In this paper, we propose to use deep syntactic information for obtaining fine-grained translation rules.

A head-driven phrase structure grammar (HPSG) parser is used to obtain the deep syntactic information, which includes a fine-grained description of the syntactic property and a semantic representation of a sentence.

We extract fine-grained rules from aligned HPSG tree/forest-string pairs and use them in our tree-to-string and string-to-tree systems.

But, “VBN(killed)” is indeed separable into two fine-grained tree fragments of “VBN(killedzactive)” and “VBN(killed:passive)”1.

This motivates our proposal of using deep syntactic information to obtain a fine-grained translation rule set.

deep syntactic information of an English sentence, which includes a fine-grained description of the syntactic property and a semantic representation of the sentence.

Before describing our approaches of applying deep syntactic information yielded by an HPSG parser for fine-grained rule extraction, we would like to briefly review what kinds of deep syntactic information have been employed for SMT.

fine-grained tree-to-string rule extraction, rather than string-to-string translation (Hassan et al., 2007; Birch et al., 2007).

The proposed models are tested on three different tasks: coarse-grained word sense disambiguation, fine-grained word sense disambiguation, and detection of literal vs. nonliteral usages of potentially idiomatic expressions.

We evaluate our models on three different tasks: coarse-grained WSD, fine-grained WSD and literal vs. nonliteral sense detection.

To determine whether our model is also suitable for fine-grained WSD, we test on the data provided by Pradhan et al.

(2009) for the Semeval-2007 Task-l7 (English fine-grained all-words task).

Table 4: Model performance (F-score) for the fine-grained word sense disambiguation task.

5.2 Fine-grained WSD

Fine-grained WSD, however, is a more difficult task.

We apply these models to coarse- and fine-grained WSD and find that they outperform comparable systems for both tasks.

We postulate that interlinear glossed text is sufficiently fine-grained to serve our purposes.

All documents will be included in primary form, but the percentage of documents with manual annotation, or manually corrected annotation, decreases at increasingly fine-grained levels of annotation.

Where manual fine-grained annotation is unavailable, automatic methods for creating it (at a lower quality) are desirable.

But word appears to be too fine-grained in some cases such as non-compositional phrasal equivalences, where no clear word alignments exist.

It is proposed to replace too fine-grained word as basic translational unit.

But there is a deficiency in such manner that word is too fine-grained in some cases such as non-compositional phrasal equivalences, where clear word alignments do not exist.

The Petrov parser uses latent variables to refine a coarse-grained grammar extracted from a training corpus to a grammar which makes much more fine-grained syntactic distinctions.

in Petrov’s experiments on the Penn treebank, the syntactic category NP was refined to the more fine-grained N P1 and N P2 roughly corresponding to N Ps in subject and object positions.

However, this fine-grained control is exactly what the Petrov parser does automatically.

In this paper, we present a novel, fine-grained taxonomy of 43 noun-noun semantic relations, the largest annotated noun compound dataset yet created, and a supervised classification method for automatic noun compound interpretation.

The .57-.67 H figures achieved by the Voted annotations compare well with previously reported inter-annotator agreement figures for noun compounds using fine-grained taxonomies.

In this paper, we present a large, fine-grained taxonomy of 43 noun compound relations, a dataset annotated according to this taxonomy, and a supervised, automatic classification method for determining the relation between the head and modifier words in a noun compound.

We use standard classification accuracy (Acc) on the most fine-grained level of target categories in the genre hierarchy.

This paper explores a way of using information on the hierarchy of labels for improving fine-grained genre classification.

Let x be a document and wm a weight vector associated with the genre class m in a corpus with k genres at the most fine-grained level.