Báo cáo khoa học: "Evaluating Smoothing Algorithms against Plausibility Judgements" potx

... two published algorithms for finding the co-specifiers of pronouns in naturally occurring texts and dia- logues. We present the quantitative results of hand- simulating these algorithms, but ... in some sense, a further specifi- cation of the operation of tile algorithms that must be made in order to hand-simulate the algorithms. There are two major sets of assumptions, based on...

Ngày tải lên: 21/02/2014, 20:20

Ngày tải lên: 20/02/2014, 09:20

... USA {bobmoore,chrisq}@microsoft.com Abstract Kneser-Ney (1995) smoothing and its vari- ants are generally recognized as having the best perplexity of any known method for estimating N-gram language models. Kneser-Ney smoothing, however, ... highest- order model. For some applications, this makes Kneser-Ney smoothing inappropri- ate or inconvenient. In this paper, we in- troduce a new sm...

Ngày tải lên: 20/02/2014, 09:20

... analyses yielding them, and so forth – broadly trading accuracy and greater domain- dependence against speed and reduced sensitivity to domain-specific lexical behaviour (Briscoe and Carroll, ... fine-grained subcategorization infor- mation in the PoS tags and by the need to balance depth of analysis against the size of the deriva- tion space. On the Susanne corpus, the geometric mean of th...

Ngày tải lên: 20/02/2014, 12:20

Ngày tải lên: 22/02/2014, 02:20

... work. §3 presents the implemented grammar of Wambaya, describes its development, and evaluates it against unseen, naturally occurring text. §4 uses the Wambaya grammar and its devel- opment as one ... contribution (in this case, the ARG1 of the ‘proprietive’ relation). 3.4 Evaluation The grammar was evaluated against a sample of nat- urally occurring data taken from one of the texts trans...

Ngày tải lên: 08/03/2014, 01:20

... direct ob- jects, but also subjects and prepositional complements. We evaluate model per- formance against human judgments and show that there is no single method that overall performs best. We explore ... preferences, two types of evaluation are usually conducted: task-based evaluation and comparisons against hu- man judgments. Word sense disambiguation re- sults are reported by Resnik (...

Ngày tải lên: 08/03/2014, 21:20

... complement intrinsic evaluations. For example, NLP com- ponents such as parsers and co-reference resolu- tion algorithms could be compared in terms of how much they contribute to the performance of a textual ... the classification probability is below its confidence threshold. This mapping was then compared against the manually annotated labels to compute the intrin- sic evaluation scores f...

Ngày tải lên: 08/03/2014, 21:20

Ngày tải lên: 21/02/2014, 20:20

... as asking for the truth value of their explicit propositional content. Thus matching this rule against the structure for "Can you speak Spanish?" would produce the interpretations ... plan-hased conversational implicature heuristic [Hinkelman 87], [Hinkelman forthcoming] as a plausibility filter adequate for most common eases. 4. Two Constraints Integrated Section 2 sho...

Ngày tải lên: 21/02/2014, 20:20