In this work, we address the problem of assessing and constructing feedback for early-stage writing automatically using machine learning. Early-stage writing is typically vastly different from conventional writing due to phonetic spelling and lack of proper grammar, punctuation, spacing etc. Consequently, early-stage writing is highly non-trivial to analyze using common linguistic metrics. We propose to use sequence-to-sequence models for "translating" early-stage writing by students into "conventional" writing, which allows the translated text to be analyzed using linguistic metrics. Furthermore, we propose a novel robust likelihood to mitigate the effect of noise in the dataset. We investigate the proposed methods using a set of numerical experiments and demonstrate that the conventional text can be predicted with high accuracy.
Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and improving large language models (LLMs) is its reward model, trained using human feedback on model outputs. In machine translation (MT), where metrics trained from human annotations can readily be used as reward models, recent methods using minimum Bayes risk decoding and reranking have succeeded in improving the final quality of translation. In this study, we comprehensively explore and compare techniques for integrating quality metrics as reward models into the MT pipeline. This includes using the reward model for data filtering, during the training phase through RL, and at inference time by employing reranking techniques, and we assess the effects of combining these in a unified approach. Our experimental results, conducted across multiple translation tasks, underscore the crucial role of effective data filtering, based on estimated quality, in harnessing the full potential of RL in enhancing MT quality. Furthermore, our findings demonstrate the effectiveness of combining RL training with reranking techniques, showcasing substantial improvements in translation quality.
We present SentAlign, an accurate sentence alignment tool designed to handle very large parallel document pairs. Given user-defined parameters, the alignment algorithm evaluates all possible alignment paths in fairly large documents of thousands of sentences and uses a divide-and-conquer approach to align documents containing tens of thousands of sentences. The scoring function is based on LaBSE bilingual sentence representations. SentAlign outperforms five other sentence alignment tools when evaluated on two different evaluation sets, German-French and English-Icelandic, and on a downstream machine translation task.
Pre-trained language models (PLMs) show impressive performance in various downstream NLP tasks. However, pre-training large language models demands substantial memory and training compute. Furthermore, due to the substantial resources required, many PLM weights are confidential. Consequently, users are compelled to share their data with model owners for fine-tuning specific tasks. To overcome the limitations, we introduce Plug-in External Memory Adaptation (PEMA), a Parameter-Efficient Fine-Tuning (PEFT) method, enabling PLM fine-tuning without requiring access to all the weights. PEMA integrates with context representations from test data during inference to perform downstream tasks. It uses external memory to store PLM-generated context representations mapped with target tokens. Our method utilizes weight matrices of LoRA-like bottlenecked adapter in the PLM's final layer to enhance efficiency. Our approach also includes Gradual Unrolling, a novel interpolation strategy to improve generation quality. We validate PEMA's effectiveness through experiments on syntactic and real datasets for machine translation and style transfer. Our findings show that PEMA outperforms other PEFT approaches in memory and latency efficiency for training, and also excels in maintaining sentence meaning and generating appropriate language and styles.
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to a new language, allowing for translation between the newly added and all of the already supported languages in a challenging scenario: using only a parallel corpus between the new language and English. Previous approaches, such as continued training on parallel data including the new language, suffer from catastrophic forgetting (i.e., performance on other languages is reduced). Our novel approach Imit-MNMT treats the task as an imitation learning process, which mimicks the behavior of an expert, a technique widely used in the computer vision area, but not well explored in NLP. More specifically, we construct a pseudo multi-parallel corpus of the new and the original languages by pivoting through English, and imitate the output distribution of the original MNMT model. Extensive experiments show that our approach significantly improves the translation performance between the new and the original languages, without severe catastrophic forgetting. We also demonstrate that our approach is capable of solving copy and off-target problems, which are two common issues existence in current large-scale MNMT models.
