Share PowerPoint. Anywhere!

nakov paskaleva improved word alignments v10

Uploaded from authorPOINT Lite
Download as Download Not Available PPT
Presentation Description

No description available

Views: 16
Like it  ( Likes) Dislike it  ( Dislikes)
Added: November 26, 2007 This presentation is Public
Presentation Category :Entertainment
Tags Add Tags
Presentation StatisticsNew!
Views on authorSTREAM: 16
Presentation Transcript

Improved Word Alignments Using the Web as a Corpus : Improved Word Alignments Using the Web as a Corpus Preslav Nakov, University of California, Berkeley Svetlin Nakov, Sofia University "St. Kliment Ohridski" Elena Paskaleva, Bulgarian Academy of Sciences International Conference RANLP 2007 (Recent Advances in Natural Language Processing)


Statistical Machine Translation (SMT) : Statistical Machine Translation (SMT) 1988 – IBM models 1, 2, 3, 4 and 5 Start with bilingual parallel sentence-aligned corpus Learn translation probabilities of individual words 2004 – PHARAOH model Learn translation probabilities for phrases Alignment template approach – extracts translation phrases from word alignments Improved word alignments in sentences improve translation quality!


Word Alignments : Word Alignments The word alignments problem Given a bilingual parallel sentence-aligned corpus align the words in each sentence with corresponding words in its translation Example English sentence Example Bulgarian sentence Try our same day delivery of fresh flowers, roses, and unique gift baskets. Опитайте нашите свежи цветя, рози и уникални кошници с подаръци с доставка на същия ден.


Word Alignments – Example : Word Alignments – Example try our same day delivery of fresh flowers roses and unique gift baskets опитайте нашите свежи цветя рози и уникални кошници с подаръци с доставка на същия ден


Our Method : Our Method Use combination of Orthographic similarity measure Semantic similarity measure Competitive linking Orthographic similarity measure Modified weighted minimum-edit-distance Semantic similarity measure Analyses the co-occurring words in the local contexts of the target words using the Web as a corpus


Orthographic Similarity : Orthographic Similarity Minimum Edit Distance Ratio (MEDR) MED(s1, s2) = the minimum number of INSERT / REPLACE / DELETE operations for transforming s1 to s2 Longest Common Subsequence Ratio (LCSR) LCS(s1, s2) = the longest common subsequence of s1 and s2


Orthographic Similarity : Orthographic Similarity Modified Minimum Edit Distance Ratio (MMEDR) for Bulgarian / Russian Normalize the strings Assign weights for the edit operations Normalizing the strings Hand-crafted rules Strip the Russian letters "ь" and "ъ" Remove the Russian "й" at the endings Remove the definite article in Bulgarian (e.g. "ът", "ят" at the endings)


Orthographic Similarity : Orthographic Similarity Assigning weights for the edit operations 0.5-0.9 for the vowel to vowel substitutions, e.g. 0.5 for е  о 0.5-0.9 for some consonant-consonant replacements, e.g. с  з 1.0 for all other edit operations Example: Bulgarian първият and the Russian первый (first) Normalization produces първи and перви, thus MMED = 0.5 (weight 0.5 for ъ  о)


Semantic Similarity : Semantic Similarity What is local context? Few words before and after the target word The words in the local context of given word are semantically related to it Need to exclude the stop words: prepositions, pronouns, conjunctions, etc. Stop words appear in all contexts Need of sufficiently big corpus Same day delivery of fresh flowers, roses, and unique gift baskets from our online boutique. Flower delivery online by local florists for birthday flowers.


Semantic Similarity : Semantic Similarity Web as a corpus The Web can be used as a corpus to extract the local context for given word The Web is the largest possible corpus Contains big corpora in any language Searching some word in Google can return up to 1 000 excerpts of texts The target word is given along with its local context: few words before and after it Target language can be specified


Semantic Similarity : Semantic Similarity Web as a corpus Example: Google query for "flower"


Semantic Similarity : Semantic Similarity Measuring semantic similarity For given two words their local contexts are extracted from the Web A set of words and their frequencies Apply lemmatization Semantic similarity is measured as similarity between these local contexts Local contexts are represented as frequency vectors for given set of words Cosine between the frequency vectors in the Euclidean space is calculated


Semantic Similarity : Semantic Similarity Example of context words frequencies word: flower word: computer


Semantic Similarity : Semantic Similarity Example of frequency vectors Similarity = cosine(v1, v2) v1: flower v2: computer


Cross-Lingual Semantic Similarity : Cross-Lingual Semantic Similarity We are given two words in different languages L1 and L2 We have a bilingual glossary G of translation pairs {p ∈ L1, q ∈ L2} Measuring cross-lingual similarity: We extract the local contexts of the target words from the Web: C1 ∈ L1 and C2 ∈ L2 We translate the context We measure similarity between C1* and C2


