Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval

12/28/2020
by   Ivan Montero, et al.
0

Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English. They not only suffer from the shortcomings of non-English document retrieval, but are reliant on language-specific supervision for either the task or translation. We formulate a task setup more realistic to available resources, that circumvents document retrieval to reliably transfer knowledge from English to lower resource languages. Assuming a strong English question answering model or database, we compare and analyze methods that pivot through English: to map foreign queries to English and then English answers back to target language answers. Within this task setup we propose Reranked Multilingual Maximal Inner Product Search (RM-MIPS), akin to semantic similarity retrieval over the English training set with reranking, which outperforms the strongest baselines by 2.7 6.2 over state-of-the-art alternatives in challenging settings: low-resource languages, with extensive distractor data and query distribution misalignment. Circumventing retrieval, our analysis shows this approach offers rapid answer generation to almost any language off-the-shelf, without the need for any additional training data in the target language.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
07/26/2021

One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval

We present CORA, a Cross-lingual Open-Retrieval Answer Generation model ...
research
12/09/2021

Semantic Search as Extractive Paraphrase Span Detection

In this paper, we approach the problem of semantic search by framing the...
research
08/02/2021

ConveRT for FAQ Answering

Knowledgeable FAQ chatbots are a valuable resource to any organization. ...
research
10/14/2021

Cross-Lingual GenQA: A Language-Agnostic Generative Question Answering Approach for Open-Domain Question Answering

Open-Retrieval Generative Question Answering (GenQA) is proven to delive...
research
07/06/2022

Ask Me What You Need: Product Retrieval using Knowledge from GPT-3

As online merchandise become more common, many studies focus on embeddin...
research
02/20/2021

Multilingual Answer Sentence Reranking via Automatically Translated Data

We present a study on the design of multilingual Answer Sentence Selecti...
research
09/26/2016

Learning to Translate for Multilingual Question Answering

In multilingual question answering, either the question needs to be tran...

Please sign up or login with your details

Forgot password? Click here to reset