paper-with-me

홈 › Papers

LAReQA: Language-agnostic answer retrieval from a multilingual pool

2020-04-11 · EMNLP 2020 11 · Uma Roy, Noah Constant, Rami Al-Rfou, Aditya Barua, Aaron Phillips, Yinfei Yang

We present LAReQA, a challenging new benchmark for language-agnostic answer retrieval from a multilingual candidate pool. Unlike previous cross-lingual tasks, LAReQA tests for "strong" cross-lingual alignment, requiring semantically related cross-language pairs to be closer in representation space than unrelated same-language pairs. Building on multilingual BERT (mBERT), we study different strategies for achieving strong alignment. We find that augmenting training data via machine translation is effective, and improves significantly over using mBERT out-of-the-box. Interestingly, the embedding baseline that performs the best on LAReQA falls short of competing baselines on zero-shot variants of our task that only target "weak" alignment. This finding underscores our claim that languageagnostic retrieval is a substantively new kind of cross-lingual evaluation.

📄 PDF Abstract BibTeX arXiv:2004.05484

Code (1)

ziyi-yang/lir

Tasks

Machine TranslationRetrievalTranslation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
mBERT mBERT
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations

2021-09-10 · EMNLP 2021 11 · ZiYi Yang, Yinfei Yang, Daniel Cer, Eric Darve

Language agnostic and semantic-language information isolation is an emerging research direction for multilingual representations models. We explore this problem from a novel angle of geometric algebra and semantic space.…

Cross-Lingual TransferRetrieval

Synergistic Approach for Simultaneous Optimization of Monolingual, Cross-lingual, and Multilingual Information Retrieval

2024-08-20 · Adel Elmahdy, Sheng-Chieh Lin, Amin Ahmad

Information retrieval across different languages is an increasingly important challenge in natural language processing. Recent approaches based on multilingual pre-trained language models have achieved remarkable success…

Information RetrievalRetrieval

The Multilingual Curse at the Retrieval Layer: Evidence from Amharic

2026-05-23 · Yosef Worku Alemneh, Kidist Amde Mekonnen, Maarten de Rijke arxiv

Multilingual retrieval increasingly underpins cross-lingual question answering and retrieval-augmented generation. Strong zero-shot scores on multilingual benchmarks are often taken as evidence that current encoders tran…

Cross-Lingual Question AnsweringPassage Retrieval

Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval

2025-10-10 · Yu Wang, Tianhao Tan, Yifei Wang arxiv

Retrieving relevant instructional videos from multilingual medical archives is crucial for answering complex, multi-hop questions across language boundaries. However, existing systems either compress hour-long videos int…

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

2021-07-26 · NeurIPS 2021 12 · Akari Asai, Xinyan Yu, Jungo Kasai, Hannaneh Hajishirzi

We present Cross-lingual Open-Retrieval Answer Generation (CORA), the first unified many-to-many question answering (QA) model that can answer questions across many languages, even for ones without language-specific anno…

Answer GenerationPassage RetrievalQuestion AnsweringRetrieval+1