Báo cáo khoa học: "Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing" docx

... Linguistics Exploiting Web-Derived Selectional Preference to Improve Statistical Dependency Parsing Guangyou Zhou, Jun Zhao ∗ , Kang Liu, and Li Cai National Laboratory of Pattern Recognition Institute of Automation, ... in- corporates the web-derived selectional preferences to improve statistical dependency parsing. The re- sults show that web-scale data improves th...

Ngày tải lên: 30/03/2014, 21:20

... human annotators’ “rationales” can produce s ubstantial improvements in catego rization performance (Zaidan et al., 2007). We exp lore methods to auto- matically generate anno tator rational ... learning method to incorpo rat e rationales for document- level sen timent categorization. 3 Automatically Generating Rationales Our goal in the current w ork, is to generate anno- tator rat ion...

Ngày tải lên: 30/03/2014, 21:20

... julio@lsi.uned.es javart@bec.uned.es Abstract Is it possible to use sense inventories to improve Web search results diversity for one word queries? To answer this ques- tion, we focus on two broad-coverage ... different topics within each of the senses. Is it possible to use sense inventories to improve search results for one word queries? To answer 1357 this question, we will...

Ngày tải lên: 20/02/2014, 04:20

... inference to improve event ex- traction. In contrast to Gupta’s work, Liao do not limit themselves to time information for events, but rather use related events and event-type consis- tency to make ... (CLUTO toolkit) 3 is used to divide it into different cohesive subtypes, each of which only contains the entities of the same background. For instance, the Air entities will...

Ngày tải lên: 20/02/2014, 04:20

... the tonal and toneless STW improvements of the MSIME by using the WP identifier and the WSM are (18.9%, 10.1%) and (25.6%, 16.6%), respectively. From Table 3b, the tonal and toneless STW improvements ... to show the tonal and toneless STW accu- racies of a commercial input product (Microsoft Input Method Editor 2003, MSIME), and an optimized bigram model, BiGram (Tsai, 2005), can bot...

Ngày tải lên: 20/02/2014, 12:20

... allow us to describe word order of a projective dependency tree at a local level: in order to describe the linear position of a node, it is sufficient to de- scribe its position towards its ... part which is still to be introduced for the rewriting to be valid. The dot is an unperfect way of representing the current state in a finite state automaton equiv- alent to the re...

Ngày tải lên: 20/02/2014, 18:20

... compared to the static LM, as well as consistent improvements in SMT performance across language pairs (English-Dari and English-Pashto). 1 Introduction While much of the focus in developing a statistical machine ... target sentences in sparse vector spaces defined by their corresponding vocabularies, and relies on a bilingual projection matrix to transform vectors in the target language...

Ngày tải lên: 17/03/2014, 00:20

... NO-ARC is there to move tokens around so each token in β can be compared to all (or some) tokens prior to it. 688 It 1 was 2 in 3 my 4 interest 5 to 6 Root 0 see 7 you 8 SBJ ROOT PRD NMOD PMOD IM NMOD OBJ Transition ... the transition-based approach is that it can use parse history as features to make the next pre- diction. This parse information helps to improve parsing accurac...

Ngày tải lên: 17/03/2014, 00:20

... 2004), with a small improve- ment in accuracy. To write rules for a rule-based analyzer, and to produce an analyzer using machine-learning tech- niques, it is crucial to construct a dependency- analyzed ... a dependency- analyzed corpus to produce a highly accurate dependency analyzer. Thus in this paper, we discuss fundamental sampling strategies for a dependency- analyzed co...

Ngày tải lên: 17/03/2014, 04:20

... coreference sys- tem to bypass the resolution of non-anaphoric noun phrases. Perhaps surprisingly, recent attempts to incorporate automatically acquired anaphoricity in- formation into coreference ... evaluation schemes. Since our goal is to evaluate the effect of anaphoricity infor- mation on coreference resolution, we make no at- tempt to modify our system to adhere to the rules...

Ngày tải lên: 31/03/2014, 03:20