mRobust04: A Multilingual Version of the TREC Robust 2004 Benchmark

Robust 2004 is an information retrieval benchmark whose large number of judgments per query make it a reliable evaluation dataset. In this paper, we present mRobust04, a multilingual version of Robust04 that was translated to 8 languages using Google Translate. We also provide results of three different multilingual retrievers on this dataset. The dataset is available at https://huggingface.co/datasets/unicamp-dl/mrobust

MonoByte: A Pool of Monolingual Byte-level Language Models

The zero-shot cross-lingual ability of models pretrained on multilingual and even monolingual corpora has spurred many hypotheses to explain this intriguing empirical result. However, due to the costs of pretraining, most research uses public models whose pretraining methodology, such as the choice of tokenization, corpus size, and computational budget, might differ drastically. When researchers pretrain their own models, they often do so under a constrained budget, and the resulting models might underperform significantly compared to SOTA models. These experimental differences led to various inconsistent conclusions about the nature of the cross-lingual ability of these models. To help further research on the topic, we released 10 monolingual byte-level models rigorously pretrained under the same configuration with a large compute budget (equivalent to 420 days on a V100) and corpora that are 4 times larger than the original BERT's. Because they are tokenizer-free, the problem of unseen token embeddings is eliminated, thus allowing researchers to try a wider range of cross-lingual experiments in languages with different scripts. Additionally, we release two models pretrained on non-natural language texts that can be used in sanity-check experiments. Experiments on QA and NLI tasks show that our monolingual models achieve competitive performance to the multilingual one, and hence can be served to strengthen our understanding of cross-lingual transferability in language models.

Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models

The ability to extrapolate, i.e., to make predictions on sequences that are longer than those presented as training examples, is a challenging problem for current deep learning models. Recent work shows that this limitation persists in state-of-the-art Transformer-based models. Most solutions to this problem use specific architectures or training methods that do not generalize to other tasks. We demonstrate that large language models can succeed in extrapolation without modifying their architecture or training procedure. Experimental results show that generating step-by-step rationales and introducing marker tokens are both required for effective extrapolation. First, we induce it to produce step-by-step rationales before outputting the answer to effectively communicate the task to the model. However, as sequences become longer, we find that current models struggle to keep track of token positions. To address this issue, we interleave output tokens with markup tokens that act as explicit positional and counting symbols. Our findings show how these two complementary approaches enable remarkable sequence extrapolation and highlight a limitation of current architectures to effectively generalize without explicit surface form guidance. Code available at https://github.com/MirelleB/induced-rationales-markup-tokens

A Boring-yet-effective Approach for the Product Ranking Task of the Amazon KDD Cup 2022

In this work we describe our submission to the product ranking task of the Amazon KDD Cup 2022. We rely on a receipt that showed to be effective in previous competitions: we focus our efforts towards efficiently training and deploying large language odels, such as mT5, while reducing to a minimum the number of task-specific adaptations. Despite the simplicity of our approach, our best model was less than 0.004 nDCG@20 below the top submission. As the top 20 teams achieved an nDCG@20 close to .90, we argue that we need more difficult e-Commerce evaluation datasets to discriminate retrieval methods.

No Parameter Left Behind: How Distillation and Model Size Affect Zero-Shot Retrieval

Recent work has shown that small distilled language models are strong competitors to models that are orders of magnitude larger and slower in a wide range of information retrieval tasks. This has made distilled and dense models, due to latency constraints, the go-to choice for deployment in real-world retrieval applications. In this work, we question this practice by showing that the number of parameters and early query-document interaction play a significant role in the generalization ability of retrieval models. Our experiments show that increasing model size results in marginal gains on in-domain test sets, but much larger gains in new domains never seen during fine-tuning. Furthermore, we show that rerankers largely outperform dense ones of similar size in several tasks. Our largest reranker reaches the state of the art in 12 of the 18 datasets of the Benchmark-IR (BEIR) and surpasses the previous state of the art by 3 average points. Finally, we confirm that in-domain effectiveness is not a good indicator of zero-shot effectiveness. Code is available at https://github.com/guilhermemr04/scaling-zero-shot-retrieval.git

