Báo cáo khoa học: "Learning Context-Dependent Mappings from Sentences to Logical Form" doc

... from( x, bos) ∧ to( x, phi) ∧ dur ing(x, morning) Some parts of this logical form (from( x, bos) and to( x, phi)) depend on the context. They have to be recovered from the previous logical forms. At ... arguments to the left. Using these rules, we can parse the following phrase: flights to boston N (N\N)/NP NP λx.flight(x) λy .λf.λx.f (x) ∧ to( x, y) boston > (N\N) λf.λx.f(x...

Ngày tải lên: 23/03/2014, 16:21

... is from 5 to 7 in the natural logarithmic scale, which corresponds to about 1.5 minutes to 30 minutes. The other is from 14 to 17 in the natural logarithmic scale, which corresponds to about ... Fortemps, 1997), but these make no attempt to collect hu- man judgments on such durations or learn to ex- tract them automatically from texts.) 2 Inter-Annotator Agreement Al...

Ngày tải lên: 20/02/2014, 12:20

... sentence- aligned parallel data, which can be costly to obtain and difficult to scale to many languages. On the other hand, our model does not require sentences to be aligned. Moreover, since the complexity ... Linguistics Learning Common Grammar from Multilingual Corpus Tomoharu Iwata Daichi Mochihashi NTT Communication Science Laboratories 2-4 Hikaridai, Seika-cho, Soraku-gun, Ky...

Ngày tải lên: 07/03/2014, 22:20

... rules to identify con- joined event pairs. 1000 pairs were annotated by two annotators and adjudicated by a third. Table 1 S ADVP RB Then NP PRP they VP VP CC VP VBD took NP DT the NN art PP TO to NP NNP Acapulco and began SVBD VP TO to VP VB trade NP some ... VP VBD took NP DT the NN art PP TO to NP NNP Acapulco and began SVBD VP TO to VP VB trade NP some of it PP for cocaine Figur...

Ngày tải lên: 08/03/2014, 01:20

... Corporation Midtown Tower, 9-7-1 Akasaka, Minato-ku, Tokyo 107-6211, Japan {smakimot,kuchiumi,msassano}@yahoo-corp.jp Abstract As the web grows larger, knowledge ac- quisition from the web has ... devel- oped to help elicit knowledge from query logs. These algorithms use contextual patterns to extract a category or a relation in order to learn a target in- stance which belongs to...

Ngày tải lên: 08/03/2014, 01:20

... order to explore system robustness to heuristically chosen seed lexi- cons, we automatically extracted a seed lexicon sim- ilarly to Koehn and Knight (2002): we ran EDIT- DIST on EN-ES-D and took ... were purely morphological errors (e.g. airport to aeropuertos), 30 were semantically related (e.g. basketball to b ´ eisbol), 15 were words with strong orthographic similarities (e.g. c...

Ngày tải lên: 31/03/2014, 00:20

... from corpora. The EX approach aims to construct a large and up -to- date transliteration lexicon from live corpora. Towards this objective, some have proposed extracting translation pairs from ... English graphemes to phonemes, referred to as the letter -to- sound transformation, then syllabify the phoneme sequence into a syllable sequence. For this method, a letter -to- s...

Ngày tải lên: 31/03/2014, 01:20

... are modeled as functions tr from source to target tense. Precision figures give the proportion of source tense tokens ts that the strategy correctly translates to target tense tt, recall ... Transducers Two partial parsers (rather: transducers) are used to detect English and German CVPs and to translate them into predicate argument structures (verb chains). The parsers...

Ngày tải lên: 31/03/2014, 04:20

... flexible programmatic access to the data, allowing users to write clients to customize and automate access directly from their simulation software, systems biology platforms, tools or databases [25]. ... developed to advise on the mini- mum requirements to follow in the storage and dis- semination of experimental data in fields such as transcriptomics and proteomics, which will ulti...

Ngày tải lên: 18/02/2014, 04:20

... translating the topology of a phrase tree into a corresponding de- pendency tree, and (ii) a procedure as- signing analytical functions to the nodes of the dependency tree. Apart from an outline ... parties intend to share the resources they create. Prior to this exchange, 10,000 words from the LDC Arabic Newswire A Corpus were manually annotated in both syntactic styles as a step...

Ngày tải lên: 22/02/2014, 02:20