Competitive Linking : Competitive Linking What is competitive linking? One-to-one bi-directional word alignments algorithm Greedy "best first" approach Links the most probable pair first, removes it, and repeats the same for the rest


Applying Competitive Linking : Applying Competitive Linking Make all words lowercase Remove punctuation Remove the stop words: prepositions, pronouns, conjunctions, etc. We don't align them Align the most similar pair of words Using the orthographic similarity combined with the semantic similarity Remove the aligned words Align the rest of the sentences


Our Method – Example : Our Method – Example Bulgarian sentence Russian sentence Процесът на създаването на такива рефлекси е по-сложен, но същността им е еднаква. Процесс создания таких рефлексов сложнее, но существо то же.


Out Method – Example : Out Method – Example Remove the stop words Bulgarian: на, на, такива, е, но, им, е Russian: таких, но, то Align рефлекси and рефлексов (semantic similarity = 0.989) Align по-сложен and сложнее (orthographic similarity = 0.750) Align процесът and процесс (orthographic similarity = 0.714) Align създаването and создания (orthographic similarity = 0.544) Align процесът and процесс (orthographic similarity = 0.536) Not aligned: еднаква


Our Method – Example : Our Method – Example процесът на създаването на такива рефлекси е по-сложен но същността им е еднаква процесс создания таких рефлексов сложнее но существо то же


Evaluation : Evaluation We evaluated the following algorithms BASELINE: the traditional alignment algorithm (IBM model 4) LCSR, MEDR, MMEDR: orthographic similarity algorithms WEB-ONLY: semantic similarity algorithm WEB-AVG: average of WEB-ONLY and MMEDR WEB-MAX: maximum of WEB-ONLY and MMEDR WEB-CUT: 1 if MMEDR(s1, s2) >= α (0 < α < 1), or WEB-ONLY(s1, s2) otherwise


Testing Data and Experiments : Testing Data and Experiments Testing data set A corpus of 5 827 parallel sentences Training set: 4 827 sentences Tuning set: 500 sentences Testing set: 500 sentences Experiments Manual evaluation of WEB-CUT AER for competitive linking Translation quality: BLEU / NIST


Manual Evaluation of WEB-CUT : Manual Evaluation of WEB-CUT Aligned the texts of the testing data set Used competitive linking and WEB-CUT for α=0.62 Obtained 14,246 distinct word pairs Manually evaluated the aligned pairs as: Correct Rough (considered incorrect) Wrong (considered incorrect) Calculated precision and recall For the case MMEDR < 0.62


Manual Evaluation of WEB-CUT : Manual Evaluation of WEB-CUT Precision-recall curve


Evaluation of Alignment Error Rate : Evaluation of Alignment Error Rate Gold standard for alignment For the first 100 sentences Created manually by a linguist Stop words and punctuation were removed Evaluated the alignment error rate (AER) for competitive linking Evaluated for all the algorithms LCSR, MEDR, MMEDR, WEB-ONLY, WEB-AVG, WEB-MAX and WEB-CUT


Evaluation of Alignment Error Rate : Evaluation of Alignment Error Rate AER for competitive linking


Evaluation of Translation Quality : Evaluation of Translation Quality Built a Russian  Bulgarian statistical machine translation (SMT) system Extracted from the training set the distinct word pairs aligned with competitive linking Added them twice as additional “sentence” pairs to the training corpus Trained log-linear model for SMT with standard feature functions Used minimum error rate training on the tuning set Evaluated BLUE and NIST score on the testing set


Evaluation of Translation Quality : Evaluation of Translation Quality Translation quality: BLEU


Evaluation of Translation Quality : Evaluation of Translation Quality Translation quality: NIST


Resources : Resources We used the following resources: Bulgarian-Russian parallel corpus: 5 827 sentences Bilingual Bulgarian / Russian glossary: 3 794 pairs of translation words A list of 599 Bulgarian / 508 Russian stop words Bulgarian lemma dictionary: 1 000 000 wordforms and 70 000 lemmata Russian lemma dictionary: 1 500 000 wordforms and 100 000 lemmata


Conclusion and Future Work : Conclusion and Future Work Conclusion Semantic similarity extracted from the Web can improve statistical machine translation For similar languages like Bulgarian and Russian orthographic similarity is useful Future Work Improve MMED with automatic leaned rules Improve the semantic similarity algorithm Filter parasite words like "site", "click", etc. Replace competitive linking with maximum weight bipartite matching


Questions? : Questions? Improved Word Alignments Using the Web as a Corpus