Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911988406288384 |
|---|---|
| author | Ilani, Roy Karidi, Taelin Abend, Omri |
| author_facet | Ilani, Roy Karidi, Taelin Abend, Omri |
| contents | While cross-linguistic model transfer is effective in many settings, there is still limited understanding of the conditions under which it works. In this paper, we focus on assessing the role of lexical semantics in cross-lingual transfer, as we compare its impact to that of other language properties. Examining each language property individually, we systematically analyze how differences between English and a target language influence the capacity to align the language with an English pretrained representation space. We do so by artificially manipulating the English sentences in ways that mimic specific characteristics of the target language, and reporting the effect of each manipulation on the quality of alignment with the representation space. We show that while properties such as the script or word order only have a limited impact on alignment quality, the degree of lexical matching between the two languages, which we define using a measure of translation entropy, greatly affects it. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_07599 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations Ilani, Roy Karidi, Taelin Abend, Omri Computation and Language While cross-linguistic model transfer is effective in many settings, there is still limited understanding of the conditions under which it works. In this paper, we focus on assessing the role of lexical semantics in cross-lingual transfer, as we compare its impact to that of other language properties. Examining each language property individually, we systematically analyze how differences between English and a target language influence the capacity to align the language with an English pretrained representation space. We do so by artificially manipulating the English sentences in ways that mimic specific characteristics of the target language, and reporting the effect of each manipulation on the quality of alignment with the representation space. We show that while properties such as the script or word order only have a limited impact on alignment quality, the degree of lexical matching between the two languages, which we define using a measure of translation entropy, greatly affects it. |
| title | Assessing the Role of Lexical Semantics in Cross-lingual Transfer through Controlled Manipulations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2408.07599 |