Generative Large Language Models (LLMs) have achieved remarkable advancements in various NLP tasks. In this work, our aim is to explore the multilingual capabilities of large language models by using machine translation as a task involving English and 22 Indian languages. We first investigate the translation capabilities of raw large language models, followed by exploring the in-context learning capabilities of the same raw models. We fine-tune these large language models using parameter efficient fine-tuning methods such as LoRA and additionally with full fine-tuning. Through our study, we have identified the best performing large language model for the translation task involving LLMs, which is based on LLaMA. Our results demonstrate significant progress, with average BLEU scores of 13.42, 15.93, 12.13, 12.30, and 12.07, as well as CHRF scores of 43.98, 46.99, 42.55, 42.42, and 45.39, respectively, using 2-stage fine-tuned LLaMA-13b for English to Indian languages on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Similarly, for Indian languages to English, we achieved average BLEU scores of 14.03, 16.65, 16.17, 15.35 and 12.55 along with chrF scores of 36.71, 40.44, 40.26, 39.51, and 36.20, respectively, using fine-tuned LLaMA-13b on IN22 (conversational), IN22 (general), flores200-dev, flores200-devtest, and newstest2019 testsets. Overall, our findings highlight the potential and strength of large language models for machine translation capabilities, including for languages that are currently underrepresented in LLMs.
Machine Translation (MT) continues to improve in quality and adoption, yet the inadvertent perpetuation of gender bias remains a significant concern. Despite numerous studies into gender bias in translations from gender-neutral languages such as Turkish into more strongly gendered languages like English, there are no benchmarks for evaluating this phenomenon or for assessing mitigation strategies. To address this gap, we introduce GATE X-E, an extension to the GATE (Rarrick et al., 2023) corpus, that consists of human translations from Turkish, Hungarian, Finnish, and Persian into English. Each translation is accompanied by feminine, masculine, and neutral variants for each possible gender interpretation. The dataset, which contains between 1250 and 1850 instances for each of the four language pairs, features natural sentences with a wide range of sentence lengths and domains, challenging translation rewriters on various linguistic phenomena. Additionally, we present an English gender rewriting solution built on GPT-3.5 Turbo and use GATE X-E to evaluate it. We open source our contributions to encourage further research on gender debiasing.
It has been widely observed that exact or approximate MAP (mode-seeking) decoding from natural language generation (NLG) models consistently leads to degenerate outputs (Holtzman et al., 2019; Stahlberg and Byrne, 2019). Prior work has attributed this behavior to either a fundamental and unavoidable inadequacy of modes in probabilistic models or weaknesses in language modeling. Contrastingly, we argue that degenerate modes can even occur in the absence of any modeling error, due to contamination of the training data. Specifically, we argue that mixing even a tiny amount of low-entropy noise with a population text distribution can cause the data distribution's mode to become degenerate. We therefore propose to apply MAP decoding to the model's true conditional distribution where the conditioning variable explicitly avoids specific degenerate behavior. Using exact search, we empirically verify that the length-conditional modes of machine translation models and language models are indeed more fluent and topical than their unconditional modes. For the first time, we also share many examples of exact modal sequences from these models, and from several variants of the LLaMA-7B model. Notably, we observe that various kinds of degenerate modes persist, even at the scale of LLaMA-7B. Although we cannot tractably address these degeneracies with exact search, we perform a classifier-based approximate search on LLaMA-7B, a model which was not trained for instruction following, and find that we are able to elicit reasonable outputs without any finetuning.
We propose the on-the-fly ensembling of a machine translation model with an LLM, prompted on the same task and input. We perform experiments on 4 language pairs (both directions) with varying data amounts. We find that a slightly weaker-at-translation LLM can improve translations of a NMT model, and ensembling with an LLM can produce better translations than ensembling two stronger MT models. We combine our method with various techniques from LLM prompting, such as in context learning and translation context.
Compositional generalisation (CG), in NLP and in machine learning more generally, has been assessed mostly using artificial datasets. It is important to develop benchmarks to assess CG also in real-world natural language tasks in order to understand the abilities and limitations of systems deployed in the wild. To this end, our GenBench Collaborative Benchmarking Task submission utilises the distribution-based compositionality assessment (DBCA) framework to split the Europarl translation corpus into a training and a test set in such a way that the test set requires compositional generalisation capacity. Specifically, the training and test sets have divergent distributions of dependency relations, testing NMT systems' capability of translating dependencies that they have not been trained on. This is a fully-automated procedure to create natural language compositionality benchmarks, making it simple and inexpensive to apply it further to other datasets and languages. The code and data for the experiments is available at https://github.com/aalto-speech/dbca.
