Fully parsing the Penn Treebank

Abstract

We present a two stage parser that recovers Penn Treebank style syntactic analyses of new sentences including skeletal syntactic structure, and, for the first time, both function tags and empty categories. The accuracy of the first-stage parser on the standard Parseval metric matches that of the (Collins, 2003) parser on which it is based, despite the data fragmentation caused by the greatly enriched space of possible node labels. This first stage simultaneously achieves near state-of-theart performance on recovering function tags with minimal modifications to the underlying parser, modifying less than ten lines of code. The second stage achieves state-of-the-art performance on the recovery of empty categories by combining a linguistically-informed architecture and a rich feature set with the power of modern machine learning methods.

Sorry Dave, I'm Afraid I Can't Do That: Explaining Unachievable Robot Tasks Using Natural Language

“…While simple natural language understanding can be performed with shallower processing techniques, parsing allows for recovery of the hierarchical structure of the sentence, allowing for proper handling of natural language phenomena such as negation (e.g., Never go to the lounge) and coordination (e.g., Go to the lounge and kitchen) which are crucial to understanding commands. SLURP uses the pipeline of natural language processing components used by Brooks et al [6]: the Bikel parser [3] combined with the null element (understood subject) restoration of Gabbard et al [12] to parse sentences. Before being given to the parser, the input is tagged using MXPOST [23].…”

Building an Efficient Functional-Tag Labeling System for Vietnamese

“…Gabbard et al [9] claimed that by modifying less than ten lines of code, Bikel's parser, a state-of-the-art implementation of Collins' method, achieved near stateof-the-art performance on recovering functional tags. However, since parsing models are often designed based on probabilistic context-free grammars (PCFGs), it is not easy to extend these models to use new features.…”

“…In this by-parsing approach [7,9], functional labels are determined immediately during the parsing process. Traditionally, syntactic parsing bases on formal grammars such as context-free grammars in which nonterminal symbols represents linguistic constituents such as noun phrase (NP tag) while in parsing adapted for including functional labeling, non-terminal symbols represent linguistic constituents with richer information such as temporal noun phrase (NP-TMP tag).…”

Resumptive Pronoun Detection for Modern Standard Arabic to English MT

“…Recent research demonstrates that recovery of empty categories can lead to improved translation quality for some language pairs (Chung and Gildea, 2010;Xiang et al, 2013). For more information on the recovery of empty categories, we refer the interested reader to work by Kukkadapu and Mannem (2013), Cai et al (2011), Yang andXue (2010), Gabbard et al (2006), Schmid (2006), Dienes andDubey (2003), andJohnson (2002).…”