This paper presents and evaluates an original approach to automatically align bitexts at the word level. It relies on a syntactic dependency analysis of the source and target texts and uses a machine-learning technique, namely inductive logic programming, to automatically infer rules called syntactic alignment rules. These rules make the most of the syntactic information to align words. This ma...

Fine et al. (2013) recently demonstrated that readers continually adapt their syntactic expectations in order to accurately approximate the distributions of syntactic structures in a given communicative context. Here, we examine patterns of eye movements as subjects read sentences that contain an atypical distribution of syntactic structures to gain more fine-grained insight into the time-cours...

We present an approach for deriving syntactic word clusters from parsed text, grouping words according to their unlexicalized syntactic contexts. We then explore the use of these syntactic clusters in leveraging a large corpus of trees generated by a high-accuracy parser to improve the accuracy of another parser based on a different formalism for representing a different level of sentence struc...

Thorough investigation of early syntactic knowledge necessitates methodologies that tap young children's linguistic competence while minimizing extra-linguistic demands and not relying on production. The preferential looking paradigm is uniquely suited to such a task. We present here a test case for the exploration of early syntactic knowledge in young children: Principle C effects at 30 months...

Much recent work in computational linguistics emphasizes the role of lexical information in syntactic representation and processing. In this paper, I propose to represent syntax as an abstraction of subcategorization frames, from a word-speciic level to a general, abstract level (syntactic categories). The representation is linguistically perspicuous, and useful for processing. I deene a parsin...

This paper will discuss the necessity for standardizing semantics beyond simply standardizing syntactic and structural (XML) vocabularies in the area of Ecommerce. We will present an ontology-based approach to handle semantics, which enables application developers to raise the level of abstraction from errorprone syntactic manipulations to a conceptual level. This approach has been implemented ...

This paper presents a system that carries out highly eeective searches over collections of textual information, such as those found on the Internet. The system is comprised of two major parts. The rst part consists of an agent, MUSAG, that learns to relate concepts that are semantically \similar" to one another. In other words, this agent dynamically builds a dictionary of expressions for a giv...

Automatic evaluation of machine translation, based on computing n-gram similarity between system output and human reference translations, has revolutionized the development of MT systems. We explore the use of syntactic information, including constituent labels and head-modifier dependencies, in computing similarity between output and reference. Our results show that adding syntactic informatio...

1. Introduction This paper investigates the effect of changing syntactic categories on speaker choice, using the needs to be done ∼ needs doing alternation as the testing ground. The two alternants in this alternation have different syntactic properties , and so we hypothesize that the syntactic preferences of the alternation's environment influence alternant choice. Our hypothesis is that, all...