The widespread adoption of large language models (LLMs) across diverse AI applications is proof of the outstanding achievements obtained in several tasks, such as text mining, text generation, and question answering. However, LLMs are not exempt from drawbacks. One of the most concerning aspects regards the emerging problematic phenomena known as "Hallucinations". They manifest in text generation systems, particularly in question-answering systems reliant on LLMs, potentially resulting in false or misleading information propagation. This paper delves into the underlying causes of AI hallucination and elucidates its significance in artificial intelligence. In particular, Hallucination classification is tackled over several tasks (Machine Translation, Question and Answer, Dialog Systems, Summarisation Systems, Knowledge Graph with LLMs, and Visual Question Answer). Additionally, we explore potential strategies to mitigate hallucinations, aiming to enhance the overall reliability of LLMs. Our research addresses this critical issue within the HeReFaNMi (Health-Related Fake News Mitigation) project, generously supported by NGI Search, dedicated to combating Health-Related Fake News dissemination on the Internet. This endeavour represents a concerted effort to safeguard the integrity of information dissemination in an age of evolving AI technologies.
Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive. We show how the recently developed Reinforcement Learning technique, Direct Preference Optimization (DPO), can fine-tune MLLMs to get the gains of MBR without any additional computation in inference. Our method uses only a small monolingual fine-tuning set and yields significantly improved performance on multiple NMT test sets compared to MLLMs without DPO.
Recent advancements in natural language processing have led to the proliferation of large language models (LLMs). These models have been shown to yield good performance, using in-context learning, even on tasks and languages they are not trained on. However, their performance on African languages is largely understudied relative to high-resource languages. We present an analysis of four popular large language models (mT0, Aya, LLaMa 2, and GPT-4) on six tasks (topic classification, sentiment classification, machine translation, summarization, question answering, and named entity recognition) across 60 African languages, spanning different language families and geographical regions. Our results suggest that all LLMs produce lower performance for African languages, and there is a large gap in performance compared to high-resource languages (such as English) for most tasks. We find that GPT-4 has an average to good performance on classification tasks, yet its performance on generative tasks such as machine translation and summarization is significantly lacking. Surprisingly, we find that mT0 had the best overall performance for cross-lingual QA, better than the state-of-the-art supervised model (i.e. fine-tuned mT5) and GPT-4 on African languages. Similarly, we find the recent Aya model to have comparable result to mT0 in almost all tasks except for topic classification where it outperform mT0. Overall, LLaMa 2 showed the worst performance, which we believe is due to its English and code-centric~(around 98%) pre-training corpus. Our findings confirms that performance on African languages continues to remain a hurdle for the current LLMs, underscoring the need for additional efforts to close this gap.
Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly calibrated for this task. One of the most effective approaches to handling this bias is to adopt a contrastive decoding objective, which accounts for the prior probability of generating the next token by conditioning on some context. This work introduces an Anti-Language Model objective with a decay factor designed to address the weaknesses of In-context Machine Translation. We conduct our experiments across 3 model types and sizes, 3 language directions, and for both greedy decoding and beam search ($B=5$). The proposed method outperforms other state-of-art decoding objectives, with up to $20$ BLEU point improvement from the default objective observed in some settings.
Large language models (LLMs) have become increasingly prominent in academia and industry due to their remarkable performance in diverse applications. As these models evolve with increasing parameters, they excel in tasks like sentiment analysis and machine translation. However, even models with billions of parameters face challenges in tasks demanding multi-step reasoning. Code generation and comprehension, especially in C and C++, emerge as significant challenges. While LLMs trained on code datasets demonstrate competence in many tasks, they struggle with rectifying non-compilable C and C++ code. Our investigation attributes this subpar performance to two primary factors: the quality of the training dataset and the inherent complexity of the problem which demands intricate reasoning. Existing "Chain of Thought" (CoT) prompting techniques aim to enhance multi-step reasoning. This approach, however, retains the limitations associated with the latent drawbacks of LLMs. In this work, we propose CompCodeVet, a compiler-guided CoT approach to produce compilable code from non-compilable ones. Diverging from the conventional approach of utilizing larger LLMs, we employ compilers as a teacher to establish a more robust zero-shot thought process. The evaluation of CompCodeVet on two open-source code datasets shows that CompCodeVet has the ability to improve the training dataset quality for LLMs.
