, chomsky hierarchy, nl not cfg
+
+Ch17: complete
+Meaning, ambiguity, fologin, canonical form, inference, expressiveness.
+       first order logic, lambda notation. event/state notation(time,aspect
+       description subsumption
+
+Ch18: Intro, 18.1, 18.2, 18.6, Summary
+Computational semantics, syntax driven, idioms and compositionality
+
+Ch19: complete
+Lexical semantics, word sense, relations(synonym...), wordnet, roles, propbank,
+       framenet, component analysis, metaphors
+
+Ch20: complete
+Computational lexical semantics, sense disambiguation, supervised method,
+evaluation, dictionary method(lesk), bootstrapping, similarity(thesaurus,
+distributional), vector distances, hyponymy, role labeling
+word2vec
+
+Ch21: Intro, 21.1, 21.3, 21.4, 21.5, 21.6, 21.7, Summary
+Computational discourse, dialogue, coherence, segmentation, reference
+       resolution, reference phenomena, pronom anaphora resolution, coreference
+
+Ch22: complete
+Information extraction, named entities(rec/prec), relations
+       ((lightly)supervised),, temporal/event(normalization, timebank) template
+       filling (fsm,stat)
+
+Ch23: Intro, 23.1, 23.2, 23.3, 23.6, Summary
+question answering, summarization, information retrieval(vectorspace), factoid
+answering(query formulation, classification, passage retrieval, answer
+processing, evaluation), summarization, focussed summarization/qa
+
+Ch24: complete
+Dialogue, conversational agents, human conversation(turn taking, speech acts,
+grounding, structure, implicature),
+basic: dialogue system(asr, nul, ttl, dialogue manager,
+       confirmation/rejection), ds design/evaluation, information state(dialacts)
+marko decision, plan based
+
+Ch25: complete
+Machine translation, difficulties(typology, structural divergence, lexical
+divergence)
+classical mt: vauquois triangle, direct, syntactic transfer, semantic transfer
+statistical mt: phrase based, alignment, IBM model, HMM alignment, EM training,
+decoding
+evaluation

diff --git a/excerpt_mt.txt b/excerpt_mt.txt
deleted file mode 100644 (file)
index 5530550..0000000
--- a/excerpt_mt.txt
+++ /dev/null
@@ -1,26 +0,0 @@
-Ch1:  complete
-Overview
-Ch2:  complete
-Regex, (non-)deterministic automata
-Ch3:  Intro, 3.1, 3.2, 3.8, 3.9, Summary, Notes
-Morfology, stem, affix, form words from stems, porterstemmer
-Ch4:  Intro, 4.1, 4.2, 4.3, 4.4, 4.5, 4.6, 4.7.intro, 4.8, 4.9, 4.10, 4.11, Summary, Notes
-NGrams, smoothing, perplexity, entropy
-Ch5:  Intro, 5.1, 5.2, 5.3, 5.4, 5.5, 5.6, 5.7, 5.8, Summary, Notes
-POS-tagging, rulebased, hmm, viterbi, table, noisy channel
-Ch6:  Intro, 6.1, 6.2, 6.3, 6.4, 6.5,  6.6, 6.7, 6.8, Summary, Notes
-hmm, forward, viterbi, forwardbackward, mem (hypothesis, iterate), 
-Ch7:  Intro, 7.1, 7.3, 7.4, Summary
-Phonetics, features, voicing, spectogram, IPA
-Ch8:  complete
-Synthesis, (norm-phonetic-prosody-repr-make), diphone, unit selection
-Ch9:  complete
-asr, cepstralfeature-model,likelihood-viterbi/codebook(distance), worderrorrate 
-Ch12: Intro, 12.1, 12.2, 12.3, 12.4, 12.5, 12.6, 12.7.intro, 12.7.1, 12.8, Summary, Notes
-Grammar, CFG, sample grammars, head(most important), chomsky nf, spoken(disfl)
-Ch13: complete
-Syntax parsing, top down(cky), bottomup(early), partial(IOB)
-Ch15: Intro, 15.1, 15.2, 15.3, 15.5.intro, 15.5.1, 15.6.intro, 15.6.1, Summary, Notes
-Features, unification, structures, grammar addition, typing
-Ch16: Intro, 16.1, 16.3, Summary
-Complexity, chomsky hierarchy, nl not cfg