Language models (LMs) exhibit remarkable abilities to solve new tasks from just a few examples or textual instructions, especially at scale. They also, paradoxically, struggle with basic functionality, such as arithmetic or factual lookup, where much simpler and smaller models excel. In this paper, we show that LMs can teach themselves to use external tools via simple APIs and achieve the best of both worlds. We introduce Toolformer, a model trained to decide which APIs to call, when to call them, what arguments to pass, and how to best incorporate the results into future token prediction. This is done in a self-supervised way, requiring nothing more than a handful of demonstrations for each API. We incorporate a range of tools, including a calculator, a Q\&A system, two different search engines, a translation system, and a calendar. Toolformer achieves substantially improved zero-shot performance across a variety of downstream tasks, often competitive with much larger models, without sacrificing its core language modeling abilities.

Providing access to information across languages has been a goal of Information Retrieval (IR) for decades. While progress has been made on Cross Language IR (CLIR) where queries are expressed in one language and documents in another, the multilingual (MLIR) task to create a single ranked list of documents across many languages is considerably more challenging. This paper investigates whether advances in neural document translation and pretrained multilingual neural language models enable improvements in the state of the art over earlier MLIR techniques. The results show that although combining neural document translation with neural ranking yields the best Mean Average Precision (MAP), 98% of that MAP score can be achieved with an 84% reduction in indexing time by using a pretrained XLM-R multilingual language model to index documents in their native language, and that 2% difference in effectiveness is not statistically significant. Key to achieving these results for MLIR is to fine-tune XLM-R using mixed-language batches from neural translations of MS MARCO passages.

Google Translate is getting an AI-powered upgrade in the coming weeks to help you find more accurate translations, particularly for words with multiple definitions. The app will offer additional contextual translation options with descriptions and examples. Let's say you're looking for a translation of the word "row," which has multiple meanings in English. It could refer to an argument, a line of seats on a plane or using an oar to propel a boat. Google Translate should soon offer translations for all of those variants, along with examples of how they're used.

Simultaneous translation is a task in which translation begins before the speaker has finished speaking. In its evaluation, we have to consider the latency of the translation in addition to the quality. The latency is preferably as small as possible for users to comprehend what the speaker says with a small delay. Existing latency metrics focus on when the translation starts but do not consider adequately when the translation ends. This means such metrics do not penalize the latency caused by a long translation output, which actually delays users' comprehension. In this work, we propose a novel latency evaluation metric called Average Token Delay (ATD) that focuses on the end timings of partial translations in simultaneous translation. We discuss the advantage of ATD using simulated examples and also investigate the differences between ATD and Average Lagging with simultaneous translation experiments.

Improving machine translation (MT) systems with translation memories (TMs) is of great interest to practitioners in the MT community. However, previous approaches require either a significant update of the model architecture and/or additional training efforts to make the models well-behaved when TMs are taken as additional input. In this paper, we present a simple but effective method to introduce TMs into neural machine translation (NMT) systems. Specifically, we treat TMs as prompts to the NMT model at test time, but leave the training process unchanged. The result is a slight update of an existing NMT system, which can be implemented in a few hours by anyone who is familiar with NMT. Experimental results on several datasets demonstrate that our system significantly outperforms strong baselines.

Nearest neighbor machine translation augments the Autoregressive Translation~(AT) with $k$-nearest-neighbor retrieval, by comparing the similarity between the token-level context representations of the target tokens in the query and the datastore. However, the token-level representation may introduce noise when translating ambiguous words, or fail to provide accurate retrieval results when the representation generated by the model contains indistinguishable context information, e.g., Non-Autoregressive Translation~(NAT) models. In this paper, we propose a novel $n$-gram nearest neighbor retrieval method that is model agnostic and applicable to both AT and NAT models. Specifically, we concatenate the adjacent $n$-gram hidden representations as the key, while the tuple of corresponding target tokens is the value. In inference, we propose tailored decoding algorithms for AT and NAT models respectively. We demonstrate that the proposed method consistently outperforms the token-level method on both AT and NAT models as well on general as on domain adaptation translation tasks. On domain adaptation, the proposed method brings $1.03$ and $2.76$ improvements regarding the average BLEU score on AT and NAT models respectively.