Added toxicity in the context of translation refers to the fact of producing a translation output with more toxicity than there exists in the input. In this paper, we present MinTox which is a novel pipeline to identify added toxicity and mitigate this issue which works at inference time. MinTox uses a toxicity detection classifier which is multimodal (speech and text) and works in languages at scale. The mitigation method is applied to languages at scale and directly in text outputs. MinTox is applied to SEAMLESSM4T, which is the latest multimodal and massively multilingual machine translation system. For this system, MinTox achieves significant added toxicity mitigation across domains, modalities and language directions. MinTox manages to approximately filter out from 25% to 95% of added toxicity (depending on the modality and domain) while keeping translation quality.
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and testing: e.g., the wait-k testing model consistently trained with wait-k is much worse than that model inconsistently trained with wait-k' (k' is not equal to k) in terms of translation quality. To this end, we first investigate the underlying reasons behind this phenomenon and uncover the following two factors: 1) the limited correlation between translation quality and training (cross-entropy) loss; 2) exposure bias between training and testing. Based on both reasons, we then propose an effective training approach called context consistency training accordingly, which makes consistent the context usage between training and testing by optimizing translation quality and latency as bi-objectives and exposing the predictions to the model during the training. The experiments on three language pairs demonstrate our intuition: our system encouraging context consistency outperforms that existing systems with context inconsistency for the first time, with the help of our context consistency training approach.
In cross-lingual language understanding, machine translation is often utilized to enhance the transferability of models across languages, either by translating the training data from the source language to the target, or from the target to the source to aid inference. However, in cross-lingual machine reading comprehension (MRC), it is difficult to perform a deep level of assistance to enhance cross-lingual transfer because of the variation of answer span positions in different languages. In this paper, we propose X-STA, a new approach for cross-lingual MRC. Specifically, we leverage an attentive teacher to subtly transfer the answer spans of the source language to the answer output space of the target. A Gradient-Disentangled Knowledge Sharing technique is proposed as an improved cross-attention block. In addition, we force the model to learn semantic alignments from multiple granularities and calibrate the model outputs with teacher guidance to enhance cross-lingual transferability. Experiments on three multi-lingual MRC datasets show the effectiveness of our method, outperforming state-of-the-art approaches.
Computer-assisted methods have emerged as valuable tools for retrosynthesis analysis. However, quantifying the plausibility of generated retrosynthesis routes remains a challenging task. We introduce Retro-BLEU, a statistical metric adapted from the well-established BLEU score in machine translation, to evaluate the plausibility of retrosynthesis routes based on reaction template sequences analysis. We demonstrate the effectiveness of Retro-BLEU by applying it to a diverse set of retrosynthesis routes generated by state-of-the-art algorithms and compare the performance with other evaluation metrics. The results show that Retro-BLEU is capable of differentiating between plausible and implausible routes. Furthermore, we provide insights into the strengths and weaknesses of Retro-BLEU, paving the way for future developments and improvements in this field.
Massively multilingual machine translation models allow for the translation of a large number of languages with a single model, but have limited performance on low- and very-low-resource translation directions. Pivoting via high-resource languages remains a strong strategy for low-resource directions, and in this paper we revisit ways of pivoting through multiple languages. Previous work has used a simple averaging of probability distributions from multiple paths, but we find that this performs worse than using a single pivot, and exacerbates the hallucination problem because the same hallucinations can be probable across different paths. We also propose MaxEns, a novel combination strategy that makes the output biased towards the most confident predictions, hypothesising that confident predictions are less prone to be hallucinations. We evaluate different strategies on the FLORES benchmark for 20 low-resource language directions, demonstrating that MaxEns improves translation quality for low-resource languages while reducing hallucination in translations, compared to both direct translation and an averaging approach. On average, multi-pivot strategies still lag behind using English as a single pivot language, raising the question of how to identify the best pivoting strategy for a given translation direction.