Unlike previous work, which primarily leverages syntactic analysis through dependency tree matching, we focus on improving the performance using models of lexical semantic resources.

Experiments show that our systems can be consistently and significantly improved with rich lexical semantic information, regardless of the choice of learning algorithms.

nent, lexical semantics .

We formulate answer selection as a semantic matching problem with a latent word-alignment structure as in (Chang et al., 2010) and conduct a series of experimental studies on leveraging recently proposed lexical semantic models.

First, by incorporating the abundant information from a variety of lexical semantic models, the answer selection system can be enhanced substantially, regardless of the choice of learning algorithms and settings.

1For example, Heilman and Smith (2010) emphasized that “The tree edit model, which does not use lexical semantics knowledge, produced the best result reported to date.”

In this work, we focus our study on leveraging the low-level semantic cues from recently proposed lexical semantic models.

Although lexical semantic information derived from WordNet has been used in some of these approaches, the research has mainly focused on modeling the mapping between the syntactic structures of questions and sentences, produced from syntactic analysis.

The potential improvement from enhanced lexical semantic models seems to have been deliberately overlooked.1

We proposed syntactic tree kernels enriched by lexical semantic similarity to tackle the portability of a relation extractor to different domains.

In the empirical evaluation on Automatic Content Extraction (ACE) data, we evaluate the impact of convolution tree kernels embedding lexical semantic similarities.

The same holds also for the lexical semantic kernel based on LSA (P_LSA), however, to only two out of three domains.

As the two semantically enriched kernels, PETLSA and PET_WC, seem to capture different information we use composite kernels (rows 10-11): the baseline kernel (PET) summed with the lexical semantic kernels.

It builds on the development of lexical semantic resources and provides a platform for learning to utilize these resources.

As opposed to Roth and Frank, PARMA is designed as a a trainable platform for the incorporation of the sort of lexical semantic resources used in the related areas of Recognizing Textual Entailment (RTE) and Question Answering (QA).

The focus of PARMA is the integration of a diverse range of features based on existing lexical semantic resources.