Xiaoyu Shen, Adrià de Gispert, Akari Asai, Bill Byrne
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. If it links a repository, it is listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Product Question Answering (PQA) systems are key in e-commerce applications to provide responses to customers' questions as they shop for products. While existing work on PQA focuses mainly on English, in practice there is need to support multiple customer languages while leveraging product information available in English. To study this practical industrial task, we present xPQA, a large-scale annotated cross-lingual PQA dataset in 12 languages across 9 branches, and report results in (1) candidate ranking, to select the best English candidate containing the information to answer a non-English question; and (2) answer generation, to generate a natural-sounding non-English answer based on the selected English candidate. We evaluate various approaches involving machine translation at runtime or offline, leveraging multilingual pre-trained LMs, and including or excluding xPQA training data. We find that (1) In-domain data is essential as cross-lingual rankers trained on other domains perform poorly on the PQA task; (2) Candidate ranking often prefers runtime-translation approaches while answer generation prefers multilingual approaches; (3) Translating offline to augment multilingual models helps candidate ranking mainly on languages with non-Latin scripts; and helps answer generation mainly on languages with Latin scripts. Still, there remains a significant performance gap between the English and the cross-lingual test sets. 1 Question: does the latch come in white? Candidate: it only comes in black … Label: fully answering Answer: no, it comes only in black. Question: a trava vem em branco? Candidate: it only comes in black … Label: fully answering Answer: não, só vem na cor preta Question: é a prova dgua? Candidate: i thought they were waterproof but … Label: fully answering Answer: Não. Eu realmente achei … Question: is it waterproof? Candidate: i thought they were waterproof but … Label: fully answering Answer: do not. I really … Translate question/answer into 12 languages Translate question/answer into English
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2305.09249")
get_code_for_paper("2305.09249")
have("2305.09249")
Connect an agent — have() is free.