Phrase

About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.

Semantic Roles for SMT: A Hybrid Two-Pass Model

Abstract: We present results on a novel hybrid semantic SMT model that incorporates the strengths of both semantic role labeling and phrase-based statistical machine translation. The approach avoids major complexity limitations via a two-pass architecture. The first pass is performed using a conventional phrase-based SMT model. The second pass is performed by a re-ordering strategy guided by shallow semantic parsers that produce both semantic frame and role labels. Evaluation on a Wall Street Journal newswire genre test set showed the hybrid model to yield an improvement of roughly half a point in BLEU score over a strong pure phrase-based SMT baseline -- to our knowledge, the first successful application of semantic role labeling to SMT.

Term clustering of syntactic phrases

Abstract: Term clustering and syntactic phrase formation are methods for transforming natural language text. Both have had only mixed success as strategies for improving the quality of text representations for document retrieval. Since the strengths of these methods are complementary, we have explored combining them to produce superior representations. In this paper we discuss our implementation of a syntactic phrase generator, as well as our preliminary experiments with producing phrase clusters. These experiments show small improvements in retrieval effectiveness resulting from the use of phrase clusters, but it is clear that corpora much larger than standard information retrieval test collections will be required to thoroughly evaluate the use of this technique.

Trainable Methods for Surface Natural Language Generation

Abstract: We present three systems for surface natural language generation that are trainable from annotated corpora. The first two systems, called NLG1 and NLG2, require a corpus marked only with domain-specific semantic attributes, while the last system, called NLG3, requires a corpus marked with both semantic attributes and syntactic dependency information. All systems attempt to produce a grammatical natural language phrase from a domain-specific semantic representation. NLG1 serves a baseline system and uses phrase frequencies to generate a whole phrase in one step, while NLG2 and NLG3 use maximum entropy probability models to individually generate each word in the phrase. The systems NLG2 and NLG3 learn to determine both the word choice and the word order of the phrase. We present experiments in which we generate phrases to describe flights in the air travel domain.

Prosody in Speech Understanding Systems

Abstract: Basic approaches- The baseline ASU systems- Prosody- Prosodic labeling and speech corpora- Preprocessing and classification- Prosodic phrase models- Intergration of the prosodic attributes in ASU- Future work- Summary

Minimality, Reconstruction, and PF Movement

Abstract: We investigate the interaction of clitic left-dislocation (CLLD), wh-interrogatives, and topicalization in Lebanese Arabic. A wh-phrase or a topicalized phrase can be fronted across a CLLDed element derived by movement but not across a base-generated one. A CLLDed element cannot be fronted across another CLLDed element, a wh-phrase, or a topicalized phrase. These interception effects are accounted for only if Minimality is construed as a constraint on derivations rather than representations and if fronting of the CLLDed elements is seen to apply in the PF component. It is thus suggested that the mapping between overt Syntax and the Articulatory-Perceptual level is not trivial.