In this way, we incorporate rich context information of PAS for disambiguation.

The two methods successfully incorporate the rich context information into the translation process.

Specifically, after integrating the inside context information of PAS into transformation, we can see that system IC-PASTR significantly outperforms system PASTR by 0.71 BLEU points.

Conversely, by considering the context information , the PASTR+MEPD system chooses a correct rule for translation:

In this paper, we propose two novel methods to incorporate rich context information to handle PAS ambiguities.

In order to handle the role ambiguities, in this section, we concentrate on utilizing a maximum entropy model to incorporate the context information for PAS disambiguation.

The target-side-like PAS is selected only according to the language model and translation probabilities, without considering any context information of PAS.

They combine rich context information to do disambiguation for words or phrases, and achieve improved translation performance.

By incorporating the rich context information as features, they chose better rules for translation and yielded stable improvements on translation quality.

They also combine the context information in the model.

Table 6: Impact of the contextual information .

3.5 Impact of the Contextual Information

In this paper, we translate the English questions into other four languages using Google Translate (GTrans), which takes into account contextual information during translation.

The basic idea is to capture the contextual information in modeling the translation of phrases as a whole, thus the word ambiguity problem is somewhat alleviated.

tions: (1) Contextual information is exploited during the translation from one language to another.

For example in Table 1, English words “interest” and “bank” that have multiple meanings under different contexts are correctly addressed by using the state-of-the-art translation tool — —Google Translate.4 Thus, word ambiguity based on contextual information is naturally involved when questions are translated.

Statistical machine translation (e.g., Google Translate) can utilize contextual information during the question translation, so it can solve the word ambiguity and word mismatch problems to some extent.

Long distance reordering remains one of the greatest challenges in statistical machine translation research as the key contextual information may well be beyond the confine of translation units.

We presented a novel approach to address a kind of long-distance reordering that requires global cross-boundary contextual information .

Empirical results confirm our intuition that incorporating cross-boundaries contextual information improves translation quality.

As shown, the empirical results confirm our intuition that SMT can greatly benefit from reordering model that incorporate cross-unit contextual information .

Often, such reordering decisions require contexts that span across multiple translation units.1 Unfortunately, previous approaches fall short in capturing such cross-unit contextual information that could be

In this paper, we argue that reordering modeling would greatly benefit from richer cross-boundary contextual information

We introduce a reordering model that incorporates such contextual information , named the Two-Neighbor Orientation (TNO) model.

Our results show that encoding priors on words and context information contributes significantly to the performance of semantic clustering.

Rather than using single turn utterances, we hope to utilize the context information , e.g., information from previous turns for improving the performance of the semantic tagging of the current turns.

To include contextual information , we add binary features for all possible tags.

The results indicate that incorporating context information with MTR is an effective option for identifying semantic ambiguity.

To make use of both word identity and context information of a given type, we use S-CODE co-occurrence modeling (Maron et al., 2010) as (Yatbaz et al., 2012) does.

In that experiment, POS induction is done by using word identities and context information represented by substitute words.

of a target word, we separate occurrences of the word into different groups depending on the context information represented by substitute vectors.

As the stack of a state keeps changing during the decoding process, the context information needed to calculate dependency language model and maximum entropy model probabilities (e. g., root word, leftmost child, etc.)

As a result, the chance of risk-free hypothesis recombination (Koehn et al., 2003) significantly decreases because complicated contextual information is much less likely to be identical.

In the future, we plan to include more contextual information (e.g., the uncovered source phrases) in the maximum entropy model to resolve conflicts.