Training Size: Training data improves the conditional probability baseline, but does not help the smoothing model.

We optimized argument cutoffs for each training size, but the model still appears to suffer from additional noise that the conditional probability baseline does not.

High Precision Baseline: Our conditional probability baseline is very precise.

The conditional probability is reported as Baseline.

We propose a conditional probability baseline:

(1999) showed that corpus frequency and conditional probability correlate with human decisions of adjective-noun plausibility, and Dagan et al.

(1999) appear to propose a very similar baseline for verb-noun selectional preferences, but the paper evaluates unseen data, and so the conditional probability model is not studied.

The conditional probability Baseline falls from 91.5 to 79.5, a 12% absolute drop from completely random to neighboring frequency.

Accuracy is the same as recall when the model does not guess between pseudo words that have the same conditional probabilities .

This paper presents a probabilistic model for sense disambiguation which chooses the best sense based on the conditional probability of sense paraphrases given a context.

We use a topic model to decompose this conditional probability into two conditional probabilities with latent variables.

We approach the sense disambiguation task by choosing the best sense based on the conditional probability of sense paraphrases given a context.

We propose three models which are suitable for different situations: Model I requires knowledge of the prior distribution over senses and directly maximizes the conditional probability of a sense given the context; Model 11 maximizes this conditional probability by maximizing the cosine value of two topic-document vectors (one for the sense and one for the context).

Assigning the correct sense 3 to a target word 21) occurring in a context 0 involves finding the sense which maximizes the conditional probability of senses given a context:

This conditional probability is decomposed by incorporating a hidden variable, topic 2, introduced by the topic model.

Model I directly maximizes the conditional probability of the sense given the context, where the sense is modeled as a ‘paraphrase document’ ds and the context as a ‘context document’ dc.

We obtain final BLEU scores of 19.35 ( conditional probability model) and 19.00 (joint probability model) as compared to 14.30 for a baseline phrase-based system and 16.25 for a system which transliterates OOV words in the baseline system.

We found that the joint probability model performs almost as well as the conditional probability model but that it was more complex to make it work well.

We refer to the results as Mchy where cc denotes the model number, 1 for the conditional probability model and 2 for the joint probability model and 3/ denotes a heuristic or a combination of heuristics applied to that model”.

3.1 Model-1 : Conditional Probability Model

Our model estimates the conditional probability by interpolating a word-based model and a character-based (transliteration) model.

Because our overall model is a conditional probability model, joint-probabilities are marginalized using character-based prior probabilities:

The parser produces prefix probabilities for each word of a sentence which we converted to conditional probabilities by dividing each current probability by the previous one.

Backward transitional probability is essentially the conditional probability of a word given its immediately preceding word, P(wk|wk_1).

Analogously, forward probability is the conditional probability of the current word given the next word, P(wk|wk+1).

This measure of processing cost for an input word, wk+1, given the previous context, W1...Wk, can be expressed straightforwardly in terms of its conditional probability as:

The CRF segmentation provides a list of segmentations: A : A1, A2, ..., AN, with conditional probabilities P(A1|S), P(A2|S), ..., P(AN|S).

The CRF conversion, given a segmentation Ai, provides a list of transliteration output T1,T2, ...,TM, with conditional probabilities P(T1|S,Ai),P(T2|S,Az-), ...,P(TM|S,Az-).

From the two-step CRF model we get the conditional probability PC RF (T |S ) and from the JSCM we get the joint probability P(S, T).

The conditional probability of PJSC M (T |S) can be calculuated as follows:

The edge affinities afl' between these nodes are the conditional probabilities of each word wg belonging to each cognate group 9:

Because we enforce that a word in language d must be dead if its parent word in language a is dead, we just need to learn the conditional probabilities p(Sd = dead|Sa = alive).

Given the expected counts, we now need to normalize them to ensure that the transducer represents a conditional probability distribution (Eisner, 2002; Oncina and Sebban, 2006).

The conditional probability P(o | TC) is decomposes into the product of rule probabilities:

where the first three are conditional probabilities based on fractional counts of rules defined in Section 3.4, and the last two are lexical probabilities.

We use fractional counts to compute three conditional probabilities for each rule, which will be used in the next section: