Experimental Results | We also show that the combination of unlexicalized, open extraction in O-CRF and lexicalized , supervised extraction in R1 -CRF improves precision and F-measure compared to a standalone RE system. |
Experimental Results | The lexicalized R1 -CRF extractor is able to recover from this error; the presence of the word “Acquire” is enough to recog- |
Experimental Results | We found that while RES OLVER improves the relative recall of O-CRF by nearly 50%, O-CRF locates fewer synonyms per relation compared to its lexicalized counterpart. |
Hybrid Relation Extraction | We now describe an ensemble-based or hybrid approach to RE that leverages the different views offered by open, self- supervised extraction in O-CRF, and lexicalized , supervised extraction in Rl-CRF. |
Introduction | The relationship between standard RE systems and the new Open IE paradigm is analogous to the relationship between lexicalized and unlexicalized parsers. |
Introduction | Statistical parsers are usually lexicalized (i.e. |
Introduction | In this paper, we examine the tradeoffs between relation-specific ( “lexicalized” ) extraction and relation-independent (“unlexicalized”) extraction and reach an analogous conclusion. |
Relation Extraction | To compare the behavior of open, or “unlexicalized,” extraction to relation-specific, or “lexicalized” extraction, we developed a CRF-based extractor under the traditional RE paradigm. |
Abstract | This paper describes how external resources can be used to improve parser performance for heavily lexicalised grammars, looking at both robustness and efficiency. |
Background | In all heavily lexicalised formalisms, such as LTAG, CCG, LPG and HPSG, the lexicon plays a key role in parsing. |
Conclusion | The work reported here shows the benefits that can be gained by utilising external resources to annotate parser input in highly lexicalised grammar for-malisms. |
Conclusion | Even something as simple and readily available (for languages likely to have lexicalised grammars) as a POS tagger can massively increase the parser coverage on unseen text. |
Introduction | Heavily lexicalised grammars have been used in applications such as machine translation and information extraction because they can produce semantic structures which provide more information than less informed parsers. |
Introduction | pf Lexicalised Grammars |
Introduction | improving parser performance in these two areas, by annotating the input given to one such deep parser, the PET parser (Callmeier, 2000), which uses lexicalised grammars developed under the HPSG formalism (Pollard and Sag, 1994). |
Parser Restriction | ing a deep parser with a lexicalised grammar are the precision and depth of the analysis produced, but this depth comes from making many fine distinctions which greatly increases the parser search space, making parsing slow. |
Parser Restriction | Increasing efficiency is important for enabling these heavily lexicalised grammars to bring the benefits of their deep analyses to applications, but simi- |
Unknown Word Handling | These results show very clearly one of the potential drawbacks of using a highly lexicalised grammar formalism like HPSG: unknown words are one of the main causes of parse failure, as quantified in Baldwin et al. |
Experiments | Table l: # of rules used in the testing (61' = 4 , h = 6) (BP: bilingual phrase (used in Moses), TR: tree rule (only 1 tree), TSR: tree sequence rule (> 1 tree), L: fully lexicalized, P: partially lexicalized , U: unlexicalized) |
Experiments | lexicalized rules), in which the lexicalized TSRs model all non-syntactic phrase pairs with rich syntactic information. |
Experiments | It suggests that they are complementary to each other since the lexicalized TSRs are used to model non-syntactic phrases while the other two kinds of TSRs can generalize the lexicalized rules to unseen phrases. |
Related Work | (2007) integrate supertags (a kind of lexicalized syntactic description) into the target side of translation model and language mod- |
Related Work | (2006) treat all bilingual phrases as lexicalized tree-to-string rules, including those non-syntactic phrases in training corpus. |
Rule Extraction | We first generate all fully lexicalized source and target tree sequences using a dynamic programming algorithm and then iterate over all generated source and |
Tree Sequence Alignment Model | In addition, we define two new features: 1) the number of lexical words in a rule to control the model’s preference for lexicalized rules over unlexicalized |
Conclusion and Future Work | Lexicalized PCFGs (where head words annotate phrasal nodes) have proved a key tool for high performance PCFG parsing, however its performance is hampered by the sparse lexical dependency exhibited in the Penn Treebank. |
Experiment Setup 4.1 Corpus | We first build a lexicalized frame for the verb break: NPl(he)-V—NP2(door)-PP(with:hammer). |
Experiment Setup 4.1 Corpus | Based on the lexicalized frame, we construct an SCF NPl-NP2-PPwith for break. |
Integration of Syntactic and Lexical Information | Dependency relation (DR): Our way to overcome data sparsity is to break lexicalized frames into lexicalized slots (a.k.a. |
Related Work | Lexicalized frames are usually obtained |
Abstract | In lexicalized grammatical formalisms, it is possible to separate lexical category assignment from the combinatory processes that make use of such categories, such as parsing and realization. |
Background | Changes to the derivations are necessary to reflect the lexicalized treatment of coordination and punctuation assumed by the multi-modal version of CCG that is implemented in OpenCCG. |
Introduction | In lexicalized grammatical formalisms such as Lexicalized Tree Adjoining Grammar (Schabes et al., 1988, LTAG), Combinatory Categorial Grammar (Steedman, 2000, CCG) and Head-Driven Phrase-Structure Grammar (Pollard and Sag, 1994, HPSG), it is possible to separate lexical category assignment — the assignment of informative syntactic categories to linguistic objects such as words or lexical predicates — from the combinatory processes that make use of such categories — such as parsing and surface realization. |
The Approach | Our implementation makes use of three general types of features: lexicalized features, which are simply the names of the parent and child elementary predication nodes, graph structural features, such as the total number of edges emanating from a node, the number of argument and non-argument dependents, and the names of the relations of the dependent nodes to the parent node, and syntactico-semantic attributes of nodes, such as the tense and number. |