Sign language gloss translation aims to translate the sign glosses into spoken language texts, which is challenging due to the scarcity of labeled gloss-text parallel data. Back translation (BT), which generates pseudo-parallel data by translating in-domain spoken language texts into sign glosses, has been applied to alleviate the data scarcity problem. However, the lack of large-scale high-quality domain spoken language text data limits the effect of BT. In this paper, to overcome the limitation, we propose a Prompt based domain text Generation (PGEN) approach to produce the large-scale in-domain spoken language text data. Specifically, PGEN randomly concatenates sentences from the original in-domain spoken language text data as prompts to induce a pre-trained language model (i.e., GPT-2) to generate spoken language texts in a similar style. Experimental results on three benchmarks of sign language gloss translation in varied languages demonstrate that BT with spoken language texts generated by PGEN significantly outperforms the compared methods. In addition, as the scale of spoken language texts generated by PGEN increases, the BT technique can achieve further improvements, demonstrating the effectiveness of our approach. We release the code and data for facilitating future research in this field.

With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computation as data becomes available in more languages. However, adding new languages requires updating the vocabulary, which complicates the reuse of embeddings. The question of how to reuse existing models while also making architectural changes to provide capacity for both old and new languages has also not been closely studied. In this work, we introduce three techniques that help speed up effective learning of the new languages and alleviate catastrophic forgetting despite vocabulary and architecture mismatches. Our results show that by (1) carefully initializing the network, (2) applying learning rate scaling, and (3) performing data up-sampling, it is possible to exceed the performance of a same-sized baseline model with 30% computation and recover the performance of a larger model trained from scratch with over 50% reduction in computation. Furthermore, our analysis reveals that the introduced techniques help learn the new directions more effectively and alleviate catastrophic forgetting at the same time. We hope our work will guide research into more efficient approaches to growing languages for these MMT models and ultimately maximize the reuse of existing models.

Training end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains. One practical solution to the data scarcity issue is to convert text-based machine translation (MT) data to ST data via textto-speech (TTS) systems.Yet, using TTS systems can be tedious and slow. In this work, we propose SpokenVocab, a simple, scalable and effective data augmentation technique to convert MT data to ST data on-the-fly. The idea is to retrieve and stitch audio snippets, corresponding to words in an MT sentence, from a spoken vocabulary bank. Our experiments on multiple language pairs show that stitched speech helps to improve translation quality by an average of 1.83 BLEU score, while performing equally well as TTS-generated speech in improving translation quality. We also Figure 1: Overview of generating synthetic speech showcase how SpokenVocab can be applied in from SpokenVocab on-the-fly. The first step is to prepare code-switching ST for which often no TTS the SpokenVocab bank offline and the second step systems exit.

Learned metrics such as BLEURT have in recent years become widely employed to evaluate the quality of machine translation systems. Training such metrics requires data which can be expensive and difficult to acquire, particularly for lowerresource languages. We show how knowledge can be distilled from Large Language Models (LLMs) to improve upon such learned metrics without requiring human annotators, by creating synthetic datasets which can be mixed into existing datasets, requiring only a corpus of text in the target language. We show that the performance of a BLEURT-like model on lower resource languages can be improved in this way. A machine translation system is typically evaluated by comparing its output on a given input sentence with one made by a professional translator. Until recently, commonly used metrics such as BLEU (Papineni et al., 2002b) and ROGUE (Lin, 2004) were generally based on number of co-occurring n-grams. Advantages of such methods include that they are easy to interpret, do not require learning from data, and have been shown to generally correlate with human judgement when averaged over a corpus of sentences. Nonetheless, these approaches fail when sentences are semantically similar but differ significantly in phrasing.