2023 Fiscal Year Annual Research Report
Theoretically founded algorithms for the automatic production of analogy tests in NLP
| Project/Area Number |
21K12038
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
LEPAGE YVES 早稲田大学, 理工学術院(情報生産システム研究科・センター), 教授 (70573608)
|
|---|
| Project Period (FY) |
2021-04-01 – 2024-03-31
|
| Keywords | 自然言語処理 / 単語埋め込み表現 / 類推関係 / 推論 |
|---|
| Outline of Annual Research Achievements |
The purpose of the research was to address the lack of analogy test sets to evaluate the quality of vector representations of words or sentences. A concern was to examine solutions applicable to various languages.
A parallelized version of existing tools for integer-valued string representations (task (c) in the proposal) was produced. It was used to study morphological analysis and generation in many languages. It was used to produce various kinds of sentence analogies in many languages, at formal and semantic levels as features like informativeness were used. However, it was shown that casting integer-valued edit distance ratios into real-valued vector representations is a hard problem. In practice, approximations do not permit to find analogies in word embedding spaces (tasks (a) and (b) in the proposal).
So, the project proposed techniques for exhaustive extraction of analogies in word embedding spaces and assessment methods (first sub-problem [EXTRACTALL] in the proposal): produce all possible word analogies that involve words in a given region. To solve analogies between sentences at the semantic level, various neural models were proposed. This led to the production of new sentence semantico-formal or fuzzy analogy test sets not only in English, but also in other languages like Japanese, German or Upper-Sorbian (second sub-problem [SEM&FORM] in the proposal).
An important outcome of the project is the discovery of a new formalisation of analogy between non-negative real numbers. This is a very promising direction to explore analogy in vector representations.
|
-
-
-
[Presentation] Analogie et moyenne generalisee2024
Author(s)
Y. Lepage and M. Couceiro
Organizer
In Actes de la conference Journees d'intelligence artificielle francaises -- Plateforme francaise d'intelligence artificielle (PFIA-JIAF 2024) (Accepted, to appear)
Int'l Joint Research
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
