Báo cáo khoa học: "Automatic Single-Document Key Fact Extraction from Newswire Articles" potx

... – 3 April 2009. c 2009 Association for Computational Linguistics Automatic Single-Document Key Fact Extraction from Newswire Articles Itamar Kastner Department of Computer Science Queen Mary, ... e.g., (McKeown et al., 1999). Key fact ex- traction falls in between key word extraction and summarization. Here, the challenge is to identify the most relevant facts in a docume...

Ngày tải lên: 24/03/2014, 03:20

... impor- tant terms from the corpus by using Naka- gawa’s method. These extracted terms be- come the candidates for the final step. The final step, filtering step, removes inappro- priate terms from the candidates ... our system, which is proposed in this paper, requires only a seed word; from this seed word, the system compiles a corpus from the Web by using search engines and produces a...

Ngày tải lên: 20/02/2014, 16:20

... the error is coming from or how to correct it. So finding verbs poses a serious challenge for the design of an accu- rate, general-purpose algorithm for detecting SFs. In fact, finding main ... case from the preced- ing verb and hence reveals its presence intran- sitive verbs are harder to find. Likewise, clauses fare better than infinitives because their subjects get case from...

Ngày tải lên: 20/02/2014, 21:20

... Features and tags given to the CRF 3.2 Extraction of Travel Information from Blogs We extracted pairs comprising a location name and a local product from travel blogs, which were identified ... travel blogs. 4.2 Extraction of Travel Information from Blogs Data sets and experimental settings To confirm that travel blogs are a useful informa- tion source for the extraction...

Ngày tải lên: 08/03/2014, 01:20

... to distinguish the frame. Another problem arises from the fact that our cur- rent classifier operates on a predefined set of SCFs. The COMLEX SCFs, from which ours were derived, are extremely incomplete. ... approach to SCF acquisition differs from earlier work in a number of ways. A common strategy in existing systems (e.g. (Briscoe and Carroll, 1997)) is to extract SCFs from parse t...

Ngày tải lên: 08/03/2014, 04:22

... for evaluation. Our German/English base lexicon is derived from the Collins Gem German Dictionary with about 22,300 entries. From this we eliminated all multi-word entries, so 16,380 entries ... established. How- ever, only recently new approaches have been proposed to identify word translations from non-parallel or even unrelated texts. This task is more difficult, because most...

Ngày tải lên: 08/03/2014, 06:20

... type Parse tree path from target to node Features for second stage only Has SUPP Has COP Has GOV Parse tree path from SUPP to node Parse tree path from COP to node Parse tree path from GOV to node Table ... machine or other work station] P LACE , even though a canteen is available. Figure 1: A sentence from the FrameNet example corpus, with FEs bracketed and the target word in itali...

Ngày tải lên: 08/03/2014, 21:20

... are ntis-classified as having non-stative senses. In fact, this result is not very sensitive to raising the minimum progressive frequency from .1% to as high as .6% or .7%, since most verbs ... an artificial learner. This is demonstrated by a program that exploits two par- ticular cues from the linguistic context to classify verbs automatically into those whose sole sense is one ....

Ngày tải lên: 24/03/2014, 05:21

... classification from a linguistically chal- lenging corpus of biomedical texts. The lexical classification resulting from our work is strongly domain-specific (it differs substantially from pre- vious ... as a means to ab- stract away from individual words when required. They are also helpful in many operational contexts where lexical information must be acquired from small application-...

Ngày tải lên: 31/03/2014, 01:20

... paragraph from each report, and arranged the paragraphs in clusters based on the date of issue of the report. We used only the first paragraphs of the news reports because they tend to describe facts ... case of the verb changes to obtain passive cases from the active ones. 2.3 Selecting Typical Pairs At this step, we selected typical pairs of actions from the extracted pairs. First, we...

Ngày tải lên: 31/03/2014, 20:20