Computational Knowledge Engine

NLTK: Natural Language Processing made easy

NLTK: Natural Language Processing made easy

View more presentations from outsider2.

AuthorMapper – Linguistics – Scientific Author Locations

AuthorMapper – Linguistics – Scientific Author Locations

Making sense of number sense

Gorard. (2006). Using everyday numbers effectively in research.


Simply put, quantitative approach refers to research methods based on evidence in the form of numbers or measures, while qualitative approach refers to those in the form of texts and narrations. However, treating them as separate 'paradigms' is not a good thing. I think the field of LT (Language Technology ) should be more open to work that mixes data of all kinds in searching for better solutions.

Starting quantitative research with statistics can be off-putting for newcomers with anxieties about mathematics. This may worsen the situation. A potential way out, could be to promote the sense of numbers, to realize how the kind of simple numeric techniques we use daily are of considerable value in our research as well. This is what this book seeks to do. Interesting.

python programming for linguists

python for linguists

View SlideShare presentation or Upload your own.

Digression analysis in text ?

People seem to go away from the topic from time to time. Quite often they are adding information to or expanding on the topic, to help the listeners, to think. (or prevent them from clear thinking. ) That is, what they say doesn't always fit into the logical flow of the utterance. This may be a kind of important information for text miner. So what are the cues for digression? As a lecturer, I may say "well, now, let's stop here for a second", "That reminds me ...", "By the way", etc. And when to back to the main topic? "Now, let's return to ..", "Anyway, ..", "Getting back to the subject ...". In order to get a full comprehension, it'd be better not to ignore these, but, how can we let machine learn this?

Hanzi, Hanzi, Hanzi!

How to deal with Chinese character-word mystery in terms of (western) linguistic morphology?

1. In principle, each character stands for a morpheme (morpho-semantically). Exceptions are 葡萄、踟躕、... where two characters are born to tie together.
In these cases, a morpheme 葡萄 is represented by two characters 葡 and 萄, respectively.

2. The types of morphemes that the character stand for vary. E.g., 今: bound root morpheme; 者: bound suffix; 打: free root morpheme; 了: inflectional
morpheme (?).

3. A Chinese word is composed of some possible combinations like (1) morpheme + word 辛苦 (2) word + morpheme  打字機 (3)  morpheme  喝 (4)
morpheme + morpheme 前進

4. A Chinese compound word is composed of (at least) two words/compound words. Formally, (1) w1+w2+.....電腦 (2) cw1+w2 ...電腦螢幕

5. Criteria of the judgement of Chinese wordhood:
5.1 Stand alone in the similar semantic context
5.2 Psychological reality
5.3 Proper name and fixed expressions

6. Operation:

7. Dubious/counter-intuitive cases:  腳踏車 a word or a compound word?