12/1/2014 Natural Language Processing The Task Diachronics Dan Klein – UC Berkeley Includes joint work with Alex Bouchard ‐ Cote, Tom Griffiths, and David Hall Lexical Reconstruction Tree of Languages Latin focus We assume the phylogeny is known Much work in French Spanish Italian Portuguese biology, e.g. work by Warnow, Felsenstein, feu fuego fuoco fogo Steele… Also in linguistics, e.g. Warnow et al., Gray and Atkinson… http://andromeda.rutgers.edu/~jlynch/language.html Evolution through Sound Changes Changes are Systematic Eng. camera from Latin, camera / kamera / numerus / numerus / “camera obscura” camera / kamera / Latin e _ e _ Deletion: / e /, / a / camra / kamra / numrus / numrus / Change: / k / .. / t ṏ / .. / ṏ / Insertion: / b / chambre / ṏ amb Й / French Eng. chamber from Old Fr. before the initial / t / dropped 1
12/1/2014 Changes Have Structure Changes are Contextual camera / kamera / camra / kamra / e _ _ b e _ / after stress _ b / m_r _ [ stop x ] / [ nasal x ]_r camra / kamra / cambra / kambra / Diachronic Evidence Changes are Systematic English Great Vowel Shift (Simplified!) Yahoo! Answers [ca 2000] Appendix Probi [ca 300] “time” = teem “time” = taim i e tonight not tonite tonitru non tonotru a Synchronic (Comparative) Evidence The Data Key idea: changes occur uniformly across the lexicon 2
12/1/2014 The Data The Data Data sets Data sets Small: Romance Small: Romance French, Italian, Portuguese, Spanish French, Italian, Portuguese, Spanish 2344 words 2344 words Complete cognate sets Complete cognate sets FR IT PT ES FR IT PT ES Target: (Vulgar) Latin Target: (Vulgar) Latin Large: Austronesian 637 languages 140K words Incomplete cognate sets Target: Proto ‐ Austronesian Austronesian Austronesian Examples From the Austronesian Basic Vocabulary Database Simple Model: Single Characters G The Model G C G G C C C C C G G [cf. Felsenstein 81] 3
12/1/2014 Changes are Systematic Parameters are Branch ‐ Specific focus ES LA IB /fokus/ /fokus/ /fokus/ /kentrum/ IT PT /fogo/ /fogo/ IB /fogo/ /sentro/ fuoco fuego fogo /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ /t ṏ ƌ ntro/ /sentro/ /sentro/ IT ES PT [Bouchard ‐ Cote, Griffiths, Klein, 07] Edits are Contextual, Structured # f o /fokus/ Ꜽ # f w Inference IT /fw Ꜽ ko/ Learning: Objective Learning: EM M ‐ Step Find parameters which fit /fokus/ /fokus/ z (expected) sound change counts /fogo/ /fogo/ Easy: gradient ascent on theta /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ w E ‐ Step Find (expected) change /fokus/ counts given parameters Hard: variables are string ‐ /fogo/ valued /fw Ꜽ ko/ /fwe ɋ o/ /fogo/ 4
12/1/2014 Computing Expectations A Gibbs Sampler Standard approach, e.g. [Holmes 2001]: Gibbs sampling each sequence ‘grass’ ‘grass’ [Holmes 01, Bouchard ‐ Cote, Griffiths, Klein 07] A Gibbs Sampler A Gibbs Sampler ‘grass’ ‘grass’ Getting Stuck Getting Stuck ? How could we jump to a state where the liquids /r/ and /l/ have a common ancestor? 5
12/1/2014 Efficient Sampling: Vertical Slices Single Sequence Resampling Results Ancestry Resampling [Bouchard ‐ Cote, Griffiths, Klein, 08] Results: Romance Learned Rules / Mutations Learned Rules / Mutations Results: Austronesian 6
12/1/2014 Examples: Austronesian Result: More Languages Help Distance from Blust [1993] Reconstructions Mean edit distance Number of modern languages used [Bouchard ‐ Cote, Hall, Griffiths, Klein, 13] Visualization: Learned Universals Regularity and Functional Load In a language, some pairs of sounds are more contrastive than others (higher functional load) Example: English p/d versus t/th High Load: p/d: pot/dot, pin/din dress/press, pew/dew, ... Low Load: t/th: thin/tin *The model did not have features encoding natural classes Functional Load: Timeline Regularity and Functional Load 1955: Functional Load Hypothesis (FLH): Sound changes are Data: only 4 languages from the Austronesian data less frequent when they merge phonemes with high functional load [Martinet, 55] Merger posterior probability 1967: Previous research within linguistics: “FLH does not seem to be supported by the data” [King, 67] (Based on 4 Each dot is a sound change languages as noted by [Hocket, 67; Surandran et al., 06]) identified by the system Our approach: we reexamined the question with two orders of magnitude more data [Bouchard ‐ Cote, Hall, Griffiths, Klein, 13] Functional load as computed by [King, 67] 7
12/1/2014 Regularity and Functional Load Data: all 637 languages from the Austronesian data Merger posterior probability Extensions Functional load as computed by [King, 67] Cognate Detection Grammar Induction GL Avg rel gain: 29% ‘fire’ IE G RM 70 WG NG 60 50 Portuguese Swedish Spanish Slovene Chinese English Danish Dutch /fw Ꜽ ko/ /v ƌ rbo/ /t ṏ ƌ ntro/ 40 30 /sentro/ /ber Ǎ o/ /fwe ɋ o/ 20 /v ƌ rbo/ /fogo/ /s ƌ ntro/ 10 0 [Hall and Klein, 11] [Berg ‐ Kirkpatrick and Klein, 07] Language Diversity Why are the languages of the world so similar? Universal grammar answer: Hardware constraints Common source answer: Not much time has passed [Rafferty, Griffiths, and Klein, 09] 8
Recommend
More recommend