Billions of Parameters Are Worth More Than In-domain Training Data: A case study in the Legal Case Entailment Task

Recent work has shown that language models scaled to billions of parameters, such as GPT-3, perform remarkably well in zero-shot and few-shot scenarios. In this work, we experiment with zero-shot models in the legal case entailment task of the COLIEE 2022 competition. Our experiments show that scaling the number of parameters in a language model improves the F1 score of our previous zero-shot result by more than 6 points, suggesting that stronger zero-shot capability may be a characteristic of larger models, at least for this task. Our 3B-parameter zero-shot model outperforms all models, including ensembles, in the COLIEE 2021 test set and also achieves the best performance of a single model in the COLIEE 2022 competition, second only to the ensemble composed of the 3B model itself and a smaller version of the same model. Despite the challenges posed by large language models, mainly due to latency constraints in real-time applications, we provide a demonstration of our zero-shot monoT5-3b model being used in production as a search engine, including for legal documents. The code for our submission and the demo of our system are available at https://github.com/neuralmind-ai/coliee and https://neuralsearchx.neuralmind.ai, respectively.

On the ability of monolingual models to learn language-agnostic representations

Pretrained multilingual models have become a de facto default approach for zero-shot cross-lingual transfer. Previous work has shown that these models are able to achieve cross-lingual representations when pretrained on two or more languages with shared parameters. In this work, we provide evidence that a model can achieve language-agnostic representations even when pretrained on a single language. That is, we find that monolingual models pretrained and finetuned on different languages achieve competitive performance compared to the ones that use the same target language. Surprisingly, the models show a similar performance on a same task regardless of the pretraining language. For example, models pretrained on distant languages such as German and Portuguese perform similarly on English tasks.

mMARCO: A Multilingual Version of MS MARCO Passage Ranking Dataset

The MS MARCO ranking dataset has been widely used for training deep learning models for IR tasks, achieving considerable effectiveness on diverse zero-shot scenarios. However, this type of resource is scarce in other languages than English. In this work we present mMARCO, a multilingual version of the MS MARCO passage ranking dataset comprising 8 languages that was created using machine translation. We evaluated mMARCO by fine-tuning mono and multilingual re-ranking models on it. Experimental results demonstrate that multilingual models fine-tuned on our translated dataset achieve superior effectiveness than models fine-tuned on the original English version alone. Also, our distilled multilingual re-ranker is competitive with non-distilled models while having 5.4 times fewer parameters. The translated datasets as well as fine-tuned models are available at https://github.com/unicamp-dl/mMARCO.git.

A cost-benefit analysis of cross-lingual transfer methods

An effective method for cross-lingual transfer is to fine-tune a bilingual or multilingual model on a supervised dataset in one language and evaluating it on another language in a zero-shot manner. Translating examples at training time or inference time are also viable alternatives. However, there are costs associated with these methods that are rarely addressed in the literature. In this work, we analyze cross-lingual methods in terms of their effectiveness (e.g., accuracy), development and deployment costs, as well as their latencies at inference time. Our experiments on three tasks indicate that the best cross-lingual method is highly task-dependent. Finally, by combining zero-shot and translation methods, we achieve the state-of-the-art in two of the three datasets used in this work. Based on these results, we question the need for manually labeled training data in a target language. Code, models and translated datasets are available at https://github.com/unicamp-dl/cross-lingual-analysis

Yes, BM25 is a Strong Baseline for Legal Case Retrieval

We describe our single submission to task 1 of COLIEE 2021. Our vanilla BM25 got second place, well above the median of submissions. Code is available at https://github.com/neuralmind-ai